diff --git a/.github/workflows/api-tests.yml b/.github/workflows/api-tests.yml index 8173bee58e..7c632f8a34 100644 --- a/.github/workflows/api-tests.yml +++ b/.github/workflows/api-tests.yml @@ -76,7 +76,7 @@ jobs: - name: Run Workflow run: poetry run -C api bash dev/pytest/pytest_workflow.sh - - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale) + - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch) uses: hoverkraft-tech/compose-action@v2.0.0 with: compose-file: | @@ -90,5 +90,6 @@ jobs: pgvecto-rs pgvector chroma + elasticsearch - name: Test Vector Stores run: poetry run -C api bash dev/pytest/pytest_vdb.sh diff --git a/.github/workflows/expose_service_ports.sh b/.github/workflows/expose_service_ports.sh index 3418bf0c6f..ae3e0ee69d 100755 --- a/.github/workflows/expose_service_ports.sh +++ b/.github/workflows/expose_service_ports.sh @@ -6,5 +6,6 @@ yq eval '.services.chroma.ports += ["8000:8000"]' -i docker/docker-compose.yaml yq eval '.services["milvus-standalone"].ports += ["19530:19530"]' -i docker/docker-compose.yaml yq eval '.services.pgvector.ports += ["5433:5432"]' -i docker/docker-compose.yaml yq eval '.services["pgvecto-rs"].ports += ["5431:5432"]' -i docker/docker-compose.yaml +yq eval '.services["elasticsearch"].ports += ["9200:9200"]' -i docker/docker-compose.yaml -echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs." \ No newline at end of file +echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch" \ No newline at end of file diff --git a/.github/workflows/style.yml b/.github/workflows/style.yml index f6092c8633..d681dc6627 100644 --- a/.github/workflows/style.yml +++ b/.github/workflows/style.yml @@ -45,6 +45,10 @@ jobs: if: steps.changed-files.outputs.any_changed == 'true' run: poetry run -C api dotenv-linter ./api/.env.example ./web/.env.example + - name: Ruff formatter check + if: steps.changed-files.outputs.any_changed == 'true' + run: poetry run -C api ruff format --check ./api + - name: Lint hints if: failure() run: echo "Please run 'dev/reformat' to fix the fixable linting errors." diff --git a/api/.env.example b/api/.env.example index cf3a0f302d..775149f8fd 100644 --- a/api/.env.example +++ b/api/.env.example @@ -130,6 +130,12 @@ TENCENT_VECTOR_DB_DATABASE=dify TENCENT_VECTOR_DB_SHARD=1 TENCENT_VECTOR_DB_REPLICAS=2 +# ElasticSearch configuration +ELASTICSEARCH_HOST=127.0.0.1 +ELASTICSEARCH_PORT=9200 +ELASTICSEARCH_USERNAME=elastic +ELASTICSEARCH_PASSWORD=elastic + # PGVECTO_RS configuration PGVECTO_RS_HOST=localhost PGVECTO_RS_PORT=5431 diff --git a/api/app.py b/api/app.py index 50441cb81d..ad219ca0d6 100644 --- a/api/app.py +++ b/api/app.py @@ -1,6 +1,6 @@ import os -if os.environ.get("DEBUG", "false").lower() != 'true': +if os.environ.get("DEBUG", "false").lower() != "true": from gevent import monkey monkey.patch_all() @@ -57,7 +57,7 @@ warnings.simplefilter("ignore", ResourceWarning) if os.name == "nt": os.system('tzutil /s "UTC"') else: - os.environ['TZ'] = 'UTC' + os.environ["TZ"] = "UTC" time.tzset() @@ -70,13 +70,14 @@ class DifyApp(Flask): # ------------- -config_type = os.getenv('EDITION', default='SELF_HOSTED') # ce edition first +config_type = os.getenv("EDITION", default="SELF_HOSTED") # ce edition first # ---------------------------- # Application Factory Function # ---------------------------- + def create_flask_app_with_configs() -> Flask: """ create a raw flask app @@ -92,7 +93,7 @@ def create_flask_app_with_configs() -> Flask: elif isinstance(value, int | float | bool): os.environ[key] = str(value) elif value is None: - os.environ[key] = '' + os.environ[key] = "" return dify_app @@ -100,10 +101,10 @@ def create_flask_app_with_configs() -> Flask: def create_app() -> Flask: app = create_flask_app_with_configs() - app.secret_key = app.config['SECRET_KEY'] + app.secret_key = app.config["SECRET_KEY"] log_handlers = None - log_file = app.config.get('LOG_FILE') + log_file = app.config.get("LOG_FILE") if log_file: log_dir = os.path.dirname(log_file) os.makedirs(log_dir, exist_ok=True) @@ -111,23 +112,24 @@ def create_app() -> Flask: RotatingFileHandler( filename=log_file, maxBytes=1024 * 1024 * 1024, - backupCount=5 + backupCount=5, ), - logging.StreamHandler(sys.stdout) + logging.StreamHandler(sys.stdout), ] logging.basicConfig( - level=app.config.get('LOG_LEVEL'), - format=app.config.get('LOG_FORMAT'), - datefmt=app.config.get('LOG_DATEFORMAT'), + level=app.config.get("LOG_LEVEL"), + format=app.config.get("LOG_FORMAT"), + datefmt=app.config.get("LOG_DATEFORMAT"), handlers=log_handlers, - force=True + force=True, ) - log_tz = app.config.get('LOG_TZ') + log_tz = app.config.get("LOG_TZ") if log_tz: from datetime import datetime import pytz + timezone = pytz.timezone(log_tz) def time_converter(seconds): @@ -162,24 +164,24 @@ def initialize_extensions(app): @login_manager.request_loader def load_user_from_request(request_from_flask_login): """Load user based on the request.""" - if request.blueprint not in ['console', 'inner_api']: + if request.blueprint not in ["console", "inner_api"]: return None # Check if the user_id contains a dot, indicating the old format - auth_header = request.headers.get('Authorization', '') + auth_header = request.headers.get("Authorization", "") if not auth_header: - auth_token = request.args.get('_token') + auth_token = request.args.get("_token") if not auth_token: - raise Unauthorized('Invalid Authorization token.') + raise Unauthorized("Invalid Authorization token.") else: - if ' ' not in auth_header: - raise Unauthorized('Invalid Authorization header format. Expected \'Bearer \' format.') + if " " not in auth_header: + raise Unauthorized("Invalid Authorization header format. Expected 'Bearer ' format.") auth_scheme, auth_token = auth_header.split(None, 1) auth_scheme = auth_scheme.lower() - if auth_scheme != 'bearer': - raise Unauthorized('Invalid Authorization header format. Expected \'Bearer \' format.') + if auth_scheme != "bearer": + raise Unauthorized("Invalid Authorization header format. Expected 'Bearer ' format.") decoded = PassportService().verify(auth_token) - user_id = decoded.get('user_id') + user_id = decoded.get("user_id") account = AccountService.load_logged_in_account(account_id=user_id, token=auth_token) if account: @@ -190,10 +192,11 @@ def load_user_from_request(request_from_flask_login): @login_manager.unauthorized_handler def unauthorized_handler(): """Handle unauthorized requests.""" - return Response(json.dumps({ - 'code': 'unauthorized', - 'message': "Unauthorized." - }), status=401, content_type="application/json") + return Response( + json.dumps({"code": "unauthorized", "message": "Unauthorized."}), + status=401, + content_type="application/json", + ) # register blueprint routers @@ -204,38 +207,36 @@ def register_blueprints(app): from controllers.service_api import bp as service_api_bp from controllers.web import bp as web_bp - CORS(service_api_bp, - allow_headers=['Content-Type', 'Authorization', 'X-App-Code'], - methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH'] - ) + CORS( + service_api_bp, + allow_headers=["Content-Type", "Authorization", "X-App-Code"], + methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"], + ) app.register_blueprint(service_api_bp) - CORS(web_bp, - resources={ - r"/*": {"origins": app.config['WEB_API_CORS_ALLOW_ORIGINS']}}, - supports_credentials=True, - allow_headers=['Content-Type', 'Authorization', 'X-App-Code'], - methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH'], - expose_headers=['X-Version', 'X-Env'] - ) + CORS( + web_bp, + resources={r"/*": {"origins": app.config["WEB_API_CORS_ALLOW_ORIGINS"]}}, + supports_credentials=True, + allow_headers=["Content-Type", "Authorization", "X-App-Code"], + methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"], + expose_headers=["X-Version", "X-Env"], + ) app.register_blueprint(web_bp) - CORS(console_app_bp, - resources={ - r"/*": {"origins": app.config['CONSOLE_CORS_ALLOW_ORIGINS']}}, - supports_credentials=True, - allow_headers=['Content-Type', 'Authorization'], - methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH'], - expose_headers=['X-Version', 'X-Env'] - ) + CORS( + console_app_bp, + resources={r"/*": {"origins": app.config["CONSOLE_CORS_ALLOW_ORIGINS"]}}, + supports_credentials=True, + allow_headers=["Content-Type", "Authorization"], + methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"], + expose_headers=["X-Version", "X-Env"], + ) app.register_blueprint(console_app_bp) - CORS(files_bp, - allow_headers=['Content-Type'], - methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH'] - ) + CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"]) app.register_blueprint(files_bp) app.register_blueprint(inner_api_bp) @@ -245,29 +246,29 @@ def register_blueprints(app): app = create_app() celery = app.extensions["celery"] -if app.config.get('TESTING'): +if app.config.get("TESTING"): print("App is running in TESTING mode") @app.after_request def after_request(response): """Add Version headers to the response.""" - response.set_cookie('remember_token', '', expires=0) - response.headers.add('X-Version', app.config['CURRENT_VERSION']) - response.headers.add('X-Env', app.config['DEPLOY_ENV']) + response.set_cookie("remember_token", "", expires=0) + response.headers.add("X-Version", app.config["CURRENT_VERSION"]) + response.headers.add("X-Env", app.config["DEPLOY_ENV"]) return response -@app.route('/health') +@app.route("/health") def health(): - return Response(json.dumps({ - 'pid': os.getpid(), - 'status': 'ok', - 'version': app.config['CURRENT_VERSION'] - }), status=200, content_type="application/json") + return Response( + json.dumps({"pid": os.getpid(), "status": "ok", "version": app.config["CURRENT_VERSION"]}), + status=200, + content_type="application/json", + ) -@app.route('/threads') +@app.route("/threads") def threads(): num_threads = threading.active_count() threads = threading.enumerate() @@ -278,32 +279,34 @@ def threads(): thread_id = thread.ident is_alive = thread.is_alive() - thread_list.append({ - 'name': thread_name, - 'id': thread_id, - 'is_alive': is_alive - }) + thread_list.append( + { + "name": thread_name, + "id": thread_id, + "is_alive": is_alive, + } + ) return { - 'pid': os.getpid(), - 'thread_num': num_threads, - 'threads': thread_list + "pid": os.getpid(), + "thread_num": num_threads, + "threads": thread_list, } -@app.route('/db-pool-stat') +@app.route("/db-pool-stat") def pool_stat(): engine = db.engine return { - 'pid': os.getpid(), - 'pool_size': engine.pool.size(), - 'checked_in_connections': engine.pool.checkedin(), - 'checked_out_connections': engine.pool.checkedout(), - 'overflow_connections': engine.pool.overflow(), - 'connection_timeout': engine.pool.timeout(), - 'recycle_time': db.engine.pool._recycle + "pid": os.getpid(), + "pool_size": engine.pool.size(), + "checked_in_connections": engine.pool.checkedin(), + "checked_out_connections": engine.pool.checkedout(), + "overflow_connections": engine.pool.overflow(), + "connection_timeout": engine.pool.timeout(), + "recycle_time": db.engine.pool._recycle, } -if __name__ == '__main__': - app.run(host='0.0.0.0', port=5001) +if __name__ == "__main__": + app.run(host="0.0.0.0", port=5001) diff --git a/api/commands.py b/api/commands.py index c7ffb47b51..41f1a6444c 100644 --- a/api/commands.py +++ b/api/commands.py @@ -27,32 +27,29 @@ from models.provider import Provider, ProviderModel from services.account_service import RegisterService, TenantService -@click.command('reset-password', help='Reset the account password.') -@click.option('--email', prompt=True, help='The email address of the account whose password you need to reset') -@click.option('--new-password', prompt=True, help='the new password.') -@click.option('--password-confirm', prompt=True, help='the new password confirm.') +@click.command("reset-password", help="Reset the account password.") +@click.option("--email", prompt=True, help="The email address of the account whose password you need to reset") +@click.option("--new-password", prompt=True, help="the new password.") +@click.option("--password-confirm", prompt=True, help="the new password confirm.") def reset_password(email, new_password, password_confirm): """ Reset password of owner account Only available in SELF_HOSTED mode """ if str(new_password).strip() != str(password_confirm).strip(): - click.echo(click.style('sorry. The two passwords do not match.', fg='red')) + click.echo(click.style("sorry. The two passwords do not match.", fg="red")) return - account = db.session.query(Account). \ - filter(Account.email == email). \ - one_or_none() + account = db.session.query(Account).filter(Account.email == email).one_or_none() if not account: - click.echo(click.style('sorry. the account: [{}] not exist .'.format(email), fg='red')) + click.echo(click.style("sorry. the account: [{}] not exist .".format(email), fg="red")) return try: valid_password(new_password) except: - click.echo( - click.style('sorry. The passwords must match {} '.format(password_pattern), fg='red')) + click.echo(click.style("sorry. The passwords must match {} ".format(password_pattern), fg="red")) return # generate password salt @@ -65,80 +62,87 @@ def reset_password(email, new_password, password_confirm): account.password = base64_password_hashed account.password_salt = base64_salt db.session.commit() - click.echo(click.style('Congratulations! Password has been reset.', fg='green')) + click.echo(click.style("Congratulations! Password has been reset.", fg="green")) -@click.command('reset-email', help='Reset the account email.') -@click.option('--email', prompt=True, help='The old email address of the account whose email you need to reset') -@click.option('--new-email', prompt=True, help='the new email.') -@click.option('--email-confirm', prompt=True, help='the new email confirm.') +@click.command("reset-email", help="Reset the account email.") +@click.option("--email", prompt=True, help="The old email address of the account whose email you need to reset") +@click.option("--new-email", prompt=True, help="the new email.") +@click.option("--email-confirm", prompt=True, help="the new email confirm.") def reset_email(email, new_email, email_confirm): """ Replace account email :return: """ if str(new_email).strip() != str(email_confirm).strip(): - click.echo(click.style('Sorry, new email and confirm email do not match.', fg='red')) + click.echo(click.style("Sorry, new email and confirm email do not match.", fg="red")) return - account = db.session.query(Account). \ - filter(Account.email == email). \ - one_or_none() + account = db.session.query(Account).filter(Account.email == email).one_or_none() if not account: - click.echo(click.style('sorry. the account: [{}] not exist .'.format(email), fg='red')) + click.echo(click.style("sorry. the account: [{}] not exist .".format(email), fg="red")) return try: email_validate(new_email) except: - click.echo( - click.style('sorry. {} is not a valid email. '.format(email), fg='red')) + click.echo(click.style("sorry. {} is not a valid email. ".format(email), fg="red")) return account.email = new_email db.session.commit() - click.echo(click.style('Congratulations!, email has been reset.', fg='green')) + click.echo(click.style("Congratulations!, email has been reset.", fg="green")) -@click.command('reset-encrypt-key-pair', help='Reset the asymmetric key pair of workspace for encrypt LLM credentials. ' - 'After the reset, all LLM credentials will become invalid, ' - 'requiring re-entry.' - 'Only support SELF_HOSTED mode.') -@click.confirmation_option(prompt=click.style('Are you sure you want to reset encrypt key pair?' - ' this operation cannot be rolled back!', fg='red')) +@click.command( + "reset-encrypt-key-pair", + help="Reset the asymmetric key pair of workspace for encrypt LLM credentials. " + "After the reset, all LLM credentials will become invalid, " + "requiring re-entry." + "Only support SELF_HOSTED mode.", +) +@click.confirmation_option( + prompt=click.style( + "Are you sure you want to reset encrypt key pair?" " this operation cannot be rolled back!", fg="red" + ) +) def reset_encrypt_key_pair(): """ Reset the encrypted key pair of workspace for encrypt LLM credentials. After the reset, all LLM credentials will become invalid, requiring re-entry. Only support SELF_HOSTED mode. """ - if dify_config.EDITION != 'SELF_HOSTED': - click.echo(click.style('Sorry, only support SELF_HOSTED mode.', fg='red')) + if dify_config.EDITION != "SELF_HOSTED": + click.echo(click.style("Sorry, only support SELF_HOSTED mode.", fg="red")) return tenants = db.session.query(Tenant).all() for tenant in tenants: if not tenant: - click.echo(click.style('Sorry, no workspace found. Please enter /install to initialize.', fg='red')) + click.echo(click.style("Sorry, no workspace found. Please enter /install to initialize.", fg="red")) return tenant.encrypt_public_key = generate_key_pair(tenant.id) - db.session.query(Provider).filter(Provider.provider_type == 'custom', Provider.tenant_id == tenant.id).delete() + db.session.query(Provider).filter(Provider.provider_type == "custom", Provider.tenant_id == tenant.id).delete() db.session.query(ProviderModel).filter(ProviderModel.tenant_id == tenant.id).delete() db.session.commit() - click.echo(click.style('Congratulations! ' - 'the asymmetric key pair of workspace {} has been reset.'.format(tenant.id), fg='green')) + click.echo( + click.style( + "Congratulations! " "the asymmetric key pair of workspace {} has been reset.".format(tenant.id), + fg="green", + ) + ) -@click.command('vdb-migrate', help='migrate vector db.') -@click.option('--scope', default='all', prompt=False, help='The scope of vector database to migrate, Default is All.') +@click.command("vdb-migrate", help="migrate vector db.") +@click.option("--scope", default="all", prompt=False, help="The scope of vector database to migrate, Default is All.") def vdb_migrate(scope: str): - if scope in ['knowledge', 'all']: + if scope in ["knowledge", "all"]: migrate_knowledge_vector_database() - if scope in ['annotation', 'all']: + if scope in ["annotation", "all"]: migrate_annotation_vector_database() @@ -146,7 +150,7 @@ def migrate_annotation_vector_database(): """ Migrate annotation datas to target vector database . """ - click.echo(click.style('Start migrate annotation data.', fg='green')) + click.echo(click.style("Start migrate annotation data.", fg="green")) create_count = 0 skipped_count = 0 total_count = 0 @@ -154,98 +158,103 @@ def migrate_annotation_vector_database(): while True: try: # get apps info - apps = db.session.query(App).filter( - App.status == 'normal' - ).order_by(App.created_at.desc()).paginate(page=page, per_page=50) + apps = ( + db.session.query(App) + .filter(App.status == "normal") + .order_by(App.created_at.desc()) + .paginate(page=page, per_page=50) + ) except NotFound: break page += 1 for app in apps: total_count = total_count + 1 - click.echo(f'Processing the {total_count} app {app.id}. ' - + f'{create_count} created, {skipped_count} skipped.') + click.echo( + f"Processing the {total_count} app {app.id}. " + f"{create_count} created, {skipped_count} skipped." + ) try: - click.echo('Create app annotation index: {}'.format(app.id)) - app_annotation_setting = db.session.query(AppAnnotationSetting).filter( - AppAnnotationSetting.app_id == app.id - ).first() + click.echo("Create app annotation index: {}".format(app.id)) + app_annotation_setting = ( + db.session.query(AppAnnotationSetting).filter(AppAnnotationSetting.app_id == app.id).first() + ) if not app_annotation_setting: skipped_count = skipped_count + 1 - click.echo('App annotation setting is disabled: {}'.format(app.id)) + click.echo("App annotation setting is disabled: {}".format(app.id)) continue # get dataset_collection_binding info - dataset_collection_binding = db.session.query(DatasetCollectionBinding).filter( - DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id - ).first() + dataset_collection_binding = ( + db.session.query(DatasetCollectionBinding) + .filter(DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id) + .first() + ) if not dataset_collection_binding: - click.echo('App annotation collection binding is not exist: {}'.format(app.id)) + click.echo("App annotation collection binding is not exist: {}".format(app.id)) continue annotations = db.session.query(MessageAnnotation).filter(MessageAnnotation.app_id == app.id).all() dataset = Dataset( id=app.id, tenant_id=app.tenant_id, - indexing_technique='high_quality', + indexing_technique="high_quality", embedding_model_provider=dataset_collection_binding.provider_name, embedding_model=dataset_collection_binding.model_name, - collection_binding_id=dataset_collection_binding.id + collection_binding_id=dataset_collection_binding.id, ) documents = [] if annotations: for annotation in annotations: document = Document( page_content=annotation.question, - metadata={ - "annotation_id": annotation.id, - "app_id": app.id, - "doc_id": annotation.id - } + metadata={"annotation_id": annotation.id, "app_id": app.id, "doc_id": annotation.id}, ) documents.append(document) - vector = Vector(dataset, attributes=['doc_id', 'annotation_id', 'app_id']) + vector = Vector(dataset, attributes=["doc_id", "annotation_id", "app_id"]) click.echo(f"Start to migrate annotation, app_id: {app.id}.") try: vector.delete() - click.echo( - click.style(f'Successfully delete vector index for app: {app.id}.', - fg='green')) + click.echo(click.style(f"Successfully delete vector index for app: {app.id}.", fg="green")) except Exception as e: - click.echo( - click.style(f'Failed to delete vector index for app {app.id}.', - fg='red')) + click.echo(click.style(f"Failed to delete vector index for app {app.id}.", fg="red")) raise e if documents: try: - click.echo(click.style( - f'Start to created vector index with {len(documents)} annotations for app {app.id}.', - fg='green')) - vector.create(documents) click.echo( - click.style(f'Successfully created vector index for app {app.id}.', fg='green')) + click.style( + f"Start to created vector index with {len(documents)} annotations for app {app.id}.", + fg="green", + ) + ) + vector.create(documents) + click.echo(click.style(f"Successfully created vector index for app {app.id}.", fg="green")) except Exception as e: - click.echo(click.style(f'Failed to created vector index for app {app.id}.', fg='red')) + click.echo(click.style(f"Failed to created vector index for app {app.id}.", fg="red")) raise e - click.echo(f'Successfully migrated app annotation {app.id}.') + click.echo(f"Successfully migrated app annotation {app.id}.") create_count += 1 except Exception as e: click.echo( - click.style('Create app annotation index error: {} {}'.format(e.__class__.__name__, str(e)), - fg='red')) + click.style( + "Create app annotation index error: {} {}".format(e.__class__.__name__, str(e)), fg="red" + ) + ) continue click.echo( - click.style(f'Congratulations! Create {create_count} app annotation indexes, and skipped {skipped_count} apps.', - fg='green')) + click.style( + f"Congratulations! Create {create_count} app annotation indexes, and skipped {skipped_count} apps.", + fg="green", + ) + ) def migrate_knowledge_vector_database(): """ Migrate vector database datas to target vector database . """ - click.echo(click.style('Start migrate vector db.', fg='green')) + click.echo(click.style("Start migrate vector db.", fg="green")) create_count = 0 skipped_count = 0 total_count = 0 @@ -253,87 +262,77 @@ def migrate_knowledge_vector_database(): page = 1 while True: try: - datasets = db.session.query(Dataset).filter(Dataset.indexing_technique == 'high_quality') \ - .order_by(Dataset.created_at.desc()).paginate(page=page, per_page=50) + datasets = ( + db.session.query(Dataset) + .filter(Dataset.indexing_technique == "high_quality") + .order_by(Dataset.created_at.desc()) + .paginate(page=page, per_page=50) + ) except NotFound: break page += 1 for dataset in datasets: total_count = total_count + 1 - click.echo(f'Processing the {total_count} dataset {dataset.id}. ' - + f'{create_count} created, {skipped_count} skipped.') + click.echo( + f"Processing the {total_count} dataset {dataset.id}. " + + f"{create_count} created, {skipped_count} skipped." + ) try: - click.echo('Create dataset vdb index: {}'.format(dataset.id)) + click.echo("Create dataset vdb index: {}".format(dataset.id)) if dataset.index_struct_dict: - if dataset.index_struct_dict['type'] == vector_type: + if dataset.index_struct_dict["type"] == vector_type: skipped_count = skipped_count + 1 continue - collection_name = '' + collection_name = "" if vector_type == VectorType.WEAVIATE: dataset_id = dataset.id collection_name = Dataset.gen_collection_name_by_id(dataset_id) - index_struct_dict = { - "type": VectorType.WEAVIATE, - "vector_store": {"class_prefix": collection_name} - } + index_struct_dict = {"type": VectorType.WEAVIATE, "vector_store": {"class_prefix": collection_name}} dataset.index_struct = json.dumps(index_struct_dict) elif vector_type == VectorType.QDRANT: if dataset.collection_binding_id: - dataset_collection_binding = db.session.query(DatasetCollectionBinding). \ - filter(DatasetCollectionBinding.id == dataset.collection_binding_id). \ - one_or_none() + dataset_collection_binding = ( + db.session.query(DatasetCollectionBinding) + .filter(DatasetCollectionBinding.id == dataset.collection_binding_id) + .one_or_none() + ) if dataset_collection_binding: collection_name = dataset_collection_binding.collection_name else: - raise ValueError('Dataset Collection Bindings is not exist!') + raise ValueError("Dataset Collection Bindings is not exist!") else: dataset_id = dataset.id collection_name = Dataset.gen_collection_name_by_id(dataset_id) - index_struct_dict = { - "type": VectorType.QDRANT, - "vector_store": {"class_prefix": collection_name} - } + index_struct_dict = {"type": VectorType.QDRANT, "vector_store": {"class_prefix": collection_name}} dataset.index_struct = json.dumps(index_struct_dict) elif vector_type == VectorType.MILVUS: dataset_id = dataset.id collection_name = Dataset.gen_collection_name_by_id(dataset_id) - index_struct_dict = { - "type": VectorType.MILVUS, - "vector_store": {"class_prefix": collection_name} - } + index_struct_dict = {"type": VectorType.MILVUS, "vector_store": {"class_prefix": collection_name}} dataset.index_struct = json.dumps(index_struct_dict) elif vector_type == VectorType.RELYT: dataset_id = dataset.id collection_name = Dataset.gen_collection_name_by_id(dataset_id) - index_struct_dict = { - "type": 'relyt', - "vector_store": {"class_prefix": collection_name} - } + index_struct_dict = {"type": "relyt", "vector_store": {"class_prefix": collection_name}} dataset.index_struct = json.dumps(index_struct_dict) elif vector_type == VectorType.TENCENT: dataset_id = dataset.id collection_name = Dataset.gen_collection_name_by_id(dataset_id) - index_struct_dict = { - "type": VectorType.TENCENT, - "vector_store": {"class_prefix": collection_name} - } + index_struct_dict = {"type": VectorType.TENCENT, "vector_store": {"class_prefix": collection_name}} dataset.index_struct = json.dumps(index_struct_dict) elif vector_type == VectorType.PGVECTOR: dataset_id = dataset.id collection_name = Dataset.gen_collection_name_by_id(dataset_id) - index_struct_dict = { - "type": VectorType.PGVECTOR, - "vector_store": {"class_prefix": collection_name} - } + index_struct_dict = {"type": VectorType.PGVECTOR, "vector_store": {"class_prefix": collection_name}} dataset.index_struct = json.dumps(index_struct_dict) elif vector_type == VectorType.OPENSEARCH: dataset_id = dataset.id collection_name = Dataset.gen_collection_name_by_id(dataset_id) index_struct_dict = { "type": VectorType.OPENSEARCH, - "vector_store": {"class_prefix": collection_name} + "vector_store": {"class_prefix": collection_name}, } dataset.index_struct = json.dumps(index_struct_dict) elif vector_type == VectorType.ANALYTICDB: @@ -341,9 +340,14 @@ def migrate_knowledge_vector_database(): collection_name = Dataset.gen_collection_name_by_id(dataset_id) index_struct_dict = { "type": VectorType.ANALYTICDB, - "vector_store": {"class_prefix": collection_name} + "vector_store": {"class_prefix": collection_name}, } dataset.index_struct = json.dumps(index_struct_dict) + elif vector_type == VectorType.ELASTICSEARCH: + dataset_id = dataset.id + index_name = Dataset.gen_collection_name_by_id(dataset_id) + index_struct_dict = {"type": "elasticsearch", "vector_store": {"class_prefix": index_name}} + dataset.index_struct = json.dumps(index_struct_dict) else: raise ValueError(f"Vector store {vector_type} is not supported.") @@ -353,29 +357,41 @@ def migrate_knowledge_vector_database(): try: vector.delete() click.echo( - click.style(f'Successfully delete vector index {collection_name} for dataset {dataset.id}.', - fg='green')) + click.style( + f"Successfully delete vector index {collection_name} for dataset {dataset.id}.", fg="green" + ) + ) except Exception as e: click.echo( - click.style(f'Failed to delete vector index {collection_name} for dataset {dataset.id}.', - fg='red')) + click.style( + f"Failed to delete vector index {collection_name} for dataset {dataset.id}.", fg="red" + ) + ) raise e - dataset_documents = db.session.query(DatasetDocument).filter( - DatasetDocument.dataset_id == dataset.id, - DatasetDocument.indexing_status == 'completed', - DatasetDocument.enabled == True, - DatasetDocument.archived == False, - ).all() + dataset_documents = ( + db.session.query(DatasetDocument) + .filter( + DatasetDocument.dataset_id == dataset.id, + DatasetDocument.indexing_status == "completed", + DatasetDocument.enabled == True, + DatasetDocument.archived == False, + ) + .all() + ) documents = [] segments_count = 0 for dataset_document in dataset_documents: - segments = db.session.query(DocumentSegment).filter( - DocumentSegment.document_id == dataset_document.id, - DocumentSegment.status == 'completed', - DocumentSegment.enabled == True - ).all() + segments = ( + db.session.query(DocumentSegment) + .filter( + DocumentSegment.document_id == dataset_document.id, + DocumentSegment.status == "completed", + DocumentSegment.enabled == True, + ) + .all() + ) for segment in segments: document = Document( @@ -385,7 +401,7 @@ def migrate_knowledge_vector_database(): "doc_hash": segment.index_node_hash, "document_id": segment.document_id, "dataset_id": segment.dataset_id, - } + }, ) documents.append(document) @@ -393,37 +409,43 @@ def migrate_knowledge_vector_database(): if documents: try: - click.echo(click.style( - f'Start to created vector index with {len(documents)} documents of {segments_count} segments for dataset {dataset.id}.', - fg='green')) + click.echo( + click.style( + f"Start to created vector index with {len(documents)} documents of {segments_count} segments for dataset {dataset.id}.", + fg="green", + ) + ) vector.create(documents) click.echo( - click.style(f'Successfully created vector index for dataset {dataset.id}.', fg='green')) + click.style(f"Successfully created vector index for dataset {dataset.id}.", fg="green") + ) except Exception as e: - click.echo(click.style(f'Failed to created vector index for dataset {dataset.id}.', fg='red')) + click.echo(click.style(f"Failed to created vector index for dataset {dataset.id}.", fg="red")) raise e db.session.add(dataset) db.session.commit() - click.echo(f'Successfully migrated dataset {dataset.id}.') + click.echo(f"Successfully migrated dataset {dataset.id}.") create_count += 1 except Exception as e: db.session.rollback() click.echo( - click.style('Create dataset index error: {} {}'.format(e.__class__.__name__, str(e)), - fg='red')) + click.style("Create dataset index error: {} {}".format(e.__class__.__name__, str(e)), fg="red") + ) continue click.echo( - click.style(f'Congratulations! Create {create_count} dataset indexes, and skipped {skipped_count} datasets.', - fg='green')) + click.style( + f"Congratulations! Create {create_count} dataset indexes, and skipped {skipped_count} datasets.", fg="green" + ) + ) -@click.command('convert-to-agent-apps', help='Convert Agent Assistant to Agent App.') +@click.command("convert-to-agent-apps", help="Convert Agent Assistant to Agent App.") def convert_to_agent_apps(): """ Convert Agent Assistant to Agent App. """ - click.echo(click.style('Start convert to agent apps.', fg='green')) + click.echo(click.style("Start convert to agent apps.", fg="green")) proceeded_app_ids = [] @@ -458,7 +480,7 @@ def convert_to_agent_apps(): break for app in apps: - click.echo('Converting app: {}'.format(app.id)) + click.echo("Converting app: {}".format(app.id)) try: app.mode = AppMode.AGENT_CHAT.value @@ -470,137 +492,139 @@ def convert_to_agent_apps(): ) db.session.commit() - click.echo(click.style('Converted app: {}'.format(app.id), fg='green')) + click.echo(click.style("Converted app: {}".format(app.id), fg="green")) except Exception as e: - click.echo( - click.style('Convert app error: {} {}'.format(e.__class__.__name__, - str(e)), fg='red')) + click.echo(click.style("Convert app error: {} {}".format(e.__class__.__name__, str(e)), fg="red")) - click.echo(click.style('Congratulations! Converted {} agent apps.'.format(len(proceeded_app_ids)), fg='green')) + click.echo(click.style("Congratulations! Converted {} agent apps.".format(len(proceeded_app_ids)), fg="green")) -@click.command('add-qdrant-doc-id-index', help='add qdrant doc_id index.') -@click.option('--field', default='metadata.doc_id', prompt=False, help='index field , default is metadata.doc_id.') +@click.command("add-qdrant-doc-id-index", help="add qdrant doc_id index.") +@click.option("--field", default="metadata.doc_id", prompt=False, help="index field , default is metadata.doc_id.") def add_qdrant_doc_id_index(field: str): - click.echo(click.style('Start add qdrant doc_id index.', fg='green')) + click.echo(click.style("Start add qdrant doc_id index.", fg="green")) vector_type = dify_config.VECTOR_STORE if vector_type != "qdrant": - click.echo(click.style('Sorry, only support qdrant vector store.', fg='red')) + click.echo(click.style("Sorry, only support qdrant vector store.", fg="red")) return create_count = 0 try: bindings = db.session.query(DatasetCollectionBinding).all() if not bindings: - click.echo(click.style('Sorry, no dataset collection bindings found.', fg='red')) + click.echo(click.style("Sorry, no dataset collection bindings found.", fg="red")) return import qdrant_client from qdrant_client.http.exceptions import UnexpectedResponse from qdrant_client.http.models import PayloadSchemaType from core.rag.datasource.vdb.qdrant.qdrant_vector import QdrantConfig + for binding in bindings: if dify_config.QDRANT_URL is None: - raise ValueError('Qdrant url is required.') + raise ValueError("Qdrant url is required.") qdrant_config = QdrantConfig( endpoint=dify_config.QDRANT_URL, api_key=dify_config.QDRANT_API_KEY, root_path=current_app.root_path, timeout=dify_config.QDRANT_CLIENT_TIMEOUT, grpc_port=dify_config.QDRANT_GRPC_PORT, - prefer_grpc=dify_config.QDRANT_GRPC_ENABLED + prefer_grpc=dify_config.QDRANT_GRPC_ENABLED, ) try: client = qdrant_client.QdrantClient(**qdrant_config.to_qdrant_params()) # create payload index - client.create_payload_index(binding.collection_name, field, - field_schema=PayloadSchemaType.KEYWORD) + client.create_payload_index(binding.collection_name, field, field_schema=PayloadSchemaType.KEYWORD) create_count += 1 except UnexpectedResponse as e: # Collection does not exist, so return if e.status_code == 404: - click.echo(click.style(f'Collection not found, collection_name:{binding.collection_name}.', fg='red')) + click.echo( + click.style(f"Collection not found, collection_name:{binding.collection_name}.", fg="red") + ) continue # Some other error occurred, so re-raise the exception else: - click.echo(click.style(f'Failed to create qdrant index, collection_name:{binding.collection_name}.', fg='red')) + click.echo( + click.style( + f"Failed to create qdrant index, collection_name:{binding.collection_name}.", fg="red" + ) + ) except Exception as e: - click.echo(click.style('Failed to create qdrant client.', fg='red')) + click.echo(click.style("Failed to create qdrant client.", fg="red")) - click.echo( - click.style(f'Congratulations! Create {create_count} collection indexes.', - fg='green')) + click.echo(click.style(f"Congratulations! Create {create_count} collection indexes.", fg="green")) -@click.command('create-tenant', help='Create account and tenant.') -@click.option('--email', prompt=True, help='The email address of the tenant account.') -@click.option('--language', prompt=True, help='Account language, default: en-US.') +@click.command("create-tenant", help="Create account and tenant.") +@click.option("--email", prompt=True, help="The email address of the tenant account.") +@click.option("--language", prompt=True, help="Account language, default: en-US.") def create_tenant(email: str, language: Optional[str] = None): """ Create tenant account """ if not email: - click.echo(click.style('Sorry, email is required.', fg='red')) + click.echo(click.style("Sorry, email is required.", fg="red")) return # Create account email = email.strip() - if '@' not in email: - click.echo(click.style('Sorry, invalid email address.', fg='red')) + if "@" not in email: + click.echo(click.style("Sorry, invalid email address.", fg="red")) return - account_name = email.split('@')[0] + account_name = email.split("@")[0] if language not in languages: - language = 'en-US' + language = "en-US" # generate random password new_password = secrets.token_urlsafe(16) # register account - account = RegisterService.register( - email=email, - name=account_name, - password=new_password, - language=language - ) + account = RegisterService.register(email=email, name=account_name, password=new_password, language=language) TenantService.create_owner_tenant_if_not_exist(account) - click.echo(click.style('Congratulations! Account and tenant created.\n' - 'Account: {}\nPassword: {}'.format(email, new_password), fg='green')) + click.echo( + click.style( + "Congratulations! Account and tenant created.\n" "Account: {}\nPassword: {}".format(email, new_password), + fg="green", + ) + ) -@click.command('upgrade-db', help='upgrade the database') +@click.command("upgrade-db", help="upgrade the database") def upgrade_db(): - click.echo('Preparing database migration...') - lock = redis_client.lock(name='db_upgrade_lock', timeout=60) + click.echo("Preparing database migration...") + lock = redis_client.lock(name="db_upgrade_lock", timeout=60) if lock.acquire(blocking=False): try: - click.echo(click.style('Start database migration.', fg='green')) + click.echo(click.style("Start database migration.", fg="green")) # run db migration import flask_migrate + flask_migrate.upgrade() - click.echo(click.style('Database migration successful!', fg='green')) + click.echo(click.style("Database migration successful!", fg="green")) except Exception as e: - logging.exception(f'Database migration failed, error: {e}') + logging.exception(f"Database migration failed, error: {e}") finally: lock.release() else: - click.echo('Database migration skipped') + click.echo("Database migration skipped") -@click.command('fix-app-site-missing', help='Fix app related site missing issue.') +@click.command("fix-app-site-missing", help="Fix app related site missing issue.") def fix_app_site_missing(): """ Fix app related site missing issue. """ - click.echo(click.style('Start fix app related site missing issue.', fg='green')) + click.echo(click.style("Start fix app related site missing issue.", fg="green")) failed_app_ids = [] while True: @@ -631,15 +655,14 @@ where sites.id is null limit 1000""" app_was_created.send(app, account=account) except Exception as e: failed_app_ids.append(app_id) - click.echo(click.style('Fix app {} related site missing issue failed!'.format(app_id), fg='red')) - logging.exception(f'Fix app related site missing issue failed, error: {e}') + click.echo(click.style("Fix app {} related site missing issue failed!".format(app_id), fg="red")) + logging.exception(f"Fix app related site missing issue failed, error: {e}") continue if not processed_count: break - - click.echo(click.style('Congratulations! Fix app related site missing issue successful!', fg='green')) + click.echo(click.style("Congratulations! Fix app related site missing issue successful!", fg="green")) def register_commands(app): diff --git a/api/configs/packaging/__init__.py b/api/configs/packaging/__init__.py index 1104e298b1..247fcde655 100644 --- a/api/configs/packaging/__init__.py +++ b/api/configs/packaging/__init__.py @@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings): CURRENT_VERSION: str = Field( description='Dify version', - default='0.6.16', + default='0.7.0', ) COMMIT_SHA: str = Field( diff --git a/api/constants/__init__.py b/api/constants/__init__.py index e374c04316..e22c3268ef 100644 --- a/api/constants/__init__.py +++ b/api/constants/__init__.py @@ -1 +1 @@ -HIDDEN_VALUE = '[__HIDDEN__]' +HIDDEN_VALUE = "[__HIDDEN__]" diff --git a/api/constants/languages.py b/api/constants/languages.py index 38e49e0d1e..524dc61b57 100644 --- a/api/constants/languages.py +++ b/api/constants/languages.py @@ -1,22 +1,22 @@ language_timezone_mapping = { - 'en-US': 'America/New_York', - 'zh-Hans': 'Asia/Shanghai', - 'zh-Hant': 'Asia/Taipei', - 'pt-BR': 'America/Sao_Paulo', - 'es-ES': 'Europe/Madrid', - 'fr-FR': 'Europe/Paris', - 'de-DE': 'Europe/Berlin', - 'ja-JP': 'Asia/Tokyo', - 'ko-KR': 'Asia/Seoul', - 'ru-RU': 'Europe/Moscow', - 'it-IT': 'Europe/Rome', - 'uk-UA': 'Europe/Kyiv', - 'vi-VN': 'Asia/Ho_Chi_Minh', - 'ro-RO': 'Europe/Bucharest', - 'pl-PL': 'Europe/Warsaw', - 'hi-IN': 'Asia/Kolkata', - 'tr-TR': 'Europe/Istanbul', - 'fa-IR': 'Asia/Tehran', + "en-US": "America/New_York", + "zh-Hans": "Asia/Shanghai", + "zh-Hant": "Asia/Taipei", + "pt-BR": "America/Sao_Paulo", + "es-ES": "Europe/Madrid", + "fr-FR": "Europe/Paris", + "de-DE": "Europe/Berlin", + "ja-JP": "Asia/Tokyo", + "ko-KR": "Asia/Seoul", + "ru-RU": "Europe/Moscow", + "it-IT": "Europe/Rome", + "uk-UA": "Europe/Kyiv", + "vi-VN": "Asia/Ho_Chi_Minh", + "ro-RO": "Europe/Bucharest", + "pl-PL": "Europe/Warsaw", + "hi-IN": "Asia/Kolkata", + "tr-TR": "Europe/Istanbul", + "fa-IR": "Asia/Tehran", } languages = list(language_timezone_mapping.keys()) @@ -26,6 +26,5 @@ def supported_language(lang): if lang in languages: return lang - error = ('{lang} is not a valid language.' - .format(lang=lang)) + error = "{lang} is not a valid language.".format(lang=lang) raise ValueError(error) diff --git a/api/constants/model_template.py b/api/constants/model_template.py index cc5a370254..7e1a196356 100644 --- a/api/constants/model_template.py +++ b/api/constants/model_template.py @@ -5,82 +5,79 @@ from models.model import AppMode default_app_templates = { # workflow default mode AppMode.WORKFLOW: { - 'app': { - 'mode': AppMode.WORKFLOW.value, - 'enable_site': True, - 'enable_api': True + "app": { + "mode": AppMode.WORKFLOW.value, + "enable_site": True, + "enable_api": True, } }, - # completion default mode AppMode.COMPLETION: { - 'app': { - 'mode': AppMode.COMPLETION.value, - 'enable_site': True, - 'enable_api': True + "app": { + "mode": AppMode.COMPLETION.value, + "enable_site": True, + "enable_api": True, }, - 'model_config': { - 'model': { + "model_config": { + "model": { "provider": "openai", "name": "gpt-4o", "mode": "chat", - "completion_params": {} + "completion_params": {}, }, - 'user_input_form': json.dumps([ - { - "paragraph": { - "label": "Query", - "variable": "query", - "required": True, - "default": "" - } - } - ]), - 'pre_prompt': '{{query}}' + "user_input_form": json.dumps( + [ + { + "paragraph": { + "label": "Query", + "variable": "query", + "required": True, + "default": "", + }, + }, + ] + ), + "pre_prompt": "{{query}}", }, - }, - # chat default mode AppMode.CHAT: { - 'app': { - 'mode': AppMode.CHAT.value, - 'enable_site': True, - 'enable_api': True + "app": { + "mode": AppMode.CHAT.value, + "enable_site": True, + "enable_api": True, }, - 'model_config': { - 'model': { + "model_config": { + "model": { "provider": "openai", "name": "gpt-4o", "mode": "chat", - "completion_params": {} - } - } + "completion_params": {}, + }, + }, }, - # advanced-chat default mode AppMode.ADVANCED_CHAT: { - 'app': { - 'mode': AppMode.ADVANCED_CHAT.value, - 'enable_site': True, - 'enable_api': True - } + "app": { + "mode": AppMode.ADVANCED_CHAT.value, + "enable_site": True, + "enable_api": True, + }, }, - # agent-chat default mode AppMode.AGENT_CHAT: { - 'app': { - 'mode': AppMode.AGENT_CHAT.value, - 'enable_site': True, - 'enable_api': True + "app": { + "mode": AppMode.AGENT_CHAT.value, + "enable_site": True, + "enable_api": True, }, - 'model_config': { - 'model': { + "model_config": { + "model": { "provider": "openai", "name": "gpt-4o", "mode": "chat", - "completion_params": {} - } - } - } + "completion_params": {}, + }, + }, + }, } diff --git a/api/contexts/__init__.py b/api/contexts/__init__.py index 306fac3a93..623a1a28eb 100644 --- a/api/contexts/__init__.py +++ b/api/contexts/__init__.py @@ -1,3 +1,7 @@ from contextvars import ContextVar -tenant_id: ContextVar[str] = ContextVar('tenant_id') \ No newline at end of file +from core.workflow.entities.variable_pool import VariablePool + +tenant_id: ContextVar[str] = ContextVar("tenant_id") + +workflow_variable_pool: ContextVar[VariablePool] = ContextVar("workflow_variable_pool") diff --git a/api/controllers/console/app/conversation.py b/api/controllers/console/app/conversation.py index 844788a9e3..eb61c83d46 100644 --- a/api/controllers/console/app/conversation.py +++ b/api/controllers/console/app/conversation.py @@ -33,7 +33,7 @@ class CompletionConversationApi(Resource): @get_app_model(mode=AppMode.COMPLETION) @marshal_with(conversation_pagination_fields) def get(self, app_model): - if not current_user.is_admin_or_owner: + if not current_user.is_editor: raise Forbidden() parser = reqparse.RequestParser() parser.add_argument('keyword', type=str, location='args') @@ -108,7 +108,7 @@ class CompletionConversationDetailApi(Resource): @get_app_model(mode=AppMode.COMPLETION) @marshal_with(conversation_message_detail_fields) def get(self, app_model, conversation_id): - if not current_user.is_admin_or_owner: + if not current_user.is_editor: raise Forbidden() conversation_id = str(conversation_id) @@ -119,7 +119,7 @@ class CompletionConversationDetailApi(Resource): @account_initialization_required @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]) def delete(self, app_model, conversation_id): - if not current_user.is_admin_or_owner: + if not current_user.is_editor: raise Forbidden() conversation_id = str(conversation_id) @@ -256,7 +256,7 @@ class ChatConversationDetailApi(Resource): @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]) @account_initialization_required def delete(self, app_model, conversation_id): - if not current_user.is_admin_or_owner: + if not current_user.is_editor: raise Forbidden() conversation_id = str(conversation_id) diff --git a/api/controllers/console/datasets/datasets.py b/api/controllers/console/datasets/datasets.py index 3e98843280..a5bc2dd86a 100644 --- a/api/controllers/console/datasets/datasets.py +++ b/api/controllers/console/datasets/datasets.py @@ -555,7 +555,7 @@ class DatasetRetrievalSettingApi(Resource): RetrievalMethod.SEMANTIC_SEARCH.value ] } - case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH | VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE: + case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH | VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE | VectorType.ELASTICSEARCH: return { 'retrieval_method': [ RetrievalMethod.SEMANTIC_SEARCH.value, @@ -579,7 +579,7 @@ class DatasetRetrievalSettingMockApi(Resource): RetrievalMethod.SEMANTIC_SEARCH.value ] } - case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH| VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE: + case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH| VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE | VectorType.ELASTICSEARCH: return { 'retrieval_method': [ RetrievalMethod.SEMANTIC_SEARCH.value, diff --git a/api/controllers/console/datasets/datasets_document.py b/api/controllers/console/datasets/datasets_document.py index afe0ca7c69..976b97660a 100644 --- a/api/controllers/console/datasets/datasets_document.py +++ b/api/controllers/console/datasets/datasets_document.py @@ -178,11 +178,20 @@ class DatasetDocumentListApi(Resource): .subquery() query = query.outerjoin(sub_query, sub_query.c.document_id == Document.id) \ - .order_by(sort_logic(db.func.coalesce(sub_query.c.total_hit_count, 0))) + .order_by( + sort_logic(db.func.coalesce(sub_query.c.total_hit_count, 0)), + sort_logic(Document.position), + ) elif sort == 'created_at': - query = query.order_by(sort_logic(Document.created_at)) + query = query.order_by( + sort_logic(Document.created_at), + sort_logic(Document.position), + ) else: - query = query.order_by(desc(Document.created_at)) + query = query.order_by( + desc(Document.created_at), + desc(Document.position), + ) paginated_documents = query.paginate( page=page, per_page=limit, max_per_page=100, error_out=False) diff --git a/api/core/app/app_config/easy_ui_based_app/dataset/manager.py b/api/core/app/app_config/easy_ui_based_app/dataset/manager.py index ec17db5f06..f4e6675bd4 100644 --- a/api/core/app/app_config/easy_ui_based_app/dataset/manager.py +++ b/api/core/app/app_config/easy_ui_based_app/dataset/manager.py @@ -93,6 +93,7 @@ class DatasetConfigManager: reranking_model=dataset_configs.get('reranking_model'), weights=dataset_configs.get('weights'), reranking_enabled=dataset_configs.get('reranking_enabled', True), + rerank_mode=dataset_configs["reranking_mode"], ) ) diff --git a/api/core/app/apps/advanced_chat/app_generator.py b/api/core/app/apps/advanced_chat/app_generator.py index c9d3ad9ea3..2555d1276a 100644 --- a/api/core/app/apps/advanced_chat/app_generator.py +++ b/api/core/app/apps/advanced_chat/app_generator.py @@ -33,7 +33,7 @@ logger = logging.getLogger(__name__) class AdvancedChatAppGenerator(MessageBasedAppGenerator): def generate( - self, + self, app_model: App, workflow: Workflow, user: Union[Account, EndUser], @@ -121,7 +121,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): conversation=conversation, stream=stream ) - + def single_iteration_generate(self, app_model: App, workflow: Workflow, node_id: str, @@ -141,10 +141,10 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): """ if not node_id: raise ValueError('node_id is required') - + if args.get('inputs') is None: raise ValueError('inputs is required') - + # convert to app config app_config = AdvancedChatAppConfigManager.get_app_config( app_model=app_model, @@ -191,7 +191,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): -> dict[str, Any] | Generator[str, Any, None]: """ Generate App response. - + :param workflow: Workflow :param user: account or end user :param invoke_from: invoke from source @@ -232,8 +232,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): 'queue_manager': queue_manager, 'conversation_id': conversation.id, 'message_id': message.id, - 'user': user, - 'context': contextvars.copy_context() + 'context': contextvars.copy_context(), }) worker_thread.start() @@ -246,7 +245,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): conversation=conversation, message=message, user=user, - stream=stream + stream=stream, ) return AdvancedChatAppGenerateResponseConverter.convert( @@ -259,7 +258,6 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): queue_manager: AppQueueManager, conversation_id: str, message_id: str, - user: Account, context: contextvars.Context) -> None: """ Generate worker in a new thread. @@ -307,14 +305,17 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): finally: db.session.close() - def _handle_advanced_chat_response(self, application_generate_entity: AdvancedChatAppGenerateEntity, - workflow: Workflow, - queue_manager: AppQueueManager, - conversation: Conversation, - message: Message, - user: Union[Account, EndUser], - stream: bool = False) \ - -> Union[ChatbotAppBlockingResponse, Generator[ChatbotAppStreamResponse, None, None]]: + def _handle_advanced_chat_response( + self, + *, + application_generate_entity: AdvancedChatAppGenerateEntity, + workflow: Workflow, + queue_manager: AppQueueManager, + conversation: Conversation, + message: Message, + user: Union[Account, EndUser], + stream: bool = False, + ) -> Union[ChatbotAppBlockingResponse, Generator[ChatbotAppStreamResponse, None, None]]: """ Handle response. :param application_generate_entity: application generate entity @@ -334,7 +335,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator): conversation=conversation, message=message, user=user, - stream=stream + stream=stream, ) try: diff --git a/api/core/app/apps/advanced_chat/app_runner.py b/api/core/app/apps/advanced_chat/app_runner.py index 1483a80edb..c50ec75101 100644 --- a/api/core/app/apps/advanced_chat/app_runner.py +++ b/api/core/app/apps/advanced_chat/app_runner.py @@ -3,9 +3,6 @@ import os from collections.abc import Mapping from typing import Any, cast -from sqlalchemy import select -from sqlalchemy.orm import Session - from core.app.apps.advanced_chat.app_config_manager import AdvancedChatAppConfig from core.app.apps.base_app_queue_manager import AppQueueManager from core.app.apps.workflow_app_runner import WorkflowBasedAppRunner @@ -94,7 +91,7 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner): inputs = self.application_generate_entity.inputs query = self.application_generate_entity.query files = self.application_generate_entity.files - + # moderation if self.handle_input_moderation( app_record=app_record, diff --git a/api/core/app/apps/advanced_chat/generate_task_pipeline.py b/api/core/app/apps/advanced_chat/generate_task_pipeline.py index bf6e576bb2..bcef35e0f4 100644 --- a/api/core/app/apps/advanced_chat/generate_task_pipeline.py +++ b/api/core/app/apps/advanced_chat/generate_task_pipeline.py @@ -44,7 +44,7 @@ from core.app.task_pipeline.message_cycle_manage import MessageCycleManage from core.app.task_pipeline.workflow_cycle_manage import WorkflowCycleManage from core.model_runtime.utils.encoders import jsonable_encoder from core.ops.ops_trace_manager import TraceQueueManager -from core.workflow.entities.node_entities import SystemVariable +from core.workflow.enums import SystemVariable from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState from events.message_event import message_was_created from extensions.ext_database import db @@ -69,14 +69,14 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc _workflow_system_variables: dict[SystemVariable, Any] def __init__( - self, + self, application_generate_entity: AdvancedChatAppGenerateEntity, workflow: Workflow, queue_manager: AppQueueManager, conversation: Conversation, message: Message, user: Union[Account, EndUser], - stream: bool + stream: bool, ) -> None: """ Initialize AdvancedChatAppGenerateTaskPipeline. @@ -102,7 +102,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc SystemVariable.QUERY: message.query, SystemVariable.FILES: application_generate_entity.files, SystemVariable.CONVERSATION_ID: conversation.id, - SystemVariable.USER_ID: user_id + SystemVariable.USER_ID: user_id, } self._task_state = WorkflowTaskState() @@ -127,7 +127,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc generator = self._wrapper_process_stream_response( trace_manager=self._application_generate_entity.trace_manager ) - + if self._stream: return self._to_stream_response(generator) else: @@ -239,7 +239,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc # init fake graph runtime state graph_runtime_state = None workflow_run = None - + for queue_message in self._queue_manager.listen(): event = queue_message.event @@ -270,9 +270,9 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc elif isinstance(event, QueueNodeStartedEvent): if not workflow_run: raise Exception('Workflow run not initialized.') - + workflow_node_execution = self._handle_node_execution_start( - workflow_run=workflow_run, + workflow_run=workflow_run, event=event ) @@ -307,7 +307,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc elif isinstance(event, QueueIterationStartEvent): if not workflow_run: raise Exception('Workflow run not initialized.') - + yield self._workflow_iteration_start_to_stream_response( task_id=self._application_generate_entity.task_id, workflow_run=workflow_run, @@ -316,7 +316,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc elif isinstance(event, QueueIterationNextEvent): if not workflow_run: raise Exception('Workflow run not initialized.') - + yield self._workflow_iteration_next_to_stream_response( task_id=self._application_generate_entity.task_id, workflow_run=workflow_run, @@ -325,7 +325,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc elif isinstance(event, QueueIterationCompletedEvent): if not workflow_run: raise Exception('Workflow run not initialized.') - + yield self._workflow_iteration_completed_to_stream_response( task_id=self._application_generate_entity.task_id, workflow_run=workflow_run, @@ -334,10 +334,10 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc elif isinstance(event, QueueWorkflowSucceededEvent): if not workflow_run: raise Exception('Workflow run not initialized.') - + if not graph_runtime_state: raise Exception('Graph runtime state not initialized.') - + workflow_run = self._handle_workflow_run_success( workflow_run=workflow_run, start_at=graph_runtime_state.start_at, @@ -360,10 +360,10 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc elif isinstance(event, QueueWorkflowFailedEvent): if not workflow_run: raise Exception('Workflow run not initialized.') - + if not graph_runtime_state: raise Exception('Graph runtime state not initialized.') - + workflow_run = self._handle_workflow_run_failed( workflow_run=workflow_run, start_at=graph_runtime_state.start_at, @@ -400,7 +400,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc task_id=self._application_generate_entity.task_id, workflow_run=workflow_run ) - + # Save message self._save_message(graph_runtime_state=graph_runtime_state) @@ -413,7 +413,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc self._message.message_metadata = json.dumps(jsonable_encoder(self._task_state.metadata)) \ if self._task_state.metadata else None - + db.session.commit() db.session.close() elif isinstance(event, QueueAnnotationReplyEvent): @@ -421,7 +421,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc self._message.message_metadata = json.dumps(jsonable_encoder(self._task_state.metadata)) \ if self._task_state.metadata else None - + db.session.commit() db.session.close() elif isinstance(event, QueueTextChunkEvent): @@ -446,7 +446,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc elif isinstance(event, QueueAdvancedChatMessageEndEvent): if not graph_runtime_state: raise Exception('Graph runtime state not initialized.') - + output_moderation_answer = self._handle_output_moderation_when_task_finished(self._task_state.answer) if output_moderation_answer: self._task_state.answer = output_moderation_answer @@ -458,11 +458,11 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc yield self._message_end_to_stream_response() else: continue - + # publish None when task finished if tts_publisher: tts_publisher.publish(None) - + if self._conversation_name_generate_thread: self._conversation_name_generate_thread.join() @@ -507,7 +507,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc extras = {} if self._task_state.metadata: extras['metadata'] = self._task_state.metadata.copy() - + if 'annotation_reply' in extras['metadata']: del extras['metadata']['annotation_reply'] diff --git a/api/core/app/apps/base_app_runner.py b/api/core/app/apps/base_app_runner.py index deb1ac8bd6..1158cce49f 100644 --- a/api/core/app/apps/base_app_runner.py +++ b/api/core/app/apps/base_app_runner.py @@ -1,6 +1,6 @@ import time from collections.abc import Generator, Mapping -from typing import Any, Optional, Union +from typing import TYPE_CHECKING, Any, Optional, Union from core.app.app_config.entities import ExternalDataVariableEntity, PromptTemplateEntity from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom @@ -14,7 +14,6 @@ from core.app.entities.queue_entities import QueueAgentMessageEvent, QueueLLMChu from core.app.features.annotation_reply.annotation_reply import AnnotationReplyFeature from core.app.features.hosting_moderation.hosting_moderation import HostingModerationFeature from core.external_data_tool.external_data_fetch import ExternalDataFetch -from core.file.file_obj import FileVar from core.memory.token_buffer_memory import TokenBufferMemory from core.model_manager import ModelInstance from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage @@ -27,13 +26,16 @@ from core.prompt.entities.advanced_prompt_entities import ChatModelMessage, Comp from core.prompt.simple_prompt_transform import ModelMode, SimplePromptTransform from models.model import App, AppMode, Message, MessageAnnotation +if TYPE_CHECKING: + from core.file.file_obj import FileVar + class AppRunner: def get_pre_calculate_rest_tokens(self, app_record: App, model_config: ModelConfigWithCredentialsEntity, prompt_template_entity: PromptTemplateEntity, inputs: dict[str, str], - files: list[FileVar], + files: list["FileVar"], query: Optional[str] = None) -> int: """ Get pre calculate rest tokens @@ -126,7 +128,7 @@ class AppRunner: model_config: ModelConfigWithCredentialsEntity, prompt_template_entity: PromptTemplateEntity, inputs: dict[str, str], - files: list[FileVar], + files: list["FileVar"], query: Optional[str] = None, context: Optional[str] = None, memory: Optional[TokenBufferMemory] = None) \ @@ -366,7 +368,7 @@ class AppRunner: message_id=message_id, trace_manager=app_generate_entity.trace_manager ) - + def check_hosting_moderation(self, application_generate_entity: EasyUIBasedAppGenerateEntity, queue_manager: AppQueueManager, prompt_messages: list[PromptMessage]) -> bool: @@ -418,7 +420,7 @@ class AppRunner: inputs=inputs, query=query ) - + def query_app_annotations_to_reply(self, app_record: App, message: Message, query: str, diff --git a/api/core/app/apps/message_based_app_generator.py b/api/core/app/apps/message_based_app_generator.py index c5cd686402..12f69f1528 100644 --- a/api/core/app/apps/message_based_app_generator.py +++ b/api/core/app/apps/message_based_app_generator.py @@ -258,7 +258,7 @@ class MessageBasedAppGenerator(BaseAppGenerator): return introduction - def _get_conversation(self, conversation_id: str) -> Conversation: + def _get_conversation(self, conversation_id: str): """ Get conversation by conversation id :param conversation_id: conversation id @@ -270,6 +270,9 @@ class MessageBasedAppGenerator(BaseAppGenerator): .first() ) + if not conversation: + raise ConversationNotExistsError() + return conversation def _get_message(self, message_id: str) -> Message: diff --git a/api/core/app/apps/workflow/app_runner.py b/api/core/app/apps/workflow/app_runner.py index 6cc2a74bbc..2d1cefd33b 100644 --- a/api/core/app/apps/workflow/app_runner.py +++ b/api/core/app/apps/workflow/app_runner.py @@ -11,7 +11,8 @@ from core.app.entities.app_invoke_entities import ( WorkflowAppGenerateEntity, ) from core.workflow.callbacks.base_workflow_callback import WorkflowCallback -from core.workflow.entities.node_entities import SystemVariable, UserFrom +from core.workflow.enums import SystemVariable +from core.workflow.entities.node_entities import UserFrom from core.workflow.entities.variable_pool import VariablePool from core.workflow.workflow_entry import WorkflowEntry from extensions.ext_database import db diff --git a/api/core/app/apps/workflow/generate_task_pipeline.py b/api/core/app/apps/workflow/generate_task_pipeline.py index d19d3d3ed0..60408ca4f5 100644 --- a/api/core/app/apps/workflow/generate_task_pipeline.py +++ b/api/core/app/apps/workflow/generate_task_pipeline.py @@ -41,7 +41,9 @@ from core.app.entities.task_entities import ( from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline from core.app.task_pipeline.workflow_cycle_manage import WorkflowCycleManage from core.ops.ops_trace_manager import TraceQueueManager -from core.workflow.entities.node_entities import SystemVariable +from core.workflow.entities.node_entities import NodeType +from core.workflow.enums import SystemVariable +from core.workflow.nodes.end.end_node import EndNode from extensions.ext_database import db from models.account import Account from models.model import EndUser @@ -179,7 +181,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa if features_dict.get('text_to_speech') and features_dict['text_to_speech'].get('enabled') and features_dict[ 'text_to_speech'].get('autoPlay') == 'enabled': tts_publisher = AppGeneratorTTSPublisher(tenant_id, features_dict['text_to_speech'].get('voice')) - + for response in self._process_stream_response(tts_publisher=tts_publisher, trace_manager=trace_manager): while True: audio_response = self._listenAudioMsg(tts_publisher, task_id=task_id) @@ -246,7 +248,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa raise Exception('Workflow run not initialized.') workflow_node_execution = self._handle_node_execution_start( - workflow_run=workflow_run, + workflow_run=workflow_run, event=event ) @@ -281,7 +283,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa elif isinstance(event, QueueIterationStartEvent): if not workflow_run: raise Exception('Workflow run not initialized.') - + yield self._workflow_iteration_start_to_stream_response( task_id=self._application_generate_entity.task_id, workflow_run=workflow_run, @@ -290,7 +292,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa elif isinstance(event, QueueIterationNextEvent): if not workflow_run: raise Exception('Workflow run not initialized.') - + yield self._workflow_iteration_next_to_stream_response( task_id=self._application_generate_entity.task_id, workflow_run=workflow_run, @@ -299,7 +301,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa elif isinstance(event, QueueIterationCompletedEvent): if not workflow_run: raise Exception('Workflow run not initialized.') - + yield self._workflow_iteration_completed_to_stream_response( task_id=self._application_generate_entity.task_id, workflow_run=workflow_run, @@ -308,10 +310,10 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa elif isinstance(event, QueueWorkflowSucceededEvent): if not workflow_run: raise Exception('Workflow run not initialized.') - + if not graph_runtime_state: raise Exception('Graph runtime state not initialized.') - + workflow_run = self._handle_workflow_run_success( workflow_run=workflow_run, start_at=graph_runtime_state.start_at, @@ -332,10 +334,10 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa elif isinstance(event, QueueWorkflowFailedEvent | QueueStopEvent): if not workflow_run: raise Exception('Workflow run not initialized.') - + if not graph_runtime_state: raise Exception('Graph runtime state not initialized.') - + workflow_run = self._handle_workflow_run_failed( workflow_run=workflow_run, start_at=graph_runtime_state.start_at, diff --git a/api/core/app/entities/app_invoke_entities.py b/api/core/app/entities/app_invoke_entities.py index 9a861c29e2..6a1ab23041 100644 --- a/api/core/app/entities/app_invoke_entities.py +++ b/api/core/app/entities/app_invoke_entities.py @@ -166,4 +166,4 @@ class WorkflowAppGenerateEntity(AppGenerateEntity): node_id: str inputs: dict - single_iteration_run: Optional[SingleIterationRunEntity] = None \ No newline at end of file + single_iteration_run: Optional[SingleIterationRunEntity] = None diff --git a/api/core/app/segments/__init__.py b/api/core/app/segments/__init__.py index 174e241261..7de06dfb96 100644 --- a/api/core/app/segments/__init__.py +++ b/api/core/app/segments/__init__.py @@ -2,7 +2,6 @@ from .segment_group import SegmentGroup from .segments import ( ArrayAnySegment, ArraySegment, - FileSegment, FloatSegment, IntegerSegment, NoneSegment, @@ -13,11 +12,9 @@ from .segments import ( from .types import SegmentType from .variables import ( ArrayAnyVariable, - ArrayFileVariable, ArrayNumberVariable, ArrayObjectVariable, ArrayStringVariable, - FileVariable, FloatVariable, IntegerVariable, NoneVariable, @@ -32,7 +29,6 @@ __all__ = [ 'FloatVariable', 'ObjectVariable', 'SecretVariable', - 'FileVariable', 'StringVariable', 'ArrayAnyVariable', 'Variable', @@ -45,11 +41,9 @@ __all__ = [ 'FloatSegment', 'ObjectSegment', 'ArrayAnySegment', - 'FileSegment', 'StringSegment', 'ArrayStringVariable', 'ArrayNumberVariable', 'ArrayObjectVariable', - 'ArrayFileVariable', 'ArraySegment', ] diff --git a/api/core/app/segments/factory.py b/api/core/app/segments/factory.py index 91ff1fdb3d..e6e9ce9774 100644 --- a/api/core/app/segments/factory.py +++ b/api/core/app/segments/factory.py @@ -2,12 +2,10 @@ from collections.abc import Mapping from typing import Any from configs import dify_config -from core.file.file_obj import FileVar from .exc import VariableError from .segments import ( ArrayAnySegment, - FileSegment, FloatSegment, IntegerSegment, NoneSegment, @@ -17,11 +15,9 @@ from .segments import ( ) from .types import SegmentType from .variables import ( - ArrayFileVariable, ArrayNumberVariable, ArrayObjectVariable, ArrayStringVariable, - FileVariable, FloatVariable, IntegerVariable, ObjectVariable, @@ -49,8 +45,6 @@ def build_variable_from_mapping(mapping: Mapping[str, Any], /) -> Variable: result = FloatVariable.model_validate(mapping) case SegmentType.NUMBER if not isinstance(value, float | int): raise VariableError(f'invalid number value {value}') - case SegmentType.FILE: - result = FileVariable.model_validate(mapping) case SegmentType.OBJECT if isinstance(value, dict): result = ObjectVariable.model_validate(mapping) case SegmentType.ARRAY_STRING if isinstance(value, list): @@ -59,10 +53,6 @@ def build_variable_from_mapping(mapping: Mapping[str, Any], /) -> Variable: result = ArrayNumberVariable.model_validate(mapping) case SegmentType.ARRAY_OBJECT if isinstance(value, list): result = ArrayObjectVariable.model_validate(mapping) - case SegmentType.ARRAY_FILE if isinstance(value, list): - mapping = dict(mapping) - mapping['value'] = [{'value': v} for v in value] - result = ArrayFileVariable.model_validate(mapping) case _: raise VariableError(f'not supported value type {value_type}') if result.size > dify_config.MAX_VARIABLE_SIZE: @@ -83,6 +73,4 @@ def build_segment(value: Any, /) -> Segment: return ObjectSegment(value=value) if isinstance(value, list): return ArrayAnySegment(value=value) - if isinstance(value, FileVar): - return FileSegment(value=value) raise ValueError(f'not supported value {value}') diff --git a/api/core/app/segments/segments.py b/api/core/app/segments/segments.py index 7653e1085f..5c713cac67 100644 --- a/api/core/app/segments/segments.py +++ b/api/core/app/segments/segments.py @@ -5,8 +5,6 @@ from typing import Any from pydantic import BaseModel, ConfigDict, field_validator -from core.file.file_obj import FileVar - from .types import SegmentType @@ -78,14 +76,7 @@ class IntegerSegment(Segment): value: int -class FileSegment(Segment): - value_type: SegmentType = SegmentType.FILE - # TODO: embed FileVar in this model. - value: FileVar - @property - def markdown(self) -> str: - return self.value.to_markdown() class ObjectSegment(Segment): @@ -108,7 +99,13 @@ class ObjectSegment(Segment): class ArraySegment(Segment): @property def markdown(self) -> str: - return '\n'.join(['- ' + item.markdown for item in self.value]) + items = [] + for item in self.value: + if hasattr(item, 'to_markdown'): + items.append(item.to_markdown()) + else: + items.append(str(item)) + return '\n'.join(items) class ArrayAnySegment(ArraySegment): @@ -130,7 +127,3 @@ class ArrayObjectSegment(ArraySegment): value_type: SegmentType = SegmentType.ARRAY_OBJECT value: Sequence[Mapping[str, Any]] - -class ArrayFileSegment(ArraySegment): - value_type: SegmentType = SegmentType.ARRAY_FILE - value: Sequence[FileSegment] diff --git a/api/core/app/segments/types.py b/api/core/app/segments/types.py index a371058ef5..cdd2b0b4b0 100644 --- a/api/core/app/segments/types.py +++ b/api/core/app/segments/types.py @@ -10,8 +10,6 @@ class SegmentType(str, Enum): ARRAY_STRING = 'array[string]' ARRAY_NUMBER = 'array[number]' ARRAY_OBJECT = 'array[object]' - ARRAY_FILE = 'array[file]' OBJECT = 'object' - FILE = 'file' GROUP = 'group' diff --git a/api/core/app/segments/variables.py b/api/core/app/segments/variables.py index ac26e16542..8fef707fcf 100644 --- a/api/core/app/segments/variables.py +++ b/api/core/app/segments/variables.py @@ -4,11 +4,9 @@ from core.helper import encrypter from .segments import ( ArrayAnySegment, - ArrayFileSegment, ArrayNumberSegment, ArrayObjectSegment, ArrayStringSegment, - FileSegment, FloatSegment, IntegerSegment, NoneSegment, @@ -44,10 +42,6 @@ class IntegerVariable(IntegerSegment, Variable): pass -class FileVariable(FileSegment, Variable): - pass - - class ObjectVariable(ObjectSegment, Variable): pass @@ -68,9 +62,6 @@ class ArrayObjectVariable(ArrayObjectSegment, Variable): pass -class ArrayFileVariable(ArrayFileSegment, Variable): - pass - class SecretVariable(StringVariable): value_type: SegmentType = SegmentType.SECRET diff --git a/api/core/app/task_pipeline/workflow_cycle_state_manager.py b/api/core/app/task_pipeline/workflow_cycle_state_manager.py new file mode 100644 index 0000000000..e69de29bb2 diff --git a/api/core/file/message_file_parser.py b/api/core/file/message_file_parser.py index 01b89907db..085ff07cfd 100644 --- a/api/core/file/message_file_parser.py +++ b/api/core/file/message_file_parser.py @@ -99,7 +99,7 @@ class MessageFileParser: # return all file objs return new_files - def transform_message_files(self, files: list[MessageFile], file_extra_config: FileExtraConfig) -> list[FileVar]: + def transform_message_files(self, files: list[MessageFile], file_extra_config: FileExtraConfig): """ transform message files @@ -144,7 +144,7 @@ class MessageFileParser: return type_file_objs - def _to_file_obj(self, file: Union[dict, MessageFile], file_extra_config: FileExtraConfig) -> FileVar: + def _to_file_obj(self, file: Union[dict, MessageFile], file_extra_config: FileExtraConfig): """ transform file to file obj diff --git a/api/core/model_runtime/entities/defaults.py b/api/core/model_runtime/entities/defaults.py index 87fe4f681c..d2076bf74a 100644 --- a/api/core/model_runtime/entities/defaults.py +++ b/api/core/model_runtime/entities/defaults.py @@ -1,4 +1,3 @@ - from core.model_runtime.entities.model_entities import DefaultParameterName PARAMETER_RULE_TEMPLATE: dict[DefaultParameterName, dict] = { @@ -94,5 +93,16 @@ PARAMETER_RULE_TEMPLATE: dict[DefaultParameterName, dict] = { }, 'required': False, 'options': ['JSON', 'XML'], - } -} \ No newline at end of file + }, + DefaultParameterName.JSON_SCHEMA: { + 'label': { + 'en_US': 'JSON Schema', + }, + 'type': 'text', + 'help': { + 'en_US': 'Set a response json schema will ensure LLM to adhere it.', + 'zh_Hans': '设置返回的json schema，llm将按照它返回', + }, + 'required': False, + }, +} diff --git a/api/core/model_runtime/entities/model_entities.py b/api/core/model_runtime/entities/model_entities.py index 3d471787bb..c257ce63d2 100644 --- a/api/core/model_runtime/entities/model_entities.py +++ b/api/core/model_runtime/entities/model_entities.py @@ -95,6 +95,7 @@ class DefaultParameterName(Enum): FREQUENCY_PENALTY = "frequency_penalty" MAX_TOKENS = "max_tokens" RESPONSE_FORMAT = "response_format" + JSON_SCHEMA = "json_schema" @classmethod def value_of(cls, value: Any) -> 'DefaultParameterName': @@ -118,6 +119,7 @@ class ParameterType(Enum): INT = "int" STRING = "string" BOOLEAN = "boolean" + TEXT = "text" class ModelPropertyKey(Enum): diff --git a/api/core/model_runtime/model_providers/openai/llm/_position.yaml b/api/core/model_runtime/model_providers/openai/llm/_position.yaml index 21661b9a2b..ac7313aaa1 100644 --- a/api/core/model_runtime/model_providers/openai/llm/_position.yaml +++ b/api/core/model_runtime/model_providers/openai/llm/_position.yaml @@ -2,6 +2,7 @@ - gpt-4o - gpt-4o-2024-05-13 - gpt-4o-2024-08-06 +- chatgpt-4o-latest - gpt-4o-mini - gpt-4o-mini-2024-07-18 - gpt-4-turbo diff --git a/api/core/model_runtime/model_providers/openai/llm/chatgpt-4o-latest.yaml b/api/core/model_runtime/model_providers/openai/llm/chatgpt-4o-latest.yaml new file mode 100644 index 0000000000..98e236650c --- /dev/null +++ b/api/core/model_runtime/model_providers/openai/llm/chatgpt-4o-latest.yaml @@ -0,0 +1,44 @@ +model: chatgpt-4o-latest +label: + zh_Hans: chatgpt-4o-latest + en_US: chatgpt-4o-latest +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision +model_properties: + mode: chat + context_size: 128000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 16384 + - name: response_format + label: + zh_Hans: 回复格式 + en_US: response_format + type: string + help: + zh_Hans: 指定模型必须输出的格式 + en_US: specifying the format that the model must output + required: false + options: + - text + - json_object +pricing: + input: '2.50' + output: '10.00' + unit: '0.000001' + currency: USD diff --git a/api/core/model_runtime/model_providers/openai/llm/gpt-4o-2024-08-06.yaml b/api/core/model_runtime/model_providers/openai/llm/gpt-4o-2024-08-06.yaml index cf2de0f73a..7e430c51a7 100644 --- a/api/core/model_runtime/model_providers/openai/llm/gpt-4o-2024-08-06.yaml +++ b/api/core/model_runtime/model_providers/openai/llm/gpt-4o-2024-08-06.yaml @@ -37,6 +37,9 @@ parameter_rules: options: - text - json_object + - json_schema + - name: json_schema + use_template: json_schema pricing: input: '2.50' output: '10.00' diff --git a/api/core/model_runtime/model_providers/openai/llm/gpt-4o-mini.yaml b/api/core/model_runtime/model_providers/openai/llm/gpt-4o-mini.yaml index b97fbf8aab..23dcf85085 100644 --- a/api/core/model_runtime/model_providers/openai/llm/gpt-4o-mini.yaml +++ b/api/core/model_runtime/model_providers/openai/llm/gpt-4o-mini.yaml @@ -37,6 +37,9 @@ parameter_rules: options: - text - json_object + - json_schema + - name: json_schema + use_template: json_schema pricing: input: '0.15' output: '0.60' diff --git a/api/core/model_runtime/model_providers/openai/llm/llm.py b/api/core/model_runtime/model_providers/openai/llm/llm.py index aae2729bdf..06135c9584 100644 --- a/api/core/model_runtime/model_providers/openai/llm/llm.py +++ b/api/core/model_runtime/model_providers/openai/llm/llm.py @@ -1,3 +1,4 @@ +import json import logging from collections.abc import Generator from typing import Optional, Union, cast @@ -544,13 +545,18 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel): response_format = model_parameters.get("response_format") if response_format: - if response_format == "json_object": - response_format = {"type": "json_object"} + if response_format == "json_schema": + json_schema = model_parameters.get("json_schema") + if not json_schema: + raise ValueError("Must define JSON Schema when the response format is json_schema") + try: + schema = json.loads(json_schema) + except: + raise ValueError(f"not currect json_schema format: {json_schema}") + model_parameters.pop("json_schema") + model_parameters["response_format"] = {"type": "json_schema", "json_schema": schema} else: - response_format = {"type": "text"} - - model_parameters["response_format"] = response_format - + model_parameters["response_format"] = {"type": response_format} extra_model_kwargs = {} @@ -922,11 +928,14 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel): tools: Optional[list[PromptMessageTool]] = None) -> int: """Calculate num tokens for gpt-3.5-turbo and gpt-4 with tiktoken package. - Official documentation: https://github.com/openai/openai-cookbook/blob/ - main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb""" + Official documentation: https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb""" if model.startswith('ft:'): model = model.split(':')[1] + # Currently, we can use gpt4o to calculate chatgpt-4o-latest's token. + if model == "chatgpt-4o-latest": + model = "gpt-4o" + try: encoding = tiktoken.encoding_for_model(model) except KeyError: @@ -946,7 +955,7 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel): raise NotImplementedError( f"get_num_tokens_from_messages() is not presently implemented " f"for model {model}." - "See https://github.com/openai/openai-python/blob/main/chatml.md for " + "See https://platform.openai.com/docs/advanced-usage/managing-tokens for " "information on how messages are converted to tokens." ) num_tokens = 0 diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/Llama3-Chinese_v2.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/Llama3-Chinese_v2.yaml new file mode 100644 index 0000000000..87712874b9 --- /dev/null +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Llama3-Chinese_v2.yaml @@ -0,0 +1,61 @@ +model: Llama3-Chinese_v2 +label: + en_US: Llama3-Chinese_v2 +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 8192 +parameter_rules: + - name: temperature + use_template: temperature + type: float + default: 0.5 + min: 0.0 + max: 2.0 + help: + zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。 + en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain. + - name: max_tokens + use_template: max_tokens + type: int + default: 600 + min: 1 + max: 1248 + help: + zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。 + en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time. + - name: top_p + use_template: top_p + type: float + default: 0.8 + min: 0.1 + max: 0.9 + help: + zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。 + en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated. + - name: top_k + type: int + min: 0 + max: 99 + label: + zh_Hans: 取样数量 + en_US: Top k + help: + zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。 + en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. + - name: repetition_penalty + required: false + type: float + default: 1.1 + label: + en_US: Repetition penalty + help: + zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 + en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. +pricing: + input: "0.000" + output: "0.000" + unit: "0.000" + currency: RMB diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3-70B-Instruct-GPTQ-Int4.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3-70B-Instruct-GPTQ-Int4.yaml new file mode 100644 index 0000000000..f16f3de60b --- /dev/null +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3-70B-Instruct-GPTQ-Int4.yaml @@ -0,0 +1,61 @@ +model: Meta-Llama-3-70B-Instruct-GPTQ-Int4 +label: + en_US: Meta-Llama-3-70B-Instruct-GPTQ-Int4 +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 1024 +parameter_rules: + - name: temperature + use_template: temperature + type: float + default: 0.5 + min: 0.0 + max: 2.0 + help: + zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。 + en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain. + - name: max_tokens + use_template: max_tokens + type: int + default: 600 + min: 1 + max: 1248 + help: + zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。 + en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time. + - name: top_p + use_template: top_p + type: float + default: 0.8 + min: 0.1 + max: 0.9 + help: + zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。 + en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated. + - name: top_k + type: int + min: 0 + max: 99 + label: + zh_Hans: 取样数量 + en_US: Top k + help: + zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。 + en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. + - name: repetition_penalty + required: false + type: float + default: 1.1 + label: + en_US: Repetition penalty + help: + zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 + en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. +pricing: + input: "0.000" + output: "0.000" + unit: "0.000" + currency: RMB diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3-8B-Instruct.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3-8B-Instruct.yaml new file mode 100644 index 0000000000..21267c240b --- /dev/null +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3-8B-Instruct.yaml @@ -0,0 +1,61 @@ +model: Meta-Llama-3-8B-Instruct +label: + en_US: Meta-Llama-3-8B-Instruct +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 8192 +parameter_rules: + - name: temperature + use_template: temperature + type: float + default: 0.5 + min: 0.0 + max: 2.0 + help: + zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。 + en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain. + - name: max_tokens + use_template: max_tokens + type: int + default: 600 + min: 1 + max: 1248 + help: + zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。 + en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time. + - name: top_p + use_template: top_p + type: float + default: 0.8 + min: 0.1 + max: 0.9 + help: + zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。 + en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated. + - name: top_k + type: int + min: 0 + max: 99 + label: + zh_Hans: 取样数量 + en_US: Top k + help: + zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。 + en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. + - name: repetition_penalty + required: false + type: float + default: 1.1 + label: + en_US: Repetition penalty + help: + zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 + en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. +pricing: + input: "0.000" + output: "0.000" + unit: "0.000" + currency: RMB diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3.1-405B-Instruct-AWQ-INT4.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3.1-405B-Instruct-AWQ-INT4.yaml new file mode 100644 index 0000000000..80c7ec40f2 --- /dev/null +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3.1-405B-Instruct-AWQ-INT4.yaml @@ -0,0 +1,61 @@ +model: Meta-Llama-3.1-405B-Instruct-AWQ-INT4 +label: + en_US: Meta-Llama-3.1-405B-Instruct-AWQ-INT4 +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 410960 +parameter_rules: + - name: temperature + use_template: temperature + type: float + default: 0.5 + min: 0.0 + max: 2.0 + help: + zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。 + en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain. + - name: max_tokens + use_template: max_tokens + type: int + default: 600 + min: 1 + max: 1248 + help: + zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。 + en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time. + - name: top_p + use_template: top_p + type: float + default: 0.8 + min: 0.1 + max: 0.9 + help: + zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。 + en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated. + - name: top_k + type: int + min: 0 + max: 99 + label: + zh_Hans: 取样数量 + en_US: Top k + help: + zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。 + en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. + - name: repetition_penalty + required: false + type: float + default: 1.1 + label: + en_US: Repetition penalty + help: + zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 + en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. +pricing: + input: "0.000" + output: "0.000" + unit: "0.000" + currency: RMB diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3.1-8B-Instruct.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3.1-8B-Instruct.yaml new file mode 100644 index 0000000000..bbab46344c --- /dev/null +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3.1-8B-Instruct.yaml @@ -0,0 +1,61 @@ +model: Meta-Llama-3.1-8B-Instruct +label: + en_US: Meta-Llama-3.1-8B-Instruct +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 4096 +parameter_rules: + - name: temperature + use_template: temperature + type: float + default: 0.1 + min: 0.0 + max: 2.0 + help: + zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。 + en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain. + - name: max_tokens + use_template: max_tokens + type: int + default: 600 + min: 1 + max: 1248 + help: + zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。 + en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time. + - name: top_p + use_template: top_p + type: float + default: 0.8 + min: 0.1 + max: 0.9 + help: + zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。 + en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated. + - name: top_k + type: int + min: 0 + max: 99 + label: + zh_Hans: 取样数量 + en_US: Top k + help: + zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。 + en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. + - name: repetition_penalty + required: false + type: float + default: 1.1 + label: + en_US: Repetition penalty + help: + zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 + en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. +pricing: + input: "0.000" + output: "0.000" + unit: "0.000" + currency: RMB diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen-14B-Chat-Int4.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen-14B-Chat-Int4.yaml index af6fb91cd9..ec6d9bcc14 100644 --- a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen-14B-Chat-Int4.yaml +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen-14B-Chat-Int4.yaml @@ -55,7 +55,8 @@ parameter_rules: zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. pricing: - input: '0.000' - output: '0.000' - unit: '0.000' + input: "0.000" + output: "0.000" + unit: "0.000" currency: RMB +deprecated: true diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-110B-Chat-GPTQ-Int4.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-110B-Chat-GPTQ-Int4.yaml index 4ab9a80055..b561a53039 100644 --- a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-110B-Chat-GPTQ-Int4.yaml +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-110B-Chat-GPTQ-Int4.yaml @@ -55,7 +55,8 @@ parameter_rules: zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. pricing: - input: '0.000' - output: '0.000' - unit: '0.000' + input: "0.000" + output: "0.000" + unit: "0.000" currency: RMB +deprecated: true diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-72B-Chat-GPTQ-Int4.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-72B-Chat-GPTQ-Int4.yaml index 4a8b1cf479..841dd97f35 100644 --- a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-72B-Chat-GPTQ-Int4.yaml +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-72B-Chat-GPTQ-Int4.yaml @@ -6,7 +6,7 @@ features: - agent-thought model_properties: mode: chat - context_size: 8192 + context_size: 2048 parameter_rules: - name: temperature use_template: temperature @@ -55,7 +55,7 @@ parameter_rules: zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. pricing: - input: '0.000' - output: '0.000' - unit: '0.000' + input: "0.000" + output: "0.000" + unit: "0.000" currency: RMB diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-7B.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-7B.yaml index b076504493..33d5d12b22 100644 --- a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-7B.yaml +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-7B.yaml @@ -6,7 +6,7 @@ features: - agent-thought model_properties: mode: completion - context_size: 8192 + context_size: 32768 parameter_rules: - name: temperature use_template: temperature @@ -55,7 +55,7 @@ parameter_rules: zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. pricing: - input: '0.000' - output: '0.000' - unit: '0.000' + input: "0.000" + output: "0.000" + unit: "0.000" currency: RMB diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen2-72B-Instruct-GPTQ-Int4.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen2-72B-Instruct-GPTQ-Int4.yaml index e24a69fe63..62255cc7d2 100644 --- a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen2-72B-Instruct-GPTQ-Int4.yaml +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen2-72B-Instruct-GPTQ-Int4.yaml @@ -8,12 +8,12 @@ features: - stream-tool-call model_properties: mode: chat - context_size: 8192 + context_size: 2048 parameter_rules: - name: temperature use_template: temperature type: float - default: 0.3 + default: 0.7 min: 0.0 max: 2.0 help: @@ -57,7 +57,7 @@ parameter_rules: zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. pricing: - input: '0.000' - output: '0.000' - unit: '0.000' + input: "0.000" + output: "0.000" + unit: "0.000" currency: RMB diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen2-72B-Instruct.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen2-72B-Instruct.yaml new file mode 100644 index 0000000000..cea6560295 --- /dev/null +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen2-72B-Instruct.yaml @@ -0,0 +1,61 @@ +model: Qwen2-72B-Instruct +label: + en_US: Qwen2-72B-Instruct +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 131072 +parameter_rules: + - name: temperature + use_template: temperature + type: float + default: 0.5 + min: 0.0 + max: 2.0 + help: + zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。 + en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain. + - name: max_tokens + use_template: max_tokens + type: int + default: 600 + min: 1 + max: 1248 + help: + zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。 + en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time. + - name: top_p + use_template: top_p + type: float + default: 0.8 + min: 0.1 + max: 0.9 + help: + zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。 + en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated. + - name: top_k + type: int + min: 0 + max: 99 + label: + zh_Hans: 取样数量 + en_US: Top k + help: + zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。 + en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. + - name: repetition_penalty + required: false + type: float + default: 1.1 + label: + en_US: Repetition penalty + help: + zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 + en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. +pricing: + input: "0.000" + output: "0.000" + unit: "0.000" + currency: RMB diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen2-7B.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen2-7B.yaml index e3d804729d..2f3f1f0225 100644 --- a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen2-7B.yaml +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen2-7B.yaml @@ -8,7 +8,7 @@ features: - stream-tool-call model_properties: mode: completion - context_size: 8192 + context_size: 32768 parameter_rules: - name: temperature use_template: temperature @@ -57,7 +57,7 @@ parameter_rules: zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. pricing: - input: '0.000' - output: '0.000' - unit: '0.000' + input: "0.000" + output: "0.000" + unit: "0.000" currency: RMB diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/_position.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/_position.yaml index b95f6bdc1b..2c9eac0e49 100644 --- a/api/core/model_runtime/model_providers/perfxcloud/llm/_position.yaml +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/_position.yaml @@ -1,6 +1,15 @@ +- Meta-Llama-3.1-405B-Instruct-AWQ-INT4 +- Meta-Llama-3.1-8B-Instruct +- Meta-Llama-3-70B-Instruct-GPTQ-Int4 +- Meta-Llama-3-8B-Instruct - Qwen2-72B-Instruct-GPTQ-Int4 +- Qwen2-72B-Instruct - Qwen2-7B -- Qwen1.5-110B-Chat-GPTQ-Int4 +- Qwen-14B-Chat-Int4 - Qwen1.5-72B-Chat-GPTQ-Int4 - Qwen1.5-7B -- Qwen-14B-Chat-Int4 +- Qwen1.5-110B-Chat-GPTQ-Int4 +- deepseek-v2-chat +- deepseek-v2-lite-chat +- Llama3-Chinese_v2 +- chatglm3-6b diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/chatglm3-6b.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/chatglm3-6b.yaml new file mode 100644 index 0000000000..f9c26b7f90 --- /dev/null +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/chatglm3-6b.yaml @@ -0,0 +1,61 @@ +model: chatglm3-6b +label: + en_US: chatglm3-6b +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 8192 +parameter_rules: + - name: temperature + use_template: temperature + type: float + default: 0.5 + min: 0.0 + max: 2.0 + help: + zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。 + en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain. + - name: max_tokens + use_template: max_tokens + type: int + default: 600 + min: 1 + max: 1248 + help: + zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。 + en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time. + - name: top_p + use_template: top_p + type: float + default: 0.8 + min: 0.1 + max: 0.9 + help: + zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。 + en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated. + - name: top_k + type: int + min: 0 + max: 99 + label: + zh_Hans: 取样数量 + en_US: Top k + help: + zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。 + en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. + - name: repetition_penalty + required: false + type: float + default: 1.1 + label: + en_US: Repetition penalty + help: + zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 + en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. +pricing: + input: "0.000" + output: "0.000" + unit: "0.000" + currency: RMB diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/deepseek-v2-chat.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/deepseek-v2-chat.yaml new file mode 100644 index 0000000000..078922ef95 --- /dev/null +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/deepseek-v2-chat.yaml @@ -0,0 +1,61 @@ +model: deepseek-v2-chat +label: + en_US: deepseek-v2-chat +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 4096 +parameter_rules: + - name: temperature + use_template: temperature + type: float + default: 0.5 + min: 0.0 + max: 2.0 + help: + zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。 + en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain. + - name: max_tokens + use_template: max_tokens + type: int + default: 600 + min: 1 + max: 1248 + help: + zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。 + en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time. + - name: top_p + use_template: top_p + type: float + default: 0.8 + min: 0.1 + max: 0.9 + help: + zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。 + en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated. + - name: top_k + type: int + min: 0 + max: 99 + label: + zh_Hans: 取样数量 + en_US: Top k + help: + zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。 + en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. + - name: repetition_penalty + required: false + type: float + default: 1.1 + label: + en_US: Repetition penalty + help: + zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 + en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. +pricing: + input: "0.000" + output: "0.000" + unit: "0.000" + currency: RMB diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/deepseek-v2-lite-chat.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/deepseek-v2-lite-chat.yaml new file mode 100644 index 0000000000..4ff3af7b51 --- /dev/null +++ b/api/core/model_runtime/model_providers/perfxcloud/llm/deepseek-v2-lite-chat.yaml @@ -0,0 +1,61 @@ +model: deepseek-v2-lite-chat +label: + en_US: deepseek-v2-lite-chat +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 2048 +parameter_rules: + - name: temperature + use_template: temperature + type: float + default: 0.5 + min: 0.0 + max: 2.0 + help: + zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。 + en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain. + - name: max_tokens + use_template: max_tokens + type: int + default: 600 + min: 1 + max: 1248 + help: + zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。 + en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time. + - name: top_p + use_template: top_p + type: float + default: 0.8 + min: 0.1 + max: 0.9 + help: + zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。 + en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated. + - name: top_k + type: int + min: 0 + max: 99 + label: + zh_Hans: 取样数量 + en_US: Top k + help: + zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。 + en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. + - name: repetition_penalty + required: false + type: float + default: 1.1 + label: + en_US: Repetition penalty + help: + zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 + en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. +pricing: + input: "0.000" + output: "0.000" + unit: "0.000" + currency: RMB diff --git a/api/core/model_runtime/model_providers/perfxcloud/text_embedding/BAAI-bge-large-en-v1.5.yaml b/api/core/model_runtime/model_providers/perfxcloud/text_embedding/BAAI-bge-large-en-v1.5.yaml new file mode 100644 index 0000000000..5756fb3d14 --- /dev/null +++ b/api/core/model_runtime/model_providers/perfxcloud/text_embedding/BAAI-bge-large-en-v1.5.yaml @@ -0,0 +1,4 @@ +model: BAAI/bge-large-en-v1.5 +model_type: text-embedding +model_properties: + context_size: 32768 diff --git a/api/core/model_runtime/model_providers/perfxcloud/text_embedding/BAAI-bge-large-zh-v1.5.yaml b/api/core/model_runtime/model_providers/perfxcloud/text_embedding/BAAI-bge-large-zh-v1.5.yaml new file mode 100644 index 0000000000..4204ab2860 --- /dev/null +++ b/api/core/model_runtime/model_providers/perfxcloud/text_embedding/BAAI-bge-large-zh-v1.5.yaml @@ -0,0 +1,4 @@ +model: BAAI/bge-large-zh-v1.5 +model_type: text-embedding +model_properties: + context_size: 32768 diff --git a/api/core/model_runtime/model_providers/tongyi/llm/farui-plus.yaml b/api/core/model_runtime/model_providers/tongyi/llm/farui-plus.yaml new file mode 100644 index 0000000000..aad07f5673 --- /dev/null +++ b/api/core/model_runtime/model_providers/tongyi/llm/farui-plus.yaml @@ -0,0 +1,81 @@ +model: farui-plus +label: + en_US: farui-plus +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call +model_properties: + mode: chat + context_size: 12288 +parameter_rules: + - name: temperature + use_template: temperature + type: float + default: 0.3 + min: 0.0 + max: 2.0 + help: + zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。 + en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain. + - name: max_tokens + use_template: max_tokens + type: int + default: 2000 + min: 1 + max: 2000 + help: + zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。 + en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time. + - name: top_p + use_template: top_p + type: float + default: 0.8 + min: 0.1 + max: 0.9 + help: + zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。 + en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated. + - name: top_k + type: int + min: 0 + max: 99 + label: + zh_Hans: 取样数量 + en_US: Top k + help: + zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。 + en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. + - name: seed + required: false + type: int + default: 1234 + label: + zh_Hans: 随机种子 + en_US: Random seed + help: + zh_Hans: 生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。 + en_US: The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time. + - name: repetition_penalty + required: false + type: float + default: 1.1 + label: + en_US: Repetition penalty + help: + zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。 + en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment. + - name: enable_search + type: boolean + default: false + help: + zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。 + en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic. + - name: response_format + use_template: response_format +pricing: + input: '0.02' + output: '0.02' + unit: '0.001' + currency: RMB diff --git a/api/core/model_runtime/model_providers/tongyi/llm/llm.py b/api/core/model_runtime/model_providers/tongyi/llm/llm.py index a75db78d8c..4e1bb0a5a4 100644 --- a/api/core/model_runtime/model_providers/tongyi/llm/llm.py +++ b/api/core/model_runtime/model_providers/tongyi/llm/llm.py @@ -159,6 +159,8 @@ You should also complete the text started with ``` but not tell ``` directly. """ if model in ['qwen-turbo-chat', 'qwen-plus-chat']: model = model.replace('-chat', '') + if model == 'farui-plus': + model = 'qwen-farui-plus' if model in self.tokenizers: tokenizer = self.tokenizers[model] diff --git a/api/core/model_runtime/model_providers/upstage/llm/_position.yaml b/api/core/model_runtime/model_providers/upstage/llm/_position.yaml index d4f03e1988..7992843dcb 100644 --- a/api/core/model_runtime/model_providers/upstage/llm/_position.yaml +++ b/api/core/model_runtime/model_providers/upstage/llm/_position.yaml @@ -1 +1 @@ -- soloar-1-mini-chat +- solar-1-mini-chat diff --git a/api/core/prompt/simple_prompt_transform.py b/api/core/prompt/simple_prompt_transform.py index 452b270348..fd7ed0181b 100644 --- a/api/core/prompt/simple_prompt_transform.py +++ b/api/core/prompt/simple_prompt_transform.py @@ -1,11 +1,10 @@ import enum import json import os -from typing import Optional +from typing import TYPE_CHECKING, Optional from core.app.app_config.entities import PromptTemplateEntity from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity -from core.file.file_obj import FileVar from core.memory.token_buffer_memory import TokenBufferMemory from core.model_runtime.entities.message_entities import ( PromptMessage, @@ -18,6 +17,9 @@ from core.prompt.prompt_transform import PromptTransform from core.prompt.utils.prompt_template_parser import PromptTemplateParser from models.model import AppMode +if TYPE_CHECKING: + from core.file.file_obj import FileVar + class ModelMode(enum.Enum): COMPLETION = 'completion' @@ -50,7 +52,7 @@ class SimplePromptTransform(PromptTransform): prompt_template_entity: PromptTemplateEntity, inputs: dict, query: str, - files: list[FileVar], + files: list["FileVar"], context: Optional[str], memory: Optional[TokenBufferMemory], model_config: ModelConfigWithCredentialsEntity) -> \ @@ -163,7 +165,7 @@ class SimplePromptTransform(PromptTransform): inputs: dict, query: str, context: Optional[str], - files: list[FileVar], + files: list["FileVar"], memory: Optional[TokenBufferMemory], model_config: ModelConfigWithCredentialsEntity) \ -> tuple[list[PromptMessage], Optional[list[str]]]: @@ -206,7 +208,7 @@ class SimplePromptTransform(PromptTransform): inputs: dict, query: str, context: Optional[str], - files: list[FileVar], + files: list["FileVar"], memory: Optional[TokenBufferMemory], model_config: ModelConfigWithCredentialsEntity) \ -> tuple[list[PromptMessage], Optional[list[str]]]: @@ -255,7 +257,7 @@ class SimplePromptTransform(PromptTransform): return [self.get_last_user_message(prompt, files)], stops - def get_last_user_message(self, prompt: str, files: list[FileVar]) -> UserPromptMessage: + def get_last_user_message(self, prompt: str, files: list["FileVar"]) -> UserPromptMessage: if files: prompt_message_contents = [TextPromptMessageContent(data=prompt)] for file in files: diff --git a/api/core/rag/datasource/vdb/elasticsearch/__init__.py b/api/core/rag/datasource/vdb/elasticsearch/__init__.py new file mode 100644 index 0000000000..e69de29bb2 diff --git a/api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py b/api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py new file mode 100644 index 0000000000..01ba6fb324 --- /dev/null +++ b/api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py @@ -0,0 +1,191 @@ +import json +from typing import Any + +import requests +from elasticsearch import Elasticsearch +from flask import current_app +from pydantic import BaseModel, model_validator + +from core.rag.datasource.entity.embedding import Embeddings +from core.rag.datasource.vdb.vector_base import BaseVector +from core.rag.datasource.vdb.vector_factory import AbstractVectorFactory +from core.rag.datasource.vdb.vector_type import VectorType +from core.rag.models.document import Document +from models.dataset import Dataset + + +class ElasticSearchConfig(BaseModel): + host: str + port: str + username: str + password: str + + @model_validator(mode='before') + def validate_config(cls, values: dict) -> dict: + if not values['host']: + raise ValueError("config HOST is required") + if not values['port']: + raise ValueError("config PORT is required") + if not values['username']: + raise ValueError("config USERNAME is required") + if not values['password']: + raise ValueError("config PASSWORD is required") + return values + + +class ElasticSearchVector(BaseVector): + def __init__(self, index_name: str, config: ElasticSearchConfig, attributes: list): + super().__init__(index_name.lower()) + self._client = self._init_client(config) + self._attributes = attributes + + def _init_client(self, config: ElasticSearchConfig) -> Elasticsearch: + try: + client = Elasticsearch( + hosts=f'{config.host}:{config.port}', + basic_auth=(config.username, config.password), + request_timeout=100000, + retry_on_timeout=True, + max_retries=10000, + ) + except requests.exceptions.ConnectionError: + raise ConnectionError("Vector database connection error") + + return client + + def get_type(self) -> str: + return 'elasticsearch' + + def add_texts(self, documents: list[Document], embeddings: list[list[float]], **kwargs): + uuids = self._get_uuids(documents) + texts = [d.page_content for d in documents] + metadatas = [d.metadata for d in documents] + + if not self._client.indices.exists(index=self._collection_name): + dim = len(embeddings[0]) + mapping = { + "properties": { + "text": { + "type": "text" + }, + "vector": { + "type": "dense_vector", + "index": True, + "dims": dim, + "similarity": "l2_norm" + }, + } + } + self._client.indices.create(index=self._collection_name, mappings=mapping) + + added_ids = [] + for i, text in enumerate(texts): + self._client.index(index=self._collection_name, + id=uuids[i], + document={ + "text": text, + "vector": embeddings[i] if embeddings[i] else None, + "metadata": metadatas[i] if metadatas[i] else {}, + }) + added_ids.append(uuids[i]) + + self._client.indices.refresh(index=self._collection_name) + return uuids + + def text_exists(self, id: str) -> bool: + return self._client.exists(index=self._collection_name, id=id).__bool__() + + def delete_by_ids(self, ids: list[str]) -> None: + for id in ids: + self._client.delete(index=self._collection_name, id=id) + + def delete_by_metadata_field(self, key: str, value: str) -> None: + query_str = { + 'query': { + 'match': { + f'metadata.{key}': f'{value}' + } + } + } + results = self._client.search(index=self._collection_name, body=query_str) + ids = [hit['_id'] for hit in results['hits']['hits']] + if ids: + self.delete_by_ids(ids) + + def delete(self) -> None: + self._client.indices.delete(index=self._collection_name) + + def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]: + query_str = { + "query": { + "script_score": { + "query": { + "match_all": {} + }, + "script": { + "source": "cosineSimilarity(params.query_vector, 'vector') + 1.0", + "params": { + "query_vector": query_vector + } + } + } + } + } + + results = self._client.search(index=self._collection_name, body=query_str) + + docs_and_scores = [] + for hit in results['hits']['hits']: + docs_and_scores.append( + (Document(page_content=hit['_source']['text'], metadata=hit['_source']['metadata']), hit['_score'])) + + docs = [] + for doc, score in docs_and_scores: + score_threshold = kwargs.get("score_threshold", .0) if kwargs.get('score_threshold', .0) else 0.0 + if score > score_threshold: + doc.metadata['score'] = score + docs.append(doc) + + # Sort the documents by score in descending order + docs = sorted(docs, key=lambda x: x.metadata['score'], reverse=True) + + return docs + def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]: + query_str = { + "match": { + "text": query + } + } + results = self._client.search(index=self._collection_name, query=query_str) + docs = [] + for hit in results['hits']['hits']: + docs.append(Document(page_content=hit['_source']['text'], metadata=hit['_source']['metadata'])) + + return docs + + def create(self, texts: list[Document], embeddings: list[list[float]], **kwargs): + return self.add_texts(texts, embeddings, **kwargs) + + +class ElasticSearchVectorFactory(AbstractVectorFactory): + def init_vector(self, dataset: Dataset, attributes: list, embeddings: Embeddings) -> ElasticSearchVector: + if dataset.index_struct_dict: + class_prefix: str = dataset.index_struct_dict['vector_store']['class_prefix'] + collection_name = class_prefix + else: + dataset_id = dataset.id + collection_name = Dataset.gen_collection_name_by_id(dataset_id) + dataset.index_struct = json.dumps( + self.gen_index_struct_dict(VectorType.ELASTICSEARCH, collection_name)) + + config = current_app.config + return ElasticSearchVector( + index_name=collection_name, + config=ElasticSearchConfig( + host=config.get('ELASTICSEARCH_HOST'), + port=config.get('ELASTICSEARCH_PORT'), + username=config.get('ELASTICSEARCH_USERNAME'), + password=config.get('ELASTICSEARCH_PASSWORD'), + ), + attributes=[] + ) diff --git a/api/core/rag/datasource/vdb/myscale/myscale_vector.py b/api/core/rag/datasource/vdb/myscale/myscale_vector.py index cff9293baa..4ae1a3395b 100644 --- a/api/core/rag/datasource/vdb/myscale/myscale_vector.py +++ b/api/core/rag/datasource/vdb/myscale/myscale_vector.py @@ -93,7 +93,7 @@ class MyScaleVector(BaseVector): @staticmethod def escape_str(value: Any) -> str: - return "".join(f"\\{c}" if c in ("\\", "'") else c for c in str(value)) + return "".join(" " if c in ("\\", "'") else c for c in str(value)) def text_exists(self, id: str) -> bool: results = self._client.query(f"SELECT id FROM {self._config.database}.{self._collection_name} WHERE id='{id}'") @@ -118,7 +118,7 @@ class MyScaleVector(BaseVector): return self._search(f"distance(vector, {str(query_vector)})", self._vec_order, **kwargs) def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]: - return self._search(f"TextSearch(text, '{query}')", SortOrder.DESC, **kwargs) + return self._search(f"TextSearch('enable_nlq=false')(text, '{query}')", SortOrder.DESC, **kwargs) def _search(self, dist: str, order: SortOrder, **kwargs: Any) -> list[Document]: top_k = kwargs.get("top_k", 5) diff --git a/api/core/rag/datasource/vdb/vector_factory.py b/api/core/rag/datasource/vdb/vector_factory.py index fad60ecf45..3e9ca8e1fe 100644 --- a/api/core/rag/datasource/vdb/vector_factory.py +++ b/api/core/rag/datasource/vdb/vector_factory.py @@ -71,6 +71,9 @@ class Vector: case VectorType.RELYT: from core.rag.datasource.vdb.relyt.relyt_vector import RelytVectorFactory return RelytVectorFactory + case VectorType.ELASTICSEARCH: + from core.rag.datasource.vdb.elasticsearch.elasticsearch_vector import ElasticSearchVectorFactory + return ElasticSearchVectorFactory case VectorType.TIDB_VECTOR: from core.rag.datasource.vdb.tidb_vector.tidb_vector import TiDBVectorFactory return TiDBVectorFactory diff --git a/api/core/rag/datasource/vdb/vector_type.py b/api/core/rag/datasource/vdb/vector_type.py index 77495044df..317ca6abc8 100644 --- a/api/core/rag/datasource/vdb/vector_type.py +++ b/api/core/rag/datasource/vdb/vector_type.py @@ -15,3 +15,4 @@ class VectorType(str, Enum): OPENSEARCH = 'opensearch' TENCENT = 'tencent' ORACLE = 'oracle' + ELASTICSEARCH = 'elasticsearch' diff --git a/api/core/tools/entities/tool_entities.py b/api/core/tools/entities/tool_entities.py index 569a1d3238..2e4433d9f6 100644 --- a/api/core/tools/entities/tool_entities.py +++ b/api/core/tools/entities/tool_entities.py @@ -46,7 +46,7 @@ class ToolProviderType(Enum): if mode.value == value: return mode raise ValueError(f'invalid mode value {value}') - + class ApiProviderSchemaType(Enum): """ Enum class for api provider schema type. @@ -68,7 +68,7 @@ class ApiProviderSchemaType(Enum): if mode.value == value: return mode raise ValueError(f'invalid mode value {value}') - + class ApiProviderAuthType(Enum): """ Enum class for api provider auth type. @@ -103,8 +103,8 @@ class ToolInvokeMessage(BaseModel): """ plain text, image url or link url """ - message: Union[str, bytes, dict] = None - meta: dict[str, Any] = None + message: str | bytes | dict | None = None + meta: dict[str, Any] | None = None save_as: str = '' class ToolInvokeMessageBinary(BaseModel): @@ -154,8 +154,8 @@ class ToolParameter(BaseModel): options: Optional[list[ToolParameterOption]] = None @classmethod - def get_simple_instance(cls, - name: str, llm_description: str, type: ToolParameterType, + def get_simple_instance(cls, + name: str, llm_description: str, type: ToolParameterType, required: bool, options: Optional[list[str]] = None) -> 'ToolParameter': """ get a simple tool parameter @@ -222,7 +222,7 @@ class ToolProviderCredentials(BaseModel): if mode.value == value: return mode raise ValueError(f'invalid mode value {value}') - + @staticmethod def default(value: str) -> str: return "" @@ -290,7 +290,7 @@ class ToolRuntimeVariablePool(BaseModel): 'tenant_id': self.tenant_id, 'pool': [variable.model_dump() for variable in self.pool], } - + def set_text(self, tool_name: str, name: str, value: str) -> None: """ set a text variable @@ -301,7 +301,7 @@ class ToolRuntimeVariablePool(BaseModel): variable = cast(ToolRuntimeTextVariable, variable) variable.value = value return - + variable = ToolRuntimeTextVariable( type=ToolRuntimeVariableType.TEXT, name=name, @@ -334,7 +334,7 @@ class ToolRuntimeVariablePool(BaseModel): variable = cast(ToolRuntimeImageVariable, variable) variable.value = value return - + variable = ToolRuntimeImageVariable( type=ToolRuntimeVariableType.IMAGE, name=name, @@ -388,21 +388,21 @@ class ToolInvokeMeta(BaseModel): Get an empty instance of ToolInvokeMeta """ return cls(time_cost=0.0, error=None, tool_config={}) - + @classmethod def error_instance(cls, error: str) -> 'ToolInvokeMeta': """ Get an instance of ToolInvokeMeta with error """ return cls(time_cost=0.0, error=error, tool_config={}) - + def to_dict(self) -> dict: return { 'time_cost': self.time_cost, 'error': self.error, 'tool_config': self.tool_config, } - + class ToolLabel(BaseModel): """ Tool label @@ -416,4 +416,4 @@ class ToolInvokeFrom(Enum): Enum class for tool invoke """ WORKFLOW = "workflow" - AGENT = "agent" \ No newline at end of file + AGENT = "agent" diff --git a/api/core/tools/provider/builtin/gitlab/_assets/gitlab.svg b/api/core/tools/provider/builtin/gitlab/_assets/gitlab.svg new file mode 100644 index 0000000000..07734077d5 --- /dev/null +++ b/api/core/tools/provider/builtin/gitlab/_assets/gitlab.svg @@ -0,0 +1,2 @@ + + \ No newline at end of file diff --git a/api/core/tools/provider/builtin/gitlab/gitlab.py b/api/core/tools/provider/builtin/gitlab/gitlab.py new file mode 100644 index 0000000000..fca34ae15f --- /dev/null +++ b/api/core/tools/provider/builtin/gitlab/gitlab.py @@ -0,0 +1,34 @@ +from typing import Any + +import requests + +from core.tools.errors import ToolProviderCredentialValidationError +from core.tools.provider.builtin_tool_provider import BuiltinToolProviderController + + +class GitlabProvider(BuiltinToolProviderController): + def _validate_credentials(self, credentials: dict[str, Any]) -> None: + try: + if 'access_tokens' not in credentials or not credentials.get('access_tokens'): + raise ToolProviderCredentialValidationError("Gitlab Access Tokens is required.") + + if 'site_url' not in credentials or not credentials.get('site_url'): + site_url = 'https://gitlab.com' + else: + site_url = credentials.get('site_url') + + try: + headers = { + "Content-Type": "application/vnd.text+json", + "Authorization": f"Bearer {credentials.get('access_tokens')}", + } + + response = requests.get( + url= f"{site_url}/api/v4/user", + headers=headers) + if response.status_code != 200: + raise ToolProviderCredentialValidationError((response.json()).get('message')) + except Exception as e: + raise ToolProviderCredentialValidationError("Gitlab Access Tokens and Api Version is invalid. {}".format(e)) + except Exception as e: + raise ToolProviderCredentialValidationError(str(e)) \ No newline at end of file diff --git a/api/core/tools/provider/builtin/gitlab/gitlab.yaml b/api/core/tools/provider/builtin/gitlab/gitlab.yaml new file mode 100644 index 0000000000..b5feea2382 --- /dev/null +++ b/api/core/tools/provider/builtin/gitlab/gitlab.yaml @@ -0,0 +1,38 @@ +identity: + author: Leo.Wang + name: gitlab + label: + en_US: Gitlab + zh_Hans: Gitlab + description: + en_US: Gitlab plugin for commit + zh_Hans: 用于获取Gitlab commit的插件 + icon: gitlab.svg +credentials_for_provider: + access_tokens: + type: secret-input + required: true + label: + en_US: Gitlab access token + zh_Hans: Gitlab access token + placeholder: + en_US: Please input your Gitlab access token + zh_Hans: 请输入你的 Gitlab access token + help: + en_US: Get your Gitlab access token from Gitlab + zh_Hans: 从 Gitlab 获取您的 access token + url: https://docs.gitlab.com/16.9/ee/api/oauth2.html + site_url: + type: text-input + required: false + default: 'https://gitlab.com' + label: + en_US: Gitlab site url + zh_Hans: Gitlab site url + placeholder: + en_US: Please input your Gitlab site url + zh_Hans: 请输入你的 Gitlab site url + help: + en_US: Find your Gitlab url + zh_Hans: 找到你的Gitlab url + url: https://gitlab.com/help diff --git a/api/core/tools/provider/builtin/gitlab/tools/gitlab_commits.py b/api/core/tools/provider/builtin/gitlab/tools/gitlab_commits.py new file mode 100644 index 0000000000..212bdb03ab --- /dev/null +++ b/api/core/tools/provider/builtin/gitlab/tools/gitlab_commits.py @@ -0,0 +1,101 @@ +import json +from datetime import datetime, timedelta +from typing import Any, Union + +import requests + +from core.tools.entities.tool_entities import ToolInvokeMessage +from core.tools.tool.builtin_tool import BuiltinTool + + +class GitlabCommitsTool(BuiltinTool): + def _invoke(self, + user_id: str, + tool_parameters: dict[str, Any] + ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]: + + project = tool_parameters.get('project', '') + employee = tool_parameters.get('employee', '') + start_time = tool_parameters.get('start_time', '') + end_time = tool_parameters.get('end_time', '') + + if not project: + return self.create_text_message('Project is required') + + if not start_time: + start_time = (datetime.utcnow() - timedelta(days=1)).isoformat() + if not end_time: + end_time = datetime.utcnow().isoformat() + + access_token = self.runtime.credentials.get('access_tokens') + site_url = self.runtime.credentials.get('site_url') + + if 'access_tokens' not in self.runtime.credentials or not self.runtime.credentials.get('access_tokens'): + return self.create_text_message("Gitlab API Access Tokens is required.") + if 'site_url' not in self.runtime.credentials or not self.runtime.credentials.get('site_url'): + site_url = 'https://gitlab.com' + + # Get commit content + result = self.fetch(user_id, site_url, access_token, project, employee, start_time, end_time) + + return self.create_text_message(json.dumps(result, ensure_ascii=False)) + + def fetch(self,user_id: str, site_url: str, access_token: str, project: str, employee: str = None, start_time: str = '', end_time: str = '') -> list[dict[str, Any]]: + domain = site_url + headers = {"PRIVATE-TOKEN": access_token} + results = [] + + try: + # Get all of projects + url = f"{domain}/api/v4/projects" + response = requests.get(url, headers=headers) + response.raise_for_status() + projects = response.json() + + filtered_projects = [p for p in projects if project == "*" or p['name'] == project] + + for project in filtered_projects: + project_id = project['id'] + project_name = project['name'] + print(f"Project: {project_name}") + + # Get all of proejct commits + commits_url = f"{domain}/api/v4/projects/{project_id}/repository/commits" + params = { + 'since': start_time, + 'until': end_time + } + if employee: + params['author'] = employee + + commits_response = requests.get(commits_url, headers=headers, params=params) + commits_response.raise_for_status() + commits = commits_response.json() + + for commit in commits: + commit_sha = commit['id'] + print(f"\tCommit SHA: {commit_sha}") + + diff_url = f"{domain}/api/v4/projects/{project_id}/repository/commits/{commit_sha}/diff" + diff_response = requests.get(diff_url, headers=headers) + diff_response.raise_for_status() + diffs = diff_response.json() + + for diff in diffs: + # Caculate code lines of changed + added_lines = diff['diff'].count('\n+') + removed_lines = diff['diff'].count('\n-') + total_changes = added_lines + removed_lines + + if total_changes > 1: + final_code = ''.join([line[1:] for line in diff['diff'].split('\n') if line.startswith('+') and not line.startswith('+++')]) + results.append({ + "project": project_name, + "commit_sha": commit_sha, + "diff": final_code + }) + print(f"Commit code:{final_code}") + except requests.RequestException as e: + print(f"Error fetching data from GitLab: {e}") + + return results \ No newline at end of file diff --git a/api/core/tools/provider/builtin/gitlab/tools/gitlab_commits.yaml b/api/core/tools/provider/builtin/gitlab/tools/gitlab_commits.yaml new file mode 100644 index 0000000000..fc4e7eb7bb --- /dev/null +++ b/api/core/tools/provider/builtin/gitlab/tools/gitlab_commits.yaml @@ -0,0 +1,56 @@ +identity: + name: gitlab_commits + author: Leo.Wang + label: + en_US: Gitlab Commits + zh_Hans: Gitlab代码提交内容 +description: + human: + en_US: A tool for query gitlab commits. Input should be a exists username. + zh_Hans: 一个用于查询gitlab代码提交记录的的工具，输入的内容应该是一个已存在的用户名或者项目名。 + llm: A tool for query gitlab commits. Input should be a exists username or project. +parameters: + - name: employee + type: string + required: false + label: + en_US: employee + zh_Hans: 员工用户名 + human_description: + en_US: employee + zh_Hans: 员工用户名 + llm_description: employee for gitlab + form: llm + - name: project + type: string + required: true + label: + en_US: project + zh_Hans: 项目名 + human_description: + en_US: project + zh_Hans: 项目名 + llm_description: project for gitlab + form: llm + - name: start_time + type: string + required: false + label: + en_US: start_time + zh_Hans: 开始时间 + human_description: + en_US: start_time + zh_Hans: 开始时间 + llm_description: start_time for gitlab + form: llm + - name: end_time + type: string + required: false + label: + en_US: end_time + zh_Hans: 结束时间 + human_description: + en_US: end_time + zh_Hans: 结束时间 + llm_description: end_time for gitlab + form: llm diff --git a/api/core/tools/tool/tool.py b/api/core/tools/tool/tool.py index 5d561911d1..d990131b5f 100644 --- a/api/core/tools/tool/tool.py +++ b/api/core/tools/tool/tool.py @@ -2,13 +2,12 @@ from abc import ABC, abstractmethod from collections.abc import Mapping from copy import deepcopy from enum import Enum -from typing import Any, Optional, Union +from typing import TYPE_CHECKING, Any, Optional, Union from pydantic import BaseModel, ConfigDict, field_validator from pydantic_core.core_schema import ValidationInfo from core.app.entities.app_invoke_entities import InvokeFrom -from core.file.file_obj import FileVar from core.tools.entities.tool_entities import ( ToolDescription, ToolIdentity, @@ -23,6 +22,9 @@ from core.tools.entities.tool_entities import ( from core.tools.tool_file_manager import ToolFileManager from core.tools.utils.tool_parameter_converter import ToolParameterConverter +if TYPE_CHECKING: + from core.file.file_obj import FileVar + class Tool(BaseModel, ABC): identity: Optional[ToolIdentity] = None @@ -76,7 +78,7 @@ class Tool(BaseModel, ABC): description=self.description.model_copy() if self.description else None, runtime=Tool.Runtime(**runtime), ) - + @abstractmethod def tool_provider_type(self) -> ToolProviderType: """ @@ -84,7 +86,7 @@ class Tool(BaseModel, ABC): :return: the tool provider type """ - + def load_variables(self, variables: ToolRuntimeVariablePool): """ load variables from database @@ -99,7 +101,7 @@ class Tool(BaseModel, ABC): """ if not self.variables: return - + self.variables.set_file(self.identity.name, variable_name, image_key) def set_text_variable(self, variable_name: str, text: str) -> None: @@ -108,9 +110,9 @@ class Tool(BaseModel, ABC): """ if not self.variables: return - + self.variables.set_text(self.identity.name, variable_name, text) - + def get_variable(self, name: Union[str, Enum]) -> Optional[ToolRuntimeVariable]: """ get a variable @@ -120,14 +122,14 @@ class Tool(BaseModel, ABC): """ if not self.variables: return None - + if isinstance(name, Enum): name = name.value - + for variable in self.variables.pool: if variable.name == name: return variable - + return None def get_default_image_variable(self) -> Optional[ToolRuntimeVariable]: @@ -138,9 +140,9 @@ class Tool(BaseModel, ABC): """ if not self.variables: return None - + return self.get_variable(self.VARIABLE_KEY.IMAGE) - + def get_variable_file(self, name: Union[str, Enum]) -> Optional[bytes]: """ get a variable file @@ -151,7 +153,7 @@ class Tool(BaseModel, ABC): variable = self.get_variable(name) if not variable: return None - + if not isinstance(variable, ToolRuntimeImageVariable): return None @@ -160,9 +162,9 @@ class Tool(BaseModel, ABC): file_binary = ToolFileManager.get_file_binary_by_message_file_id(message_file_id) if not file_binary: return None - + return file_binary[0] - + def list_variables(self) -> list[ToolRuntimeVariable]: """ list all variables @@ -171,9 +173,9 @@ class Tool(BaseModel, ABC): """ if not self.variables: return [] - + return self.variables.pool - + def list_default_image_variables(self) -> list[ToolRuntimeVariable]: """ list all image variables @@ -182,9 +184,9 @@ class Tool(BaseModel, ABC): """ if not self.variables: return [] - + result = [] - + for variable in self.variables.pool: if variable.name.startswith(self.VARIABLE_KEY.IMAGE.value): result.append(variable) @@ -225,7 +227,7 @@ class Tool(BaseModel, ABC): @abstractmethod def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]: pass - + def validate_credentials(self, credentials: dict[str, Any], parameters: dict[str, Any]) -> None: """ validate the credentials @@ -244,7 +246,7 @@ class Tool(BaseModel, ABC): :return: the runtime parameters """ return self.parameters or [] - + def get_all_runtime_parameters(self) -> list[ToolParameter]: """ get all runtime parameters @@ -278,7 +280,7 @@ class Tool(BaseModel, ABC): parameters.append(parameter) return parameters - + def create_image_message(self, image: str, save_as: str = '') -> ToolInvokeMessage: """ create an image message @@ -286,18 +288,18 @@ class Tool(BaseModel, ABC): :param image: the url of the image :return: the image message """ - return ToolInvokeMessage(type=ToolInvokeMessage.MessageType.IMAGE, - message=image, + return ToolInvokeMessage(type=ToolInvokeMessage.MessageType.IMAGE, + message=image, save_as=save_as) - - def create_file_var_message(self, file_var: FileVar) -> ToolInvokeMessage: + + def create_file_var_message(self, file_var: "FileVar") -> ToolInvokeMessage: return ToolInvokeMessage(type=ToolInvokeMessage.MessageType.FILE_VAR, message='', meta={ 'file_var': file_var }, save_as='') - + def create_link_message(self, link: str, save_as: str = '') -> ToolInvokeMessage: """ create a link message @@ -305,10 +307,10 @@ class Tool(BaseModel, ABC): :param link: the url of the link :return: the link message """ - return ToolInvokeMessage(type=ToolInvokeMessage.MessageType.LINK, - message=link, + return ToolInvokeMessage(type=ToolInvokeMessage.MessageType.LINK, + message=link, save_as=save_as) - + def create_text_message(self, text: str, save_as: str = '') -> ToolInvokeMessage: """ create a text message @@ -321,7 +323,7 @@ class Tool(BaseModel, ABC): message=text, save_as=save_as ) - + def create_blob_message(self, blob: bytes, meta: dict = None, save_as: str = '') -> ToolInvokeMessage: """ create a blob message diff --git a/api/core/tools/utils/message_transformer.py b/api/core/tools/utils/message_transformer.py index d5cf10da0c..23e7c0c243 100644 --- a/api/core/tools/utils/message_transformer.py +++ b/api/core/tools/utils/message_transformer.py @@ -1,7 +1,7 @@ import logging from mimetypes import guess_extension -from core.file.file_obj import FileTransferMethod, FileType, FileVar +from core.file.file_obj import FileTransferMethod, FileType from core.tools.entities.tool_entities import ToolInvokeMessage from core.tools.tool_file_manager import ToolFileManager @@ -28,12 +28,12 @@ class ToolFileMessageTransformer: # try to download image try: file = ToolFileManager.create_file_by_url( - user_id=user_id, + user_id=user_id, tenant_id=tenant_id, conversation_id=conversation_id, file_url=message.message ) - + url = f'/files/tools/{file.id}{guess_extension(file.mimetype) or ".png"}' result.append(ToolInvokeMessage( @@ -56,14 +56,14 @@ class ToolFileMessageTransformer: # if message is str, encode it to bytes if isinstance(message.message, str): message.message = message.message.encode('utf-8') - + file = ToolFileManager.create_file_by_raw( user_id=user_id, tenant_id=tenant_id, conversation_id=conversation_id, file_binary=message.message, mimetype=mimetype ) - + url = cls.get_tool_file_url(file.id, guess_extension(file.mimetype)) # check if file is image @@ -82,7 +82,7 @@ class ToolFileMessageTransformer: meta=message.meta.copy() if message.meta is not None else {}, )) elif message.type == ToolInvokeMessage.MessageType.FILE_VAR: - file_var: FileVar = message.meta.get('file_var') + file_var = message.meta.get('file_var') if file_var: if file_var.transfer_method == FileTransferMethod.TOOL_FILE: url = cls.get_tool_file_url(file_var.related_id, file_var.extension) @@ -104,7 +104,7 @@ class ToolFileMessageTransformer: result.append(message) return result - + @classmethod def get_tool_file_url(cls, tool_file_id: str, extension: str) -> str: - return f'/files/tools/{tool_file_id}{extension or ".bin"}' \ No newline at end of file + return f'/files/tools/{tool_file_id}{extension or ".bin"}' diff --git a/api/core/workflow/entities/node_entities.py b/api/core/workflow/entities/node_entities.py index 5e2258d624..94b8641d65 100644 --- a/api/core/workflow/entities/node_entities.py +++ b/api/core/workflow/entities/node_entities.py @@ -4,13 +4,14 @@ from typing import Any, Optional from pydantic import BaseModel from core.model_runtime.entities.llm_entities import LLMUsage -from models.workflow import WorkflowNodeExecutionStatus +from models import WorkflowNodeExecutionStatus class NodeType(Enum): """ Node Types. """ + START = 'start' END = 'end' ANSWER = 'answer' @@ -44,33 +45,11 @@ class NodeType(Enum): raise ValueError(f'invalid node type value {value}') -class SystemVariable(Enum): - """ - System Variables. - """ - QUERY = 'query' - FILES = 'files' - CONVERSATION_ID = 'conversation_id' - USER_ID = 'user_id' - - @classmethod - def value_of(cls, value: str) -> 'SystemVariable': - """ - Get value of given system variable. - - :param value: system variable value - :return: system variable - """ - for system_variable in cls: - if system_variable.value == value: - return system_variable - raise ValueError(f'invalid system variable value {value}') - - class NodeRunMetadataKey(Enum): """ Node Run Metadata Key. """ + TOTAL_TOKENS = 'total_tokens' TOTAL_PRICE = 'total_price' CURRENCY = 'currency' @@ -83,6 +62,7 @@ class NodeRunResult(BaseModel): """ Node Run Result. """ + status: WorkflowNodeExecutionStatus = WorkflowNodeExecutionStatus.RUNNING inputs: Optional[dict[str, Any]] = None # node inputs diff --git a/api/core/workflow/entities/variable_pool.py b/api/core/workflow/entities/variable_pool.py index 39165b4988..078ea2a7a8 100644 --- a/api/core/workflow/entities/variable_pool.py +++ b/api/core/workflow/entities/variable_pool.py @@ -7,7 +7,7 @@ from typing_extensions import deprecated from core.app.segments import Segment, Variable, factory from core.file.file_obj import FileVar -from core.workflow.entities.node_entities import SystemVariable +from core.workflow.enums import SystemVariable VariableValue = Union[str, int, float, dict, list, FileVar] diff --git a/api/core/workflow/enums.py b/api/core/workflow/enums.py new file mode 100644 index 0000000000..4757cf32f8 --- /dev/null +++ b/api/core/workflow/enums.py @@ -0,0 +1,25 @@ +from enum import Enum + + +class SystemVariable(str, Enum): + """ + System Variables. + """ + QUERY = 'query' + FILES = 'files' + CONVERSATION_ID = 'conversation_id' + USER_ID = 'user_id' + DIALOGUE_COUNT = 'dialogue_count' + + @classmethod + def value_of(cls, value: str): + """ + Get value of given system variable. + + :param value: system variable value + :return: system variable + """ + for system_variable in cls: + if system_variable.value == value: + return system_variable + raise ValueError(f'invalid system variable value {value}') diff --git a/api/core/workflow/nodes/http_request/http_request_node.py b/api/core/workflow/nodes/http_request/http_request_node.py index c69394a891..6db9c43555 100644 --- a/api/core/workflow/nodes/http_request/http_request_node.py +++ b/api/core/workflow/nodes/http_request/http_request_node.py @@ -140,9 +140,6 @@ class HttpRequestNode(BaseNode): """ files = [] mimetype, file_binary = response.extract_file() - # if not image, return directly - if 'image' not in mimetype: - return files if mimetype: # extract filename from url diff --git a/api/core/workflow/nodes/llm/llm_node.py b/api/core/workflow/nodes/llm/llm_node.py index b2f4f3ad4b..bdc6185cab 100644 --- a/api/core/workflow/nodes/llm/llm_node.py +++ b/api/core/workflow/nodes/llm/llm_node.py @@ -1,7 +1,7 @@ import json from collections.abc import Generator, Mapping, Sequence from copy import deepcopy -from typing import Any, Optional, cast +from typing import TYPE_CHECKING, Any, Optional, cast from pydantic import BaseModel @@ -9,7 +9,6 @@ from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEnti from core.entities.model_entities import ModelStatus from core.entities.provider_entities import QuotaUnit from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError -from core.file.file_obj import FileVar from core.memory.token_buffer_memory import TokenBufferMemory from core.model_manager import ModelInstance, ModelManager from core.model_runtime.entities.llm_entities import LLMResult, LLMUsage @@ -24,9 +23,10 @@ from core.model_runtime.utils.encoders import jsonable_encoder from core.prompt.advanced_prompt_transform import AdvancedPromptTransform from core.prompt.entities.advanced_prompt_entities import CompletionModelPromptTemplate, MemoryConfig from core.prompt.utils.prompt_message_util import PromptMessageUtil -from core.workflow.entities.node_entities import NodeRunMetadataKey, NodeRunResult, NodeType, SystemVariable +from core.workflow.entities.node_entities import NodeRunMetadataKey, NodeRunResult, NodeType from core.workflow.entities.variable_pool import VariablePool from core.workflow.graph_engine.entities.event import InNodeEvent +from core.workflow.enums import SystemVariable from core.workflow.nodes.base_node import BaseNode from core.workflow.nodes.event import RunCompletedEvent, RunEvent, RunRetrieverResourceEvent, RunStreamChunkEvent from core.workflow.nodes.llm.entities import ( @@ -41,6 +41,10 @@ from models.model import Conversation from models.provider import Provider, ProviderType from models.workflow import WorkflowNodeExecutionStatus +if TYPE_CHECKING: + from core.file.file_obj import FileVar + + class ModelInvokeCompleted(BaseModel): """ @@ -81,7 +85,7 @@ class LLMNode(BaseNode): node_inputs = {} # fetch files - files: list[FileVar] = self._fetch_files(node_data, variable_pool) + files = self._fetch_files(node_data, variable_pool) if files: node_inputs['#files#'] = [file.to_dict() for file in files] @@ -368,7 +372,7 @@ class LLMNode(BaseNode): return inputs # type: ignore - def _fetch_files(self, node_data: LLMNodeData, variable_pool: VariablePool) -> list[FileVar]: + def _fetch_files(self, node_data: LLMNodeData, variable_pool: VariablePool) -> list["FileVar"]: """ Fetch files :param node_data: node data @@ -563,7 +567,7 @@ class LLMNode(BaseNode): query: Optional[str], query_prompt_template: Optional[str], inputs: dict[str, str], - files: list[FileVar], + files: list["FileVar"], context: Optional[str], memory: Optional[TokenBufferMemory], model_config: ModelConfigWithCredentialsEntity) \ @@ -678,8 +682,8 @@ class LLMNode(BaseNode): @classmethod def _extract_variable_selector_to_variable_mapping( - cls, - graph_config: Mapping[str, Any], + cls, + graph_config: Mapping[str, Any], node_id: str, node_data: LLMNodeData ) -> Mapping[str, Sequence[str]]: diff --git a/api/core/workflow/nodes/tool/tool_node.py b/api/core/workflow/nodes/tool/tool_node.py index ebbf25c823..61f6f9bcee 100644 --- a/api/core/workflow/nodes/tool/tool_node.py +++ b/api/core/workflow/nodes/tool/tool_node.py @@ -2,19 +2,20 @@ from collections.abc import Mapping, Sequence from os import path from typing import Any, cast -from core.app.segments import parser +from core.app.segments import ArrayAnyVariable, parser from core.callback_handler.workflow_tool_callback_handler import DifyWorkflowCallbackHandler from core.file.file_obj import FileTransferMethod, FileType, FileVar from core.tools.entities.tool_entities import ToolInvokeMessage, ToolParameter from core.tools.tool_engine import ToolEngine from core.tools.tool_manager import ToolManager from core.tools.utils.message_transformer import ToolFileMessageTransformer -from core.workflow.entities.node_entities import NodeRunMetadataKey, NodeRunResult, NodeType, SystemVariable +from core.workflow.entities.node_entities import NodeRunMetadataKey, NodeRunResult, NodeType from core.workflow.entities.variable_pool import VariablePool +from core.workflow.enums import SystemVariable from core.workflow.nodes.base_node import BaseNode from core.workflow.nodes.tool.entities import ToolNodeData from core.workflow.utils.variable_template_parser import VariableTemplateParser -from models.workflow import WorkflowNodeExecutionStatus +from models import WorkflowNodeExecutionStatus class ToolNode(BaseNode): @@ -140,9 +141,9 @@ class ToolNode(BaseNode): return result def _fetch_files(self, variable_pool: VariablePool) -> list[FileVar]: - # FIXME: ensure this is a ArrayVariable contains FileVariable. variable = variable_pool.get(['sys', SystemVariable.FILES.value]) - return [file_var.value for file_var in variable.value] if variable else [] + assert isinstance(variable, ArrayAnyVariable) + return list(variable.value) if variable else [] def _convert_tool_messages(self, messages: list[ToolInvokeMessage])\ -> tuple[str, list[FileVar], list[dict]]: diff --git a/api/events/app_event.py b/api/events/app_event.py index 67a5982527..f2ce71bbbb 100644 --- a/api/events/app_event.py +++ b/api/events/app_event.py @@ -1,13 +1,13 @@ from blinker import signal # sender: app -app_was_created = signal('app-was-created') +app_was_created = signal("app-was-created") # sender: app, kwargs: app_model_config -app_model_config_was_updated = signal('app-model-config-was-updated') +app_model_config_was_updated = signal("app-model-config-was-updated") # sender: app, kwargs: published_workflow -app_published_workflow_was_updated = signal('app-published-workflow-was-updated') +app_published_workflow_was_updated = signal("app-published-workflow-was-updated") # sender: app, kwargs: synced_draft_workflow -app_draft_workflow_was_synced = signal('app-draft-workflow-was-synced') +app_draft_workflow_was_synced = signal("app-draft-workflow-was-synced") diff --git a/api/events/dataset_event.py b/api/events/dataset_event.py index d4a2b6f313..750b7424e2 100644 --- a/api/events/dataset_event.py +++ b/api/events/dataset_event.py @@ -1,4 +1,4 @@ from blinker import signal # sender: dataset -dataset_was_deleted = signal('dataset-was-deleted') +dataset_was_deleted = signal("dataset-was-deleted") diff --git a/api/events/document_event.py b/api/events/document_event.py index f95326630b..2c5a416a5e 100644 --- a/api/events/document_event.py +++ b/api/events/document_event.py @@ -1,4 +1,4 @@ from blinker import signal # sender: document -document_was_deleted = signal('document-was-deleted') +document_was_deleted = signal("document-was-deleted") diff --git a/api/events/event_handlers/clean_when_dataset_deleted.py b/api/events/event_handlers/clean_when_dataset_deleted.py index 42f1c70614..7caa2d1cc9 100644 --- a/api/events/event_handlers/clean_when_dataset_deleted.py +++ b/api/events/event_handlers/clean_when_dataset_deleted.py @@ -5,5 +5,11 @@ from tasks.clean_dataset_task import clean_dataset_task @dataset_was_deleted.connect def handle(sender, **kwargs): dataset = sender - clean_dataset_task.delay(dataset.id, dataset.tenant_id, dataset.indexing_technique, - dataset.index_struct, dataset.collection_binding_id, dataset.doc_form) + clean_dataset_task.delay( + dataset.id, + dataset.tenant_id, + dataset.indexing_technique, + dataset.index_struct, + dataset.collection_binding_id, + dataset.doc_form, + ) diff --git a/api/events/event_handlers/clean_when_document_deleted.py b/api/events/event_handlers/clean_when_document_deleted.py index 24022da15f..00a66f50ad 100644 --- a/api/events/event_handlers/clean_when_document_deleted.py +++ b/api/events/event_handlers/clean_when_document_deleted.py @@ -5,7 +5,7 @@ from tasks.clean_document_task import clean_document_task @document_was_deleted.connect def handle(sender, **kwargs): document_id = sender - dataset_id = kwargs.get('dataset_id') - doc_form = kwargs.get('doc_form') - file_id = kwargs.get('file_id') + dataset_id = kwargs.get("dataset_id") + doc_form = kwargs.get("doc_form") + file_id = kwargs.get("file_id") clean_document_task.delay(document_id, dataset_id, doc_form, file_id) diff --git a/api/events/event_handlers/create_document_index.py b/api/events/event_handlers/create_document_index.py index 68dae5a553..72a135e73d 100644 --- a/api/events/event_handlers/create_document_index.py +++ b/api/events/event_handlers/create_document_index.py @@ -14,21 +14,25 @@ from models.dataset import Document @document_index_created.connect def handle(sender, **kwargs): dataset_id = sender - document_ids = kwargs.get('document_ids', None) + document_ids = kwargs.get("document_ids", None) documents = [] start_at = time.perf_counter() for document_id in document_ids: - logging.info(click.style('Start process document: {}'.format(document_id), fg='green')) + logging.info(click.style("Start process document: {}".format(document_id), fg="green")) - document = db.session.query(Document).filter( - Document.id == document_id, - Document.dataset_id == dataset_id - ).first() + document = ( + db.session.query(Document) + .filter( + Document.id == document_id, + Document.dataset_id == dataset_id, + ) + .first() + ) if not document: - raise NotFound('Document not found') + raise NotFound("Document not found") - document.indexing_status = 'parsing' + document.indexing_status = "parsing" document.processing_started_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None) documents.append(document) db.session.add(document) @@ -38,8 +42,8 @@ def handle(sender, **kwargs): indexing_runner = IndexingRunner() indexing_runner.run(documents) end_at = time.perf_counter() - logging.info(click.style('Processed dataset: {} latency: {}'.format(dataset_id, end_at - start_at), fg='green')) + logging.info(click.style("Processed dataset: {} latency: {}".format(dataset_id, end_at - start_at), fg="green")) except DocumentIsPausedException as ex: - logging.info(click.style(str(ex), fg='yellow')) + logging.info(click.style(str(ex), fg="yellow")) except Exception: pass diff --git a/api/events/event_handlers/create_installed_app_when_app_created.py b/api/events/event_handlers/create_installed_app_when_app_created.py index 31084ce0fe..57412cc4ad 100644 --- a/api/events/event_handlers/create_installed_app_when_app_created.py +++ b/api/events/event_handlers/create_installed_app_when_app_created.py @@ -10,7 +10,7 @@ def handle(sender, **kwargs): installed_app = InstalledApp( tenant_id=app.tenant_id, app_id=app.id, - app_owner_tenant_id=app.tenant_id + app_owner_tenant_id=app.tenant_id, ) db.session.add(installed_app) db.session.commit() diff --git a/api/events/event_handlers/create_site_record_when_app_created.py b/api/events/event_handlers/create_site_record_when_app_created.py index f0eb7159b6..abaf0e41ec 100644 --- a/api/events/event_handlers/create_site_record_when_app_created.py +++ b/api/events/event_handlers/create_site_record_when_app_created.py @@ -7,15 +7,15 @@ from models.model import Site def handle(sender, **kwargs): """Create site record when an app is created.""" app = sender - account = kwargs.get('account') + account = kwargs.get("account") site = Site( app_id=app.id, title=app.name, - icon = app.icon, - icon_background = app.icon_background, + icon=app.icon, + icon_background=app.icon_background, default_language=account.interface_language, - customize_token_strategy='not_allow', - code=Site.generate_code(16) + customize_token_strategy="not_allow", + code=Site.generate_code(16), ) db.session.add(site) diff --git a/api/events/event_handlers/deduct_quota_when_messaeg_created.py b/api/events/event_handlers/deduct_quota_when_messaeg_created.py index 8cf52bf8f5..843a232096 100644 --- a/api/events/event_handlers/deduct_quota_when_messaeg_created.py +++ b/api/events/event_handlers/deduct_quota_when_messaeg_created.py @@ -8,7 +8,7 @@ from models.provider import Provider, ProviderType @message_was_created.connect def handle(sender, **kwargs): message = sender - application_generate_entity = kwargs.get('application_generate_entity') + application_generate_entity = kwargs.get("application_generate_entity") if not isinstance(application_generate_entity, ChatAppGenerateEntity | AgentChatAppGenerateEntity): return @@ -39,7 +39,7 @@ def handle(sender, **kwargs): elif quota_unit == QuotaUnit.CREDITS: used_quota = 1 - if 'gpt-4' in model_config.model: + if "gpt-4" in model_config.model: used_quota = 20 else: used_quota = 1 @@ -50,6 +50,6 @@ def handle(sender, **kwargs): Provider.provider_name == model_config.provider, Provider.provider_type == ProviderType.SYSTEM.value, Provider.quota_type == system_configuration.current_quota_type.value, - Provider.quota_limit > Provider.quota_used - ).update({'quota_used': Provider.quota_used + used_quota}) + Provider.quota_limit > Provider.quota_used, + ).update({"quota_used": Provider.quota_used + used_quota}) db.session.commit() diff --git a/api/events/event_handlers/delete_tool_parameters_cache_when_sync_draft_workflow.py b/api/events/event_handlers/delete_tool_parameters_cache_when_sync_draft_workflow.py index 1f6da34ee2..f96bb5ef74 100644 --- a/api/events/event_handlers/delete_tool_parameters_cache_when_sync_draft_workflow.py +++ b/api/events/event_handlers/delete_tool_parameters_cache_when_sync_draft_workflow.py @@ -8,8 +8,8 @@ from events.app_event import app_draft_workflow_was_synced @app_draft_workflow_was_synced.connect def handle(sender, **kwargs): app = sender - for node_data in kwargs.get('synced_draft_workflow').graph_dict.get('nodes', []): - if node_data.get('data', {}).get('type') == NodeType.TOOL.value: + for node_data in kwargs.get("synced_draft_workflow").graph_dict.get("nodes", []): + if node_data.get("data", {}).get("type") == NodeType.TOOL.value: try: tool_entity = ToolEntity(**node_data["data"]) tool_runtime = ToolManager.get_tool_runtime( @@ -23,7 +23,7 @@ def handle(sender, **kwargs): tool_runtime=tool_runtime, provider_name=tool_entity.provider_name, provider_type=tool_entity.provider_type, - identity_id=f'WORKFLOW.{app.id}.{node_data.get("id")}' + identity_id=f'WORKFLOW.{app.id}.{node_data.get("id")}', ) manager.delete_tool_parameters_cache() except: diff --git a/api/events/event_handlers/document_index_event.py b/api/events/event_handlers/document_index_event.py index 9c4e055deb..3d463fe5b3 100644 --- a/api/events/event_handlers/document_index_event.py +++ b/api/events/event_handlers/document_index_event.py @@ -1,4 +1,4 @@ from blinker import signal # sender: document -document_index_created = signal('document-index-created') +document_index_created = signal("document-index-created") diff --git a/api/events/event_handlers/update_app_dataset_join_when_app_model_config_updated.py b/api/events/event_handlers/update_app_dataset_join_when_app_model_config_updated.py index 2b202c53d0..59375b1a0b 100644 --- a/api/events/event_handlers/update_app_dataset_join_when_app_model_config_updated.py +++ b/api/events/event_handlers/update_app_dataset_join_when_app_model_config_updated.py @@ -7,13 +7,11 @@ from models.model import AppModelConfig @app_model_config_was_updated.connect def handle(sender, **kwargs): app = sender - app_model_config = kwargs.get('app_model_config') + app_model_config = kwargs.get("app_model_config") dataset_ids = get_dataset_ids_from_model_config(app_model_config) - app_dataset_joins = db.session.query(AppDatasetJoin).filter( - AppDatasetJoin.app_id == app.id - ).all() + app_dataset_joins = db.session.query(AppDatasetJoin).filter(AppDatasetJoin.app_id == app.id).all() removed_dataset_ids = [] if not app_dataset_joins: @@ -29,16 +27,12 @@ def handle(sender, **kwargs): if removed_dataset_ids: for dataset_id in removed_dataset_ids: db.session.query(AppDatasetJoin).filter( - AppDatasetJoin.app_id == app.id, - AppDatasetJoin.dataset_id == dataset_id + AppDatasetJoin.app_id == app.id, AppDatasetJoin.dataset_id == dataset_id ).delete() if added_dataset_ids: for dataset_id in added_dataset_ids: - app_dataset_join = AppDatasetJoin( - app_id=app.id, - dataset_id=dataset_id - ) + app_dataset_join = AppDatasetJoin(app_id=app.id, dataset_id=dataset_id) db.session.add(app_dataset_join) db.session.commit() @@ -51,7 +45,7 @@ def get_dataset_ids_from_model_config(app_model_config: AppModelConfig) -> set: agent_mode = app_model_config.agent_mode_dict - tools = agent_mode.get('tools', []) or [] + tools = agent_mode.get("tools", []) or [] for tool in tools: if len(list(tool.keys())) != 1: continue @@ -63,11 +57,11 @@ def get_dataset_ids_from_model_config(app_model_config: AppModelConfig) -> set: # get dataset from dataset_configs dataset_configs = app_model_config.dataset_configs_dict - datasets = dataset_configs.get('datasets', {}) or {} - for dataset in datasets.get('datasets', []) or []: + datasets = dataset_configs.get("datasets", {}) or {} + for dataset in datasets.get("datasets", []) or []: keys = list(dataset.keys()) - if len(keys) == 1 and keys[0] == 'dataset': - if dataset['dataset'].get('id'): - dataset_ids.add(dataset['dataset'].get('id')) + if len(keys) == 1 and keys[0] == "dataset": + if dataset["dataset"].get("id"): + dataset_ids.add(dataset["dataset"].get("id")) return dataset_ids diff --git a/api/events/event_handlers/update_app_dataset_join_when_app_published_workflow_updated.py b/api/events/event_handlers/update_app_dataset_join_when_app_published_workflow_updated.py index 996b1e9691..333b85ecb2 100644 --- a/api/events/event_handlers/update_app_dataset_join_when_app_published_workflow_updated.py +++ b/api/events/event_handlers/update_app_dataset_join_when_app_published_workflow_updated.py @@ -11,13 +11,11 @@ from models.workflow import Workflow @app_published_workflow_was_updated.connect def handle(sender, **kwargs): app = sender - published_workflow = kwargs.get('published_workflow') + published_workflow = kwargs.get("published_workflow") published_workflow = cast(Workflow, published_workflow) dataset_ids = get_dataset_ids_from_workflow(published_workflow) - app_dataset_joins = db.session.query(AppDatasetJoin).filter( - AppDatasetJoin.app_id == app.id - ).all() + app_dataset_joins = db.session.query(AppDatasetJoin).filter(AppDatasetJoin.app_id == app.id).all() removed_dataset_ids = [] if not app_dataset_joins: @@ -33,16 +31,12 @@ def handle(sender, **kwargs): if removed_dataset_ids: for dataset_id in removed_dataset_ids: db.session.query(AppDatasetJoin).filter( - AppDatasetJoin.app_id == app.id, - AppDatasetJoin.dataset_id == dataset_id + AppDatasetJoin.app_id == app.id, AppDatasetJoin.dataset_id == dataset_id ).delete() if added_dataset_ids: for dataset_id in added_dataset_ids: - app_dataset_join = AppDatasetJoin( - app_id=app.id, - dataset_id=dataset_id - ) + app_dataset_join = AppDatasetJoin(app_id=app.id, dataset_id=dataset_id) db.session.add(app_dataset_join) db.session.commit() @@ -54,18 +48,19 @@ def get_dataset_ids_from_workflow(published_workflow: Workflow) -> set: if not graph: return dataset_ids - nodes = graph.get('nodes', []) + nodes = graph.get("nodes", []) # fetch all knowledge retrieval nodes - knowledge_retrieval_nodes = [node for node in nodes - if node.get('data', {}).get('type') == NodeType.KNOWLEDGE_RETRIEVAL.value] + knowledge_retrieval_nodes = [ + node for node in nodes if node.get("data", {}).get("type") == NodeType.KNOWLEDGE_RETRIEVAL.value + ] if not knowledge_retrieval_nodes: return dataset_ids for node in knowledge_retrieval_nodes: try: - node_data = KnowledgeRetrievalNodeData(**node.get('data', {})) + node_data = KnowledgeRetrievalNodeData(**node.get("data", {})) dataset_ids.update(node_data.dataset_ids) except Exception as e: continue diff --git a/api/events/event_handlers/update_provider_last_used_at_when_messaeg_created.py b/api/events/event_handlers/update_provider_last_used_at_when_messaeg_created.py index 6188f1a085..a80572c0de 100644 --- a/api/events/event_handlers/update_provider_last_used_at_when_messaeg_created.py +++ b/api/events/event_handlers/update_provider_last_used_at_when_messaeg_created.py @@ -9,13 +9,13 @@ from models.provider import Provider @message_was_created.connect def handle(sender, **kwargs): message = sender - application_generate_entity = kwargs.get('application_generate_entity') + application_generate_entity = kwargs.get("application_generate_entity") if not isinstance(application_generate_entity, ChatAppGenerateEntity | AgentChatAppGenerateEntity): return db.session.query(Provider).filter( Provider.tenant_id == application_generate_entity.app_config.tenant_id, - Provider.provider_name == application_generate_entity.model_conf.provider - ).update({'last_used': datetime.now(timezone.utc).replace(tzinfo=None)}) + Provider.provider_name == application_generate_entity.model_conf.provider, + ).update({"last_used": datetime.now(timezone.utc).replace(tzinfo=None)}) db.session.commit() diff --git a/api/events/message_event.py b/api/events/message_event.py index 21da83f249..6576c35c45 100644 --- a/api/events/message_event.py +++ b/api/events/message_event.py @@ -1,4 +1,4 @@ from blinker import signal # sender: message, kwargs: conversation -message_was_created = signal('message-was-created') +message_was_created = signal("message-was-created") diff --git a/api/events/tenant_event.py b/api/events/tenant_event.py index 942f709917..d99feaac40 100644 --- a/api/events/tenant_event.py +++ b/api/events/tenant_event.py @@ -1,7 +1,7 @@ from blinker import signal # sender: tenant -tenant_was_created = signal('tenant-was-created') +tenant_was_created = signal("tenant-was-created") # sender: tenant -tenant_was_updated = signal('tenant-was-updated') +tenant_was_updated = signal("tenant-was-updated") diff --git a/api/extensions/ext_celery.py b/api/extensions/ext_celery.py index ae9a075340..f5ec7c1759 100644 --- a/api/extensions/ext_celery.py +++ b/api/extensions/ext_celery.py @@ -17,7 +17,7 @@ def init_app(app: Flask) -> Celery: backend=app.config["CELERY_BACKEND"], task_ignore_result=True, ) - + # Add SSL options to the Celery configuration ssl_options = { "ssl_cert_reqs": None, @@ -35,7 +35,7 @@ def init_app(app: Flask) -> Celery: celery_app.conf.update( broker_use_ssl=ssl_options, # Add the SSL options to the broker configuration ) - + celery_app.set_default() app.extensions["celery"] = celery_app @@ -45,18 +45,15 @@ def init_app(app: Flask) -> Celery: ] day = app.config["CELERY_BEAT_SCHEDULER_TIME"] beat_schedule = { - 'clean_embedding_cache_task': { - 'task': 'schedule.clean_embedding_cache_task.clean_embedding_cache_task', - 'schedule': timedelta(days=day), + "clean_embedding_cache_task": { + "task": "schedule.clean_embedding_cache_task.clean_embedding_cache_task", + "schedule": timedelta(days=day), + }, + "clean_unused_datasets_task": { + "task": "schedule.clean_unused_datasets_task.clean_unused_datasets_task", + "schedule": timedelta(days=day), }, - 'clean_unused_datasets_task': { - 'task': 'schedule.clean_unused_datasets_task.clean_unused_datasets_task', - 'schedule': timedelta(days=day), - } } - celery_app.conf.update( - beat_schedule=beat_schedule, - imports=imports - ) + celery_app.conf.update(beat_schedule=beat_schedule, imports=imports) return celery_app diff --git a/api/extensions/ext_compress.py b/api/extensions/ext_compress.py index 1dbaffcfb0..38e67749fc 100644 --- a/api/extensions/ext_compress.py +++ b/api/extensions/ext_compress.py @@ -2,15 +2,14 @@ from flask import Flask def init_app(app: Flask): - if app.config.get('API_COMPRESSION_ENABLED'): + if app.config.get("API_COMPRESSION_ENABLED"): from flask_compress import Compress - app.config['COMPRESS_MIMETYPES'] = [ - 'application/json', - 'image/svg+xml', - 'text/html', + app.config["COMPRESS_MIMETYPES"] = [ + "application/json", + "image/svg+xml", + "text/html", ] compress = Compress() compress.init_app(app) - diff --git a/api/extensions/ext_database.py b/api/extensions/ext_database.py index c248e173a2..f6ffa53634 100644 --- a/api/extensions/ext_database.py +++ b/api/extensions/ext_database.py @@ -2,11 +2,11 @@ from flask_sqlalchemy import SQLAlchemy from sqlalchemy import MetaData POSTGRES_INDEXES_NAMING_CONVENTION = { - 'ix': '%(column_0_label)s_idx', - 'uq': '%(table_name)s_%(column_0_name)s_key', - 'ck': '%(table_name)s_%(constraint_name)s_check', - 'fk': '%(table_name)s_%(column_0_name)s_fkey', - 'pk': '%(table_name)s_pkey', + "ix": "%(column_0_label)s_idx", + "uq": "%(table_name)s_%(column_0_name)s_key", + "ck": "%(table_name)s_%(constraint_name)s_check", + "fk": "%(table_name)s_%(column_0_name)s_fkey", + "pk": "%(table_name)s_pkey", } metadata = MetaData(naming_convention=POSTGRES_INDEXES_NAMING_CONVENTION) diff --git a/api/extensions/ext_mail.py b/api/extensions/ext_mail.py index ec3a5cc112..b435294abc 100644 --- a/api/extensions/ext_mail.py +++ b/api/extensions/ext_mail.py @@ -14,67 +14,69 @@ class Mail: return self._client is not None def init_app(self, app: Flask): - if app.config.get('MAIL_TYPE'): - if app.config.get('MAIL_DEFAULT_SEND_FROM'): - self._default_send_from = app.config.get('MAIL_DEFAULT_SEND_FROM') - - if app.config.get('MAIL_TYPE') == 'resend': - api_key = app.config.get('RESEND_API_KEY') - if not api_key: - raise ValueError('RESEND_API_KEY is not set') + if app.config.get("MAIL_TYPE"): + if app.config.get("MAIL_DEFAULT_SEND_FROM"): + self._default_send_from = app.config.get("MAIL_DEFAULT_SEND_FROM") - api_url = app.config.get('RESEND_API_URL') + if app.config.get("MAIL_TYPE") == "resend": + api_key = app.config.get("RESEND_API_KEY") + if not api_key: + raise ValueError("RESEND_API_KEY is not set") + + api_url = app.config.get("RESEND_API_URL") if api_url: resend.api_url = api_url resend.api_key = api_key self._client = resend.Emails - elif app.config.get('MAIL_TYPE') == 'smtp': + elif app.config.get("MAIL_TYPE") == "smtp": from libs.smtp import SMTPClient - if not app.config.get('SMTP_SERVER') or not app.config.get('SMTP_PORT'): - raise ValueError('SMTP_SERVER and SMTP_PORT are required for smtp mail type') - if not app.config.get('SMTP_USE_TLS') and app.config.get('SMTP_OPPORTUNISTIC_TLS'): - raise ValueError('SMTP_OPPORTUNISTIC_TLS is not supported without enabling SMTP_USE_TLS') + + if not app.config.get("SMTP_SERVER") or not app.config.get("SMTP_PORT"): + raise ValueError("SMTP_SERVER and SMTP_PORT are required for smtp mail type") + if not app.config.get("SMTP_USE_TLS") and app.config.get("SMTP_OPPORTUNISTIC_TLS"): + raise ValueError("SMTP_OPPORTUNISTIC_TLS is not supported without enabling SMTP_USE_TLS") self._client = SMTPClient( - server=app.config.get('SMTP_SERVER'), - port=app.config.get('SMTP_PORT'), - username=app.config.get('SMTP_USERNAME'), - password=app.config.get('SMTP_PASSWORD'), - _from=app.config.get('MAIL_DEFAULT_SEND_FROM'), - use_tls=app.config.get('SMTP_USE_TLS'), - opportunistic_tls=app.config.get('SMTP_OPPORTUNISTIC_TLS') + server=app.config.get("SMTP_SERVER"), + port=app.config.get("SMTP_PORT"), + username=app.config.get("SMTP_USERNAME"), + password=app.config.get("SMTP_PASSWORD"), + _from=app.config.get("MAIL_DEFAULT_SEND_FROM"), + use_tls=app.config.get("SMTP_USE_TLS"), + opportunistic_tls=app.config.get("SMTP_OPPORTUNISTIC_TLS"), ) else: - raise ValueError('Unsupported mail type {}'.format(app.config.get('MAIL_TYPE'))) + raise ValueError("Unsupported mail type {}".format(app.config.get("MAIL_TYPE"))) else: - logging.warning('MAIL_TYPE is not set') - + logging.warning("MAIL_TYPE is not set") def send(self, to: str, subject: str, html: str, from_: Optional[str] = None): if not self._client: - raise ValueError('Mail client is not initialized') + raise ValueError("Mail client is not initialized") if not from_ and self._default_send_from: from_ = self._default_send_from if not from_: - raise ValueError('mail from is not set') + raise ValueError("mail from is not set") if not to: - raise ValueError('mail to is not set') + raise ValueError("mail to is not set") if not subject: - raise ValueError('mail subject is not set') + raise ValueError("mail subject is not set") if not html: - raise ValueError('mail html is not set') + raise ValueError("mail html is not set") - self._client.send({ - "from": from_, - "to": to, - "subject": subject, - "html": html - }) + self._client.send( + { + "from": from_, + "to": to, + "subject": subject, + "html": html, + } + ) def init_app(app: Flask): diff --git a/api/extensions/ext_redis.py b/api/extensions/ext_redis.py index 23d7768d4d..d5fb162fd8 100644 --- a/api/extensions/ext_redis.py +++ b/api/extensions/ext_redis.py @@ -6,18 +6,21 @@ redis_client = redis.Redis() def init_app(app): connection_class = Connection - if app.config.get('REDIS_USE_SSL'): + if app.config.get("REDIS_USE_SSL"): connection_class = SSLConnection - redis_client.connection_pool = redis.ConnectionPool(**{ - 'host': app.config.get('REDIS_HOST'), - 'port': app.config.get('REDIS_PORT'), - 'username': app.config.get('REDIS_USERNAME'), - 'password': app.config.get('REDIS_PASSWORD'), - 'db': app.config.get('REDIS_DB'), - 'encoding': 'utf-8', - 'encoding_errors': 'strict', - 'decode_responses': False - }, connection_class=connection_class) + redis_client.connection_pool = redis.ConnectionPool( + **{ + "host": app.config.get("REDIS_HOST"), + "port": app.config.get("REDIS_PORT"), + "username": app.config.get("REDIS_USERNAME"), + "password": app.config.get("REDIS_PASSWORD"), + "db": app.config.get("REDIS_DB"), + "encoding": "utf-8", + "encoding_errors": "strict", + "decode_responses": False, + }, + connection_class=connection_class, + ) - app.extensions['redis'] = redis_client + app.extensions["redis"] = redis_client diff --git a/api/extensions/ext_sentry.py b/api/extensions/ext_sentry.py index f05c10bc08..227c6635f0 100644 --- a/api/extensions/ext_sentry.py +++ b/api/extensions/ext_sentry.py @@ -5,16 +5,13 @@ from werkzeug.exceptions import HTTPException def init_app(app): - if app.config.get('SENTRY_DSN'): + if app.config.get("SENTRY_DSN"): sentry_sdk.init( - dsn=app.config.get('SENTRY_DSN'), - integrations=[ - FlaskIntegration(), - CeleryIntegration() - ], + dsn=app.config.get("SENTRY_DSN"), + integrations=[FlaskIntegration(), CeleryIntegration()], ignore_errors=[HTTPException, ValueError], - traces_sample_rate=app.config.get('SENTRY_TRACES_SAMPLE_RATE', 1.0), - profiles_sample_rate=app.config.get('SENTRY_PROFILES_SAMPLE_RATE', 1.0), - environment=app.config.get('DEPLOY_ENV'), - release=f"dify-{app.config.get('CURRENT_VERSION')}-{app.config.get('COMMIT_SHA')}" + traces_sample_rate=app.config.get("SENTRY_TRACES_SAMPLE_RATE", 1.0), + profiles_sample_rate=app.config.get("SENTRY_PROFILES_SAMPLE_RATE", 1.0), + environment=app.config.get("DEPLOY_ENV"), + release=f"dify-{app.config.get('CURRENT_VERSION')}-{app.config.get('COMMIT_SHA')}", ) diff --git a/api/extensions/ext_storage.py b/api/extensions/ext_storage.py index 38db1c6ce1..e6c4352577 100644 --- a/api/extensions/ext_storage.py +++ b/api/extensions/ext_storage.py @@ -17,31 +17,19 @@ class Storage: self.storage_runner = None def init_app(self, app: Flask): - storage_type = app.config.get('STORAGE_TYPE') - if storage_type == 's3': - self.storage_runner = S3Storage( - app=app - ) - elif storage_type == 'azure-blob': - self.storage_runner = AzureStorage( - app=app - ) - elif storage_type == 'aliyun-oss': - self.storage_runner = AliyunStorage( - app=app - ) - elif storage_type == 'google-storage': - self.storage_runner = GoogleStorage( - app=app - ) - elif storage_type == 'tencent-cos': - self.storage_runner = TencentStorage( - app=app - ) - elif storage_type == 'oci-storage': - self.storage_runner = OCIStorage( - app=app - ) + storage_type = app.config.get("STORAGE_TYPE") + if storage_type == "s3": + self.storage_runner = S3Storage(app=app) + elif storage_type == "azure-blob": + self.storage_runner = AzureStorage(app=app) + elif storage_type == "aliyun-oss": + self.storage_runner = AliyunStorage(app=app) + elif storage_type == "google-storage": + self.storage_runner = GoogleStorage(app=app) + elif storage_type == "tencent-cos": + self.storage_runner = TencentStorage(app=app) + elif storage_type == "oci-storage": + self.storage_runner = OCIStorage(app=app) else: self.storage_runner = LocalStorage(app=app) diff --git a/api/extensions/storage/aliyun_storage.py b/api/extensions/storage/aliyun_storage.py index b81a8691f1..b962cedc55 100644 --- a/api/extensions/storage/aliyun_storage.py +++ b/api/extensions/storage/aliyun_storage.py @@ -8,23 +8,22 @@ from extensions.storage.base_storage import BaseStorage class AliyunStorage(BaseStorage): - """Implementation for aliyun storage. - """ + """Implementation for aliyun storage.""" def __init__(self, app: Flask): super().__init__(app) app_config = self.app.config - self.bucket_name = app_config.get('ALIYUN_OSS_BUCKET_NAME') + self.bucket_name = app_config.get("ALIYUN_OSS_BUCKET_NAME") oss_auth_method = aliyun_s3.Auth region = None - if app_config.get('ALIYUN_OSS_AUTH_VERSION') == 'v4': + if app_config.get("ALIYUN_OSS_AUTH_VERSION") == "v4": oss_auth_method = aliyun_s3.AuthV4 - region = app_config.get('ALIYUN_OSS_REGION') - oss_auth = oss_auth_method(app_config.get('ALIYUN_OSS_ACCESS_KEY'), app_config.get('ALIYUN_OSS_SECRET_KEY')) + region = app_config.get("ALIYUN_OSS_REGION") + oss_auth = oss_auth_method(app_config.get("ALIYUN_OSS_ACCESS_KEY"), app_config.get("ALIYUN_OSS_SECRET_KEY")) self.client = aliyun_s3.Bucket( oss_auth, - app_config.get('ALIYUN_OSS_ENDPOINT'), + app_config.get("ALIYUN_OSS_ENDPOINT"), self.bucket_name, connect_timeout=30, region=region, diff --git a/api/extensions/storage/azure_storage.py b/api/extensions/storage/azure_storage.py index af3e7ef849..ca8cbb9188 100644 --- a/api/extensions/storage/azure_storage.py +++ b/api/extensions/storage/azure_storage.py @@ -9,16 +9,15 @@ from extensions.storage.base_storage import BaseStorage class AzureStorage(BaseStorage): - """Implementation for azure storage. - """ + """Implementation for azure storage.""" def __init__(self, app: Flask): super().__init__(app) app_config = self.app.config - self.bucket_name = app_config.get('AZURE_BLOB_CONTAINER_NAME') - self.account_url = app_config.get('AZURE_BLOB_ACCOUNT_URL') - self.account_name = app_config.get('AZURE_BLOB_ACCOUNT_NAME') - self.account_key = app_config.get('AZURE_BLOB_ACCOUNT_KEY') + self.bucket_name = app_config.get("AZURE_BLOB_CONTAINER_NAME") + self.account_url = app_config.get("AZURE_BLOB_ACCOUNT_URL") + self.account_name = app_config.get("AZURE_BLOB_ACCOUNT_NAME") + self.account_key = app_config.get("AZURE_BLOB_ACCOUNT_KEY") def save(self, filename, data): client = self._sync_client() @@ -39,6 +38,7 @@ class AzureStorage(BaseStorage): blob = client.get_blob_client(container=self.bucket_name, blob=filename) blob_data = blob.download_blob() yield from blob_data.chunks() + return generate(filename) def download(self, filename, target_filepath): @@ -62,17 +62,17 @@ class AzureStorage(BaseStorage): blob_container.delete_blob(filename) def _sync_client(self): - cache_key = 'azure_blob_sas_token_{}_{}'.format(self.account_name, self.account_key) + cache_key = "azure_blob_sas_token_{}_{}".format(self.account_name, self.account_key) cache_result = redis_client.get(cache_key) if cache_result is not None: - sas_token = cache_result.decode('utf-8') + sas_token = cache_result.decode("utf-8") else: sas_token = generate_account_sas( account_name=self.account_name, account_key=self.account_key, resource_types=ResourceTypes(service=True, container=True, object=True), permission=AccountSasPermissions(read=True, write=True, delete=True, list=True, add=True, create=True), - expiry=datetime.now(timezone.utc).replace(tzinfo=None) + timedelta(hours=1) + expiry=datetime.now(timezone.utc).replace(tzinfo=None) + timedelta(hours=1), ) redis_client.set(cache_key, sas_token, ex=3000) return BlobServiceClient(account_url=self.account_url, credential=sas_token) diff --git a/api/extensions/storage/base_storage.py b/api/extensions/storage/base_storage.py index 13d9c34290..c3fe9ec82a 100644 --- a/api/extensions/storage/base_storage.py +++ b/api/extensions/storage/base_storage.py @@ -1,4 +1,5 @@ """Abstract interface for file storage implementations.""" + from abc import ABC, abstractmethod from collections.abc import Generator @@ -6,8 +7,8 @@ from flask import Flask class BaseStorage(ABC): - """Interface for file storage. - """ + """Interface for file storage.""" + app = None def __init__(self, app: Flask): diff --git a/api/extensions/storage/google_storage.py b/api/extensions/storage/google_storage.py index ef6cd69039..9ed1fcf0b4 100644 --- a/api/extensions/storage/google_storage.py +++ b/api/extensions/storage/google_storage.py @@ -11,16 +11,16 @@ from extensions.storage.base_storage import BaseStorage class GoogleStorage(BaseStorage): - """Implementation for google storage. - """ + """Implementation for google storage.""" + def __init__(self, app: Flask): super().__init__(app) app_config = self.app.config - self.bucket_name = app_config.get('GOOGLE_STORAGE_BUCKET_NAME') - service_account_json_str = app_config.get('GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64') + self.bucket_name = app_config.get("GOOGLE_STORAGE_BUCKET_NAME") + service_account_json_str = app_config.get("GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64") # if service_account_json_str is empty, use Application Default Credentials if service_account_json_str: - service_account_json = base64.b64decode(service_account_json_str).decode('utf-8') + service_account_json = base64.b64decode(service_account_json_str).decode("utf-8") # convert str to object service_account_obj = json.loads(service_account_json) self.client = GoogleCloudStorage.Client.from_service_account_info(service_account_obj) @@ -43,9 +43,10 @@ class GoogleStorage(BaseStorage): def generate(filename: str = filename) -> Generator: bucket = self.client.get_bucket(self.bucket_name) blob = bucket.get_blob(filename) - with closing(blob.open(mode='rb')) as blob_stream: + with closing(blob.open(mode="rb")) as blob_stream: while chunk := blob_stream.read(4096): yield chunk + return generate() def download(self, filename, target_filepath): @@ -60,4 +61,4 @@ class GoogleStorage(BaseStorage): def delete(self, filename): bucket = self.client.get_bucket(self.bucket_name) - bucket.delete_blob(filename) \ No newline at end of file + bucket.delete_blob(filename) diff --git a/api/extensions/storage/local_storage.py b/api/extensions/storage/local_storage.py index 389ef12f82..46ee4bf80f 100644 --- a/api/extensions/storage/local_storage.py +++ b/api/extensions/storage/local_storage.py @@ -8,21 +8,20 @@ from extensions.storage.base_storage import BaseStorage class LocalStorage(BaseStorage): - """Implementation for local storage. - """ + """Implementation for local storage.""" def __init__(self, app: Flask): super().__init__(app) - folder = self.app.config.get('STORAGE_LOCAL_PATH') + folder = self.app.config.get("STORAGE_LOCAL_PATH") if not os.path.isabs(folder): folder = os.path.join(app.root_path, folder) self.folder = folder def save(self, filename, data): - if not self.folder or self.folder.endswith('/'): + if not self.folder or self.folder.endswith("/"): filename = self.folder + filename else: - filename = self.folder + '/' + filename + filename = self.folder + "/" + filename folder = os.path.dirname(filename) os.makedirs(folder, exist_ok=True) @@ -31,10 +30,10 @@ class LocalStorage(BaseStorage): f.write(data) def load_once(self, filename: str) -> bytes: - if not self.folder or self.folder.endswith('/'): + if not self.folder or self.folder.endswith("/"): filename = self.folder + filename else: - filename = self.folder + '/' + filename + filename = self.folder + "/" + filename if not os.path.exists(filename): raise FileNotFoundError("File not found") @@ -46,10 +45,10 @@ class LocalStorage(BaseStorage): def load_stream(self, filename: str) -> Generator: def generate(filename: str = filename) -> Generator: - if not self.folder or self.folder.endswith('/'): + if not self.folder or self.folder.endswith("/"): filename = self.folder + filename else: - filename = self.folder + '/' + filename + filename = self.folder + "/" + filename if not os.path.exists(filename): raise FileNotFoundError("File not found") @@ -61,10 +60,10 @@ class LocalStorage(BaseStorage): return generate() def download(self, filename, target_filepath): - if not self.folder or self.folder.endswith('/'): + if not self.folder or self.folder.endswith("/"): filename = self.folder + filename else: - filename = self.folder + '/' + filename + filename = self.folder + "/" + filename if not os.path.exists(filename): raise FileNotFoundError("File not found") @@ -72,17 +71,17 @@ class LocalStorage(BaseStorage): shutil.copyfile(filename, target_filepath) def exists(self, filename): - if not self.folder or self.folder.endswith('/'): + if not self.folder or self.folder.endswith("/"): filename = self.folder + filename else: - filename = self.folder + '/' + filename + filename = self.folder + "/" + filename return os.path.exists(filename) def delete(self, filename): - if not self.folder or self.folder.endswith('/'): + if not self.folder or self.folder.endswith("/"): filename = self.folder + filename else: - filename = self.folder + '/' + filename + filename = self.folder + "/" + filename if os.path.exists(filename): os.remove(filename) diff --git a/api/extensions/storage/oci_storage.py b/api/extensions/storage/oci_storage.py index e78d870950..e32fa0a0ae 100644 --- a/api/extensions/storage/oci_storage.py +++ b/api/extensions/storage/oci_storage.py @@ -12,14 +12,14 @@ class OCIStorage(BaseStorage): def __init__(self, app: Flask): super().__init__(app) app_config = self.app.config - self.bucket_name = app_config.get('OCI_BUCKET_NAME') + self.bucket_name = app_config.get("OCI_BUCKET_NAME") self.client = boto3.client( - 's3', - aws_secret_access_key=app_config.get('OCI_SECRET_KEY'), - aws_access_key_id=app_config.get('OCI_ACCESS_KEY'), - endpoint_url=app_config.get('OCI_ENDPOINT'), - region_name=app_config.get('OCI_REGION') - ) + "s3", + aws_secret_access_key=app_config.get("OCI_SECRET_KEY"), + aws_access_key_id=app_config.get("OCI_ACCESS_KEY"), + endpoint_url=app_config.get("OCI_ENDPOINT"), + region_name=app_config.get("OCI_REGION"), + ) def save(self, filename, data): self.client.put_object(Bucket=self.bucket_name, Key=filename, Body=data) @@ -27,9 +27,9 @@ class OCIStorage(BaseStorage): def load_once(self, filename: str) -> bytes: try: with closing(self.client) as client: - data = client.get_object(Bucket=self.bucket_name, Key=filename)['Body'].read() + data = client.get_object(Bucket=self.bucket_name, Key=filename)["Body"].read() except ClientError as ex: - if ex.response['Error']['Code'] == 'NoSuchKey': + if ex.response["Error"]["Code"] == "NoSuchKey": raise FileNotFoundError("File not found") else: raise @@ -40,12 +40,13 @@ class OCIStorage(BaseStorage): try: with closing(self.client) as client: response = client.get_object(Bucket=self.bucket_name, Key=filename) - yield from response['Body'].iter_chunks() + yield from response["Body"].iter_chunks() except ClientError as ex: - if ex.response['Error']['Code'] == 'NoSuchKey': + if ex.response["Error"]["Code"] == "NoSuchKey": raise FileNotFoundError("File not found") else: raise + return generate() def download(self, filename, target_filepath): @@ -61,4 +62,4 @@ class OCIStorage(BaseStorage): return False def delete(self, filename): - self.client.delete_object(Bucket=self.bucket_name, Key=filename) \ No newline at end of file + self.client.delete_object(Bucket=self.bucket_name, Key=filename) diff --git a/api/extensions/storage/s3_storage.py b/api/extensions/storage/s3_storage.py index 787596fa79..022ce5b14a 100644 --- a/api/extensions/storage/s3_storage.py +++ b/api/extensions/storage/s3_storage.py @@ -10,24 +10,24 @@ from extensions.storage.base_storage import BaseStorage class S3Storage(BaseStorage): - """Implementation for s3 storage. - """ + """Implementation for s3 storage.""" + def __init__(self, app: Flask): super().__init__(app) app_config = self.app.config - self.bucket_name = app_config.get('S3_BUCKET_NAME') - if app_config.get('S3_USE_AWS_MANAGED_IAM'): + self.bucket_name = app_config.get("S3_BUCKET_NAME") + if app_config.get("S3_USE_AWS_MANAGED_IAM"): session = boto3.Session() - self.client = session.client('s3') + self.client = session.client("s3") else: self.client = boto3.client( - 's3', - aws_secret_access_key=app_config.get('S3_SECRET_KEY'), - aws_access_key_id=app_config.get('S3_ACCESS_KEY'), - endpoint_url=app_config.get('S3_ENDPOINT'), - region_name=app_config.get('S3_REGION'), - config=Config(s3={'addressing_style': app_config.get('S3_ADDRESS_STYLE')}) - ) + "s3", + aws_secret_access_key=app_config.get("S3_SECRET_KEY"), + aws_access_key_id=app_config.get("S3_ACCESS_KEY"), + endpoint_url=app_config.get("S3_ENDPOINT"), + region_name=app_config.get("S3_REGION"), + config=Config(s3={"addressing_style": app_config.get("S3_ADDRESS_STYLE")}), + ) def save(self, filename, data): self.client.put_object(Bucket=self.bucket_name, Key=filename, Body=data) @@ -35,9 +35,9 @@ class S3Storage(BaseStorage): def load_once(self, filename: str) -> bytes: try: with closing(self.client) as client: - data = client.get_object(Bucket=self.bucket_name, Key=filename)['Body'].read() + data = client.get_object(Bucket=self.bucket_name, Key=filename)["Body"].read() except ClientError as ex: - if ex.response['Error']['Code'] == 'NoSuchKey': + if ex.response["Error"]["Code"] == "NoSuchKey": raise FileNotFoundError("File not found") else: raise @@ -48,12 +48,13 @@ class S3Storage(BaseStorage): try: with closing(self.client) as client: response = client.get_object(Bucket=self.bucket_name, Key=filename) - yield from response['Body'].iter_chunks() + yield from response["Body"].iter_chunks() except ClientError as ex: - if ex.response['Error']['Code'] == 'NoSuchKey': + if ex.response["Error"]["Code"] == "NoSuchKey": raise FileNotFoundError("File not found") else: raise + return generate() def download(self, filename, target_filepath): diff --git a/api/extensions/storage/tencent_storage.py b/api/extensions/storage/tencent_storage.py index e2c1ca55e3..1d499cd3bc 100644 --- a/api/extensions/storage/tencent_storage.py +++ b/api/extensions/storage/tencent_storage.py @@ -7,18 +7,17 @@ from extensions.storage.base_storage import BaseStorage class TencentStorage(BaseStorage): - """Implementation for tencent cos storage. - """ + """Implementation for tencent cos storage.""" def __init__(self, app: Flask): super().__init__(app) app_config = self.app.config - self.bucket_name = app_config.get('TENCENT_COS_BUCKET_NAME') + self.bucket_name = app_config.get("TENCENT_COS_BUCKET_NAME") config = CosConfig( - Region=app_config.get('TENCENT_COS_REGION'), - SecretId=app_config.get('TENCENT_COS_SECRET_ID'), - SecretKey=app_config.get('TENCENT_COS_SECRET_KEY'), - Scheme=app_config.get('TENCENT_COS_SCHEME'), + Region=app_config.get("TENCENT_COS_REGION"), + SecretId=app_config.get("TENCENT_COS_SECRET_ID"), + SecretKey=app_config.get("TENCENT_COS_SECRET_KEY"), + Scheme=app_config.get("TENCENT_COS_SCHEME"), ) self.client = CosS3Client(config) @@ -26,19 +25,19 @@ class TencentStorage(BaseStorage): self.client.put_object(Bucket=self.bucket_name, Body=data, Key=filename) def load_once(self, filename: str) -> bytes: - data = self.client.get_object(Bucket=self.bucket_name, Key=filename)['Body'].get_raw_stream().read() + data = self.client.get_object(Bucket=self.bucket_name, Key=filename)["Body"].get_raw_stream().read() return data def load_stream(self, filename: str) -> Generator: def generate(filename: str = filename) -> Generator: response = self.client.get_object(Bucket=self.bucket_name, Key=filename) - yield from response['Body'].get_stream(chunk_size=4096) + yield from response["Body"].get_stream(chunk_size=4096) return generate() def download(self, filename, target_filepath): response = self.client.get_object(Bucket=self.bucket_name, Key=filename) - response['Body'].get_stream_to_file(target_filepath) + response["Body"].get_stream_to_file(target_filepath) def exists(self, filename): return self.client.object_exists(Bucket=self.bucket_name, Key=filename) diff --git a/api/fields/annotation_fields.py b/api/fields/annotation_fields.py index c778084475..379dcc6d16 100644 --- a/api/fields/annotation_fields.py +++ b/api/fields/annotation_fields.py @@ -5,7 +5,7 @@ from libs.helper import TimestampField annotation_fields = { "id": fields.String, "question": fields.String, - "answer": fields.Raw(attribute='content'), + "answer": fields.Raw(attribute="content"), "hit_count": fields.Integer, "created_at": TimestampField, # 'account': fields.Nested(simple_account_fields, allow_null=True) @@ -21,8 +21,8 @@ annotation_hit_history_fields = { "score": fields.Float, "question": fields.String, "created_at": TimestampField, - "match": fields.String(attribute='annotation_question'), - "response": fields.String(attribute='annotation_content') + "match": fields.String(attribute="annotation_question"), + "response": fields.String(attribute="annotation_content"), } annotation_hit_history_list_fields = { diff --git a/api/fields/api_based_extension_fields.py b/api/fields/api_based_extension_fields.py index 749e9900de..a85d4a34db 100644 --- a/api/fields/api_based_extension_fields.py +++ b/api/fields/api_based_extension_fields.py @@ -8,16 +8,16 @@ class HiddenAPIKey(fields.Raw): api_key = obj.api_key # If the length of the api_key is less than 8 characters, show the first and last characters if len(api_key) <= 8: - return api_key[0] + '******' + api_key[-1] + return api_key[0] + "******" + api_key[-1] # If the api_key is greater than 8 characters, show the first three and the last three characters else: - return api_key[:3] + '******' + api_key[-3:] + return api_key[:3] + "******" + api_key[-3:] api_based_extension_fields = { - 'id': fields.String, - 'name': fields.String, - 'api_endpoint': fields.String, - 'api_key': HiddenAPIKey, - 'created_at': TimestampField + "id": fields.String, + "name": fields.String, + "api_endpoint": fields.String, + "api_key": HiddenAPIKey, + "created_at": TimestampField, } diff --git a/api/fields/app_fields.py b/api/fields/app_fields.py index 94d804a919..7036d58e4a 100644 --- a/api/fields/app_fields.py +++ b/api/fields/app_fields.py @@ -3,157 +3,153 @@ from flask_restful import fields from libs.helper import TimestampField app_detail_kernel_fields = { - 'id': fields.String, - 'name': fields.String, - 'description': fields.String, - 'mode': fields.String(attribute='mode_compatible_with_agent'), - 'icon': fields.String, - 'icon_background': fields.String, + "id": fields.String, + "name": fields.String, + "description": fields.String, + "mode": fields.String(attribute="mode_compatible_with_agent"), + "icon": fields.String, + "icon_background": fields.String, } related_app_list = { - 'data': fields.List(fields.Nested(app_detail_kernel_fields)), - 'total': fields.Integer, + "data": fields.List(fields.Nested(app_detail_kernel_fields)), + "total": fields.Integer, } model_config_fields = { - 'opening_statement': fields.String, - 'suggested_questions': fields.Raw(attribute='suggested_questions_list'), - 'suggested_questions_after_answer': fields.Raw(attribute='suggested_questions_after_answer_dict'), - 'speech_to_text': fields.Raw(attribute='speech_to_text_dict'), - 'text_to_speech': fields.Raw(attribute='text_to_speech_dict'), - 'retriever_resource': fields.Raw(attribute='retriever_resource_dict'), - 'annotation_reply': fields.Raw(attribute='annotation_reply_dict'), - 'more_like_this': fields.Raw(attribute='more_like_this_dict'), - 'sensitive_word_avoidance': fields.Raw(attribute='sensitive_word_avoidance_dict'), - 'external_data_tools': fields.Raw(attribute='external_data_tools_list'), - 'model': fields.Raw(attribute='model_dict'), - 'user_input_form': fields.Raw(attribute='user_input_form_list'), - 'dataset_query_variable': fields.String, - 'pre_prompt': fields.String, - 'agent_mode': fields.Raw(attribute='agent_mode_dict'), - 'prompt_type': fields.String, - 'chat_prompt_config': fields.Raw(attribute='chat_prompt_config_dict'), - 'completion_prompt_config': fields.Raw(attribute='completion_prompt_config_dict'), - 'dataset_configs': fields.Raw(attribute='dataset_configs_dict'), - 'file_upload': fields.Raw(attribute='file_upload_dict'), - 'created_at': TimestampField + "opening_statement": fields.String, + "suggested_questions": fields.Raw(attribute="suggested_questions_list"), + "suggested_questions_after_answer": fields.Raw(attribute="suggested_questions_after_answer_dict"), + "speech_to_text": fields.Raw(attribute="speech_to_text_dict"), + "text_to_speech": fields.Raw(attribute="text_to_speech_dict"), + "retriever_resource": fields.Raw(attribute="retriever_resource_dict"), + "annotation_reply": fields.Raw(attribute="annotation_reply_dict"), + "more_like_this": fields.Raw(attribute="more_like_this_dict"), + "sensitive_word_avoidance": fields.Raw(attribute="sensitive_word_avoidance_dict"), + "external_data_tools": fields.Raw(attribute="external_data_tools_list"), + "model": fields.Raw(attribute="model_dict"), + "user_input_form": fields.Raw(attribute="user_input_form_list"), + "dataset_query_variable": fields.String, + "pre_prompt": fields.String, + "agent_mode": fields.Raw(attribute="agent_mode_dict"), + "prompt_type": fields.String, + "chat_prompt_config": fields.Raw(attribute="chat_prompt_config_dict"), + "completion_prompt_config": fields.Raw(attribute="completion_prompt_config_dict"), + "dataset_configs": fields.Raw(attribute="dataset_configs_dict"), + "file_upload": fields.Raw(attribute="file_upload_dict"), + "created_at": TimestampField, } app_detail_fields = { - 'id': fields.String, - 'name': fields.String, - 'description': fields.String, - 'mode': fields.String(attribute='mode_compatible_with_agent'), - 'icon': fields.String, - 'icon_background': fields.String, - 'enable_site': fields.Boolean, - 'enable_api': fields.Boolean, - 'model_config': fields.Nested(model_config_fields, attribute='app_model_config', allow_null=True), - 'tracing': fields.Raw, - 'created_at': TimestampField + "id": fields.String, + "name": fields.String, + "description": fields.String, + "mode": fields.String(attribute="mode_compatible_with_agent"), + "icon": fields.String, + "icon_background": fields.String, + "enable_site": fields.Boolean, + "enable_api": fields.Boolean, + "model_config": fields.Nested(model_config_fields, attribute="app_model_config", allow_null=True), + "tracing": fields.Raw, + "created_at": TimestampField, } prompt_config_fields = { - 'prompt_template': fields.String, + "prompt_template": fields.String, } model_config_partial_fields = { - 'model': fields.Raw(attribute='model_dict'), - 'pre_prompt': fields.String, + "model": fields.Raw(attribute="model_dict"), + "pre_prompt": fields.String, } -tag_fields = { - 'id': fields.String, - 'name': fields.String, - 'type': fields.String -} +tag_fields = {"id": fields.String, "name": fields.String, "type": fields.String} app_partial_fields = { - 'id': fields.String, - 'name': fields.String, - 'max_active_requests': fields.Raw(), - 'description': fields.String(attribute='desc_or_prompt'), - 'mode': fields.String(attribute='mode_compatible_with_agent'), - 'icon': fields.String, - 'icon_background': fields.String, - 'model_config': fields.Nested(model_config_partial_fields, attribute='app_model_config', allow_null=True), - 'created_at': TimestampField, - 'tags': fields.List(fields.Nested(tag_fields)) + "id": fields.String, + "name": fields.String, + "max_active_requests": fields.Raw(), + "description": fields.String(attribute="desc_or_prompt"), + "mode": fields.String(attribute="mode_compatible_with_agent"), + "icon": fields.String, + "icon_background": fields.String, + "model_config": fields.Nested(model_config_partial_fields, attribute="app_model_config", allow_null=True), + "created_at": TimestampField, + "tags": fields.List(fields.Nested(tag_fields)), } app_pagination_fields = { - 'page': fields.Integer, - 'limit': fields.Integer(attribute='per_page'), - 'total': fields.Integer, - 'has_more': fields.Boolean(attribute='has_next'), - 'data': fields.List(fields.Nested(app_partial_fields), attribute='items') + "page": fields.Integer, + "limit": fields.Integer(attribute="per_page"), + "total": fields.Integer, + "has_more": fields.Boolean(attribute="has_next"), + "data": fields.List(fields.Nested(app_partial_fields), attribute="items"), } template_fields = { - 'name': fields.String, - 'icon': fields.String, - 'icon_background': fields.String, - 'description': fields.String, - 'mode': fields.String, - 'model_config': fields.Nested(model_config_fields), + "name": fields.String, + "icon": fields.String, + "icon_background": fields.String, + "description": fields.String, + "mode": fields.String, + "model_config": fields.Nested(model_config_fields), } template_list_fields = { - 'data': fields.List(fields.Nested(template_fields)), + "data": fields.List(fields.Nested(template_fields)), } site_fields = { - 'access_token': fields.String(attribute='code'), - 'code': fields.String, - 'title': fields.String, - 'icon': fields.String, - 'icon_background': fields.String, - 'description': fields.String, - 'default_language': fields.String, - 'chat_color_theme': fields.String, - 'chat_color_theme_inverted': fields.Boolean, - 'customize_domain': fields.String, - 'copyright': fields.String, - 'privacy_policy': fields.String, - 'custom_disclaimer': fields.String, - 'customize_token_strategy': fields.String, - 'prompt_public': fields.Boolean, - 'app_base_url': fields.String, - 'show_workflow_steps': fields.Boolean, + "access_token": fields.String(attribute="code"), + "code": fields.String, + "title": fields.String, + "icon": fields.String, + "icon_background": fields.String, + "description": fields.String, + "default_language": fields.String, + "chat_color_theme": fields.String, + "chat_color_theme_inverted": fields.Boolean, + "customize_domain": fields.String, + "copyright": fields.String, + "privacy_policy": fields.String, + "custom_disclaimer": fields.String, + "customize_token_strategy": fields.String, + "prompt_public": fields.Boolean, + "app_base_url": fields.String, + "show_workflow_steps": fields.Boolean, } app_detail_fields_with_site = { - 'id': fields.String, - 'name': fields.String, - 'description': fields.String, - 'mode': fields.String(attribute='mode_compatible_with_agent'), - 'icon': fields.String, - 'icon_background': fields.String, - 'enable_site': fields.Boolean, - 'enable_api': fields.Boolean, - 'model_config': fields.Nested(model_config_fields, attribute='app_model_config', allow_null=True), - 'site': fields.Nested(site_fields), - 'api_base_url': fields.String, - 'created_at': TimestampField, - 'deleted_tools': fields.List(fields.String), + "id": fields.String, + "name": fields.String, + "description": fields.String, + "mode": fields.String(attribute="mode_compatible_with_agent"), + "icon": fields.String, + "icon_background": fields.String, + "enable_site": fields.Boolean, + "enable_api": fields.Boolean, + "model_config": fields.Nested(model_config_fields, attribute="app_model_config", allow_null=True), + "site": fields.Nested(site_fields), + "api_base_url": fields.String, + "created_at": TimestampField, + "deleted_tools": fields.List(fields.String), } app_site_fields = { - 'app_id': fields.String, - 'access_token': fields.String(attribute='code'), - 'code': fields.String, - 'title': fields.String, - 'icon': fields.String, - 'icon_background': fields.String, - 'description': fields.String, - 'default_language': fields.String, - 'customize_domain': fields.String, - 'copyright': fields.String, - 'privacy_policy': fields.String, - 'custom_disclaimer': fields.String, - 'customize_token_strategy': fields.String, - 'prompt_public': fields.Boolean, - 'show_workflow_steps': fields.Boolean, + "app_id": fields.String, + "access_token": fields.String(attribute="code"), + "code": fields.String, + "title": fields.String, + "icon": fields.String, + "icon_background": fields.String, + "description": fields.String, + "default_language": fields.String, + "customize_domain": fields.String, + "copyright": fields.String, + "privacy_policy": fields.String, + "custom_disclaimer": fields.String, + "customize_token_strategy": fields.String, + "prompt_public": fields.Boolean, + "show_workflow_steps": fields.Boolean, } diff --git a/api/fields/conversation_fields.py b/api/fields/conversation_fields.py index 79ceb02685..1b15fe3880 100644 --- a/api/fields/conversation_fields.py +++ b/api/fields/conversation_fields.py @@ -6,205 +6,202 @@ from libs.helper import TimestampField class MessageTextField(fields.Raw): def format(self, value): - return value[0]['text'] if value else '' + return value[0]["text"] if value else "" feedback_fields = { - 'rating': fields.String, - 'content': fields.String, - 'from_source': fields.String, - 'from_end_user_id': fields.String, - 'from_account': fields.Nested(simple_account_fields, allow_null=True), + "rating": fields.String, + "content": fields.String, + "from_source": fields.String, + "from_end_user_id": fields.String, + "from_account": fields.Nested(simple_account_fields, allow_null=True), } annotation_fields = { - 'id': fields.String, - 'question': fields.String, - 'content': fields.String, - 'account': fields.Nested(simple_account_fields, allow_null=True), - 'created_at': TimestampField + "id": fields.String, + "question": fields.String, + "content": fields.String, + "account": fields.Nested(simple_account_fields, allow_null=True), + "created_at": TimestampField, } annotation_hit_history_fields = { - 'annotation_id': fields.String(attribute='id'), - 'annotation_create_account': fields.Nested(simple_account_fields, allow_null=True), - 'created_at': TimestampField + "annotation_id": fields.String(attribute="id"), + "annotation_create_account": fields.Nested(simple_account_fields, allow_null=True), + "created_at": TimestampField, } message_file_fields = { - 'id': fields.String, - 'type': fields.String, - 'url': fields.String, - 'belongs_to': fields.String(default='user'), + "id": fields.String, + "type": fields.String, + "url": fields.String, + "belongs_to": fields.String(default="user"), } agent_thought_fields = { - 'id': fields.String, - 'chain_id': fields.String, - 'message_id': fields.String, - 'position': fields.Integer, - 'thought': fields.String, - 'tool': fields.String, - 'tool_labels': fields.Raw, - 'tool_input': fields.String, - 'created_at': TimestampField, - 'observation': fields.String, - 'files': fields.List(fields.String), + "id": fields.String, + "chain_id": fields.String, + "message_id": fields.String, + "position": fields.Integer, + "thought": fields.String, + "tool": fields.String, + "tool_labels": fields.Raw, + "tool_input": fields.String, + "created_at": TimestampField, + "observation": fields.String, + "files": fields.List(fields.String), } message_detail_fields = { - 'id': fields.String, - 'conversation_id': fields.String, - 'inputs': fields.Raw, - 'query': fields.String, - 'message': fields.Raw, - 'message_tokens': fields.Integer, - 'answer': fields.String(attribute='re_sign_file_url_answer'), - 'answer_tokens': fields.Integer, - 'provider_response_latency': fields.Float, - 'from_source': fields.String, - 'from_end_user_id': fields.String, - 'from_account_id': fields.String, - 'feedbacks': fields.List(fields.Nested(feedback_fields)), - 'workflow_run_id': fields.String, - 'annotation': fields.Nested(annotation_fields, allow_null=True), - 'annotation_hit_history': fields.Nested(annotation_hit_history_fields, allow_null=True), - 'created_at': TimestampField, - 'agent_thoughts': fields.List(fields.Nested(agent_thought_fields)), - 'message_files': fields.List(fields.Nested(message_file_fields), attribute='files'), - 'metadata': fields.Raw(attribute='message_metadata_dict'), - 'status': fields.String, - 'error': fields.String, + "id": fields.String, + "conversation_id": fields.String, + "inputs": fields.Raw, + "query": fields.String, + "message": fields.Raw, + "message_tokens": fields.Integer, + "answer": fields.String(attribute="re_sign_file_url_answer"), + "answer_tokens": fields.Integer, + "provider_response_latency": fields.Float, + "from_source": fields.String, + "from_end_user_id": fields.String, + "from_account_id": fields.String, + "feedbacks": fields.List(fields.Nested(feedback_fields)), + "workflow_run_id": fields.String, + "annotation": fields.Nested(annotation_fields, allow_null=True), + "annotation_hit_history": fields.Nested(annotation_hit_history_fields, allow_null=True), + "created_at": TimestampField, + "agent_thoughts": fields.List(fields.Nested(agent_thought_fields)), + "message_files": fields.List(fields.Nested(message_file_fields), attribute="files"), + "metadata": fields.Raw(attribute="message_metadata_dict"), + "status": fields.String, + "error": fields.String, } -feedback_stat_fields = { - 'like': fields.Integer, - 'dislike': fields.Integer -} +feedback_stat_fields = {"like": fields.Integer, "dislike": fields.Integer} model_config_fields = { - 'opening_statement': fields.String, - 'suggested_questions': fields.Raw, - 'model': fields.Raw, - 'user_input_form': fields.Raw, - 'pre_prompt': fields.String, - 'agent_mode': fields.Raw, + "opening_statement": fields.String, + "suggested_questions": fields.Raw, + "model": fields.Raw, + "user_input_form": fields.Raw, + "pre_prompt": fields.String, + "agent_mode": fields.Raw, } simple_configs_fields = { - 'prompt_template': fields.String, + "prompt_template": fields.String, } simple_model_config_fields = { - 'model': fields.Raw(attribute='model_dict'), - 'pre_prompt': fields.String, + "model": fields.Raw(attribute="model_dict"), + "pre_prompt": fields.String, } simple_message_detail_fields = { - 'inputs': fields.Raw, - 'query': fields.String, - 'message': MessageTextField, - 'answer': fields.String, + "inputs": fields.Raw, + "query": fields.String, + "message": MessageTextField, + "answer": fields.String, } conversation_fields = { - 'id': fields.String, - 'status': fields.String, - 'from_source': fields.String, - 'from_end_user_id': fields.String, - 'from_end_user_session_id': fields.String(), - 'from_account_id': fields.String, - 'read_at': TimestampField, - 'created_at': TimestampField, - 'annotation': fields.Nested(annotation_fields, allow_null=True), - 'model_config': fields.Nested(simple_model_config_fields), - 'user_feedback_stats': fields.Nested(feedback_stat_fields), - 'admin_feedback_stats': fields.Nested(feedback_stat_fields), - 'message': fields.Nested(simple_message_detail_fields, attribute='first_message') + "id": fields.String, + "status": fields.String, + "from_source": fields.String, + "from_end_user_id": fields.String, + "from_end_user_session_id": fields.String(), + "from_account_id": fields.String, + "read_at": TimestampField, + "created_at": TimestampField, + "annotation": fields.Nested(annotation_fields, allow_null=True), + "model_config": fields.Nested(simple_model_config_fields), + "user_feedback_stats": fields.Nested(feedback_stat_fields), + "admin_feedback_stats": fields.Nested(feedback_stat_fields), + "message": fields.Nested(simple_message_detail_fields, attribute="first_message"), } conversation_pagination_fields = { - 'page': fields.Integer, - 'limit': fields.Integer(attribute='per_page'), - 'total': fields.Integer, - 'has_more': fields.Boolean(attribute='has_next'), - 'data': fields.List(fields.Nested(conversation_fields), attribute='items') + "page": fields.Integer, + "limit": fields.Integer(attribute="per_page"), + "total": fields.Integer, + "has_more": fields.Boolean(attribute="has_next"), + "data": fields.List(fields.Nested(conversation_fields), attribute="items"), } conversation_message_detail_fields = { - 'id': fields.String, - 'status': fields.String, - 'from_source': fields.String, - 'from_end_user_id': fields.String, - 'from_account_id': fields.String, - 'created_at': TimestampField, - 'model_config': fields.Nested(model_config_fields), - 'message': fields.Nested(message_detail_fields, attribute='first_message'), + "id": fields.String, + "status": fields.String, + "from_source": fields.String, + "from_end_user_id": fields.String, + "from_account_id": fields.String, + "created_at": TimestampField, + "model_config": fields.Nested(model_config_fields), + "message": fields.Nested(message_detail_fields, attribute="first_message"), } conversation_with_summary_fields = { - 'id': fields.String, - 'status': fields.String, - 'from_source': fields.String, - 'from_end_user_id': fields.String, - 'from_end_user_session_id': fields.String, - 'from_account_id': fields.String, - 'name': fields.String, - 'summary': fields.String(attribute='summary_or_query'), - 'read_at': TimestampField, - 'created_at': TimestampField, - 'annotated': fields.Boolean, - 'model_config': fields.Nested(simple_model_config_fields), - 'message_count': fields.Integer, - 'user_feedback_stats': fields.Nested(feedback_stat_fields), - 'admin_feedback_stats': fields.Nested(feedback_stat_fields) + "id": fields.String, + "status": fields.String, + "from_source": fields.String, + "from_end_user_id": fields.String, + "from_end_user_session_id": fields.String, + "from_account_id": fields.String, + "name": fields.String, + "summary": fields.String(attribute="summary_or_query"), + "read_at": TimestampField, + "created_at": TimestampField, + "annotated": fields.Boolean, + "model_config": fields.Nested(simple_model_config_fields), + "message_count": fields.Integer, + "user_feedback_stats": fields.Nested(feedback_stat_fields), + "admin_feedback_stats": fields.Nested(feedback_stat_fields), } conversation_with_summary_pagination_fields = { - 'page': fields.Integer, - 'limit': fields.Integer(attribute='per_page'), - 'total': fields.Integer, - 'has_more': fields.Boolean(attribute='has_next'), - 'data': fields.List(fields.Nested(conversation_with_summary_fields), attribute='items') + "page": fields.Integer, + "limit": fields.Integer(attribute="per_page"), + "total": fields.Integer, + "has_more": fields.Boolean(attribute="has_next"), + "data": fields.List(fields.Nested(conversation_with_summary_fields), attribute="items"), } conversation_detail_fields = { - 'id': fields.String, - 'status': fields.String, - 'from_source': fields.String, - 'from_end_user_id': fields.String, - 'from_account_id': fields.String, - 'created_at': TimestampField, - 'annotated': fields.Boolean, - 'introduction': fields.String, - 'model_config': fields.Nested(model_config_fields), - 'message_count': fields.Integer, - 'user_feedback_stats': fields.Nested(feedback_stat_fields), - 'admin_feedback_stats': fields.Nested(feedback_stat_fields) + "id": fields.String, + "status": fields.String, + "from_source": fields.String, + "from_end_user_id": fields.String, + "from_account_id": fields.String, + "created_at": TimestampField, + "annotated": fields.Boolean, + "introduction": fields.String, + "model_config": fields.Nested(model_config_fields), + "message_count": fields.Integer, + "user_feedback_stats": fields.Nested(feedback_stat_fields), + "admin_feedback_stats": fields.Nested(feedback_stat_fields), } simple_conversation_fields = { - 'id': fields.String, - 'name': fields.String, - 'inputs': fields.Raw, - 'status': fields.String, - 'introduction': fields.String, - 'created_at': TimestampField + "id": fields.String, + "name": fields.String, + "inputs": fields.Raw, + "status": fields.String, + "introduction": fields.String, + "created_at": TimestampField, } conversation_infinite_scroll_pagination_fields = { - 'limit': fields.Integer, - 'has_more': fields.Boolean, - 'data': fields.List(fields.Nested(simple_conversation_fields)) + "limit": fields.Integer, + "has_more": fields.Boolean, + "data": fields.List(fields.Nested(simple_conversation_fields)), } conversation_with_model_config_fields = { **simple_conversation_fields, - 'model_config': fields.Raw, + "model_config": fields.Raw, } conversation_with_model_config_infinite_scroll_pagination_fields = { - 'limit': fields.Integer, - 'has_more': fields.Boolean, - 'data': fields.List(fields.Nested(conversation_with_model_config_fields)) + "limit": fields.Integer, + "has_more": fields.Boolean, + "data": fields.List(fields.Nested(conversation_with_model_config_fields)), } diff --git a/api/fields/conversation_variable_fields.py b/api/fields/conversation_variable_fields.py index 782a848c1a..983e50e73c 100644 --- a/api/fields/conversation_variable_fields.py +++ b/api/fields/conversation_variable_fields.py @@ -3,19 +3,19 @@ from flask_restful import fields from libs.helper import TimestampField conversation_variable_fields = { - 'id': fields.String, - 'name': fields.String, - 'value_type': fields.String(attribute='value_type.value'), - 'value': fields.String, - 'description': fields.String, - 'created_at': TimestampField, - 'updated_at': TimestampField, + "id": fields.String, + "name": fields.String, + "value_type": fields.String(attribute="value_type.value"), + "value": fields.String, + "description": fields.String, + "created_at": TimestampField, + "updated_at": TimestampField, } paginated_conversation_variable_fields = { - 'page': fields.Integer, - 'limit': fields.Integer, - 'total': fields.Integer, - 'has_more': fields.Boolean, - 'data': fields.List(fields.Nested(conversation_variable_fields), attribute='data'), + "page": fields.Integer, + "limit": fields.Integer, + "total": fields.Integer, + "has_more": fields.Boolean, + "data": fields.List(fields.Nested(conversation_variable_fields), attribute="data"), } diff --git a/api/fields/data_source_fields.py b/api/fields/data_source_fields.py index 6f3c920c85..071071376f 100644 --- a/api/fields/data_source_fields.py +++ b/api/fields/data_source_fields.py @@ -2,64 +2,56 @@ from flask_restful import fields from libs.helper import TimestampField -integrate_icon_fields = { - 'type': fields.String, - 'url': fields.String, - 'emoji': fields.String -} +integrate_icon_fields = {"type": fields.String, "url": fields.String, "emoji": fields.String} integrate_page_fields = { - 'page_name': fields.String, - 'page_id': fields.String, - 'page_icon': fields.Nested(integrate_icon_fields, allow_null=True), - 'is_bound': fields.Boolean, - 'parent_id': fields.String, - 'type': fields.String + "page_name": fields.String, + "page_id": fields.String, + "page_icon": fields.Nested(integrate_icon_fields, allow_null=True), + "is_bound": fields.Boolean, + "parent_id": fields.String, + "type": fields.String, } integrate_workspace_fields = { - 'workspace_name': fields.String, - 'workspace_id': fields.String, - 'workspace_icon': fields.String, - 'pages': fields.List(fields.Nested(integrate_page_fields)) + "workspace_name": fields.String, + "workspace_id": fields.String, + "workspace_icon": fields.String, + "pages": fields.List(fields.Nested(integrate_page_fields)), } integrate_notion_info_list_fields = { - 'notion_info': fields.List(fields.Nested(integrate_workspace_fields)), + "notion_info": fields.List(fields.Nested(integrate_workspace_fields)), } -integrate_icon_fields = { - 'type': fields.String, - 'url': fields.String, - 'emoji': fields.String -} +integrate_icon_fields = {"type": fields.String, "url": fields.String, "emoji": fields.String} integrate_page_fields = { - 'page_name': fields.String, - 'page_id': fields.String, - 'page_icon': fields.Nested(integrate_icon_fields, allow_null=True), - 'parent_id': fields.String, - 'type': fields.String + "page_name": fields.String, + "page_id": fields.String, + "page_icon": fields.Nested(integrate_icon_fields, allow_null=True), + "parent_id": fields.String, + "type": fields.String, } integrate_workspace_fields = { - 'workspace_name': fields.String, - 'workspace_id': fields.String, - 'workspace_icon': fields.String, - 'pages': fields.List(fields.Nested(integrate_page_fields)), - 'total': fields.Integer + "workspace_name": fields.String, + "workspace_id": fields.String, + "workspace_icon": fields.String, + "pages": fields.List(fields.Nested(integrate_page_fields)), + "total": fields.Integer, } integrate_fields = { - 'id': fields.String, - 'provider': fields.String, - 'created_at': TimestampField, - 'is_bound': fields.Boolean, - 'disabled': fields.Boolean, - 'link': fields.String, - 'source_info': fields.Nested(integrate_workspace_fields) + "id": fields.String, + "provider": fields.String, + "created_at": TimestampField, + "is_bound": fields.Boolean, + "disabled": fields.Boolean, + "link": fields.String, + "source_info": fields.Nested(integrate_workspace_fields), } integrate_list_fields = { - 'data': fields.List(fields.Nested(integrate_fields)), -} \ No newline at end of file + "data": fields.List(fields.Nested(integrate_fields)), +} diff --git a/api/fields/dataset_fields.py b/api/fields/dataset_fields.py index a9f79b5c67..9cf8da7acd 100644 --- a/api/fields/dataset_fields.py +++ b/api/fields/dataset_fields.py @@ -3,73 +3,64 @@ from flask_restful import fields from libs.helper import TimestampField dataset_fields = { - 'id': fields.String, - 'name': fields.String, - 'description': fields.String, - 'permission': fields.String, - 'data_source_type': fields.String, - 'indexing_technique': fields.String, - 'created_by': fields.String, - 'created_at': TimestampField, + "id": fields.String, + "name": fields.String, + "description": fields.String, + "permission": fields.String, + "data_source_type": fields.String, + "indexing_technique": fields.String, + "created_by": fields.String, + "created_at": TimestampField, } -reranking_model_fields = { - 'reranking_provider_name': fields.String, - 'reranking_model_name': fields.String -} +reranking_model_fields = {"reranking_provider_name": fields.String, "reranking_model_name": fields.String} -keyword_setting_fields = { - 'keyword_weight': fields.Float -} +keyword_setting_fields = {"keyword_weight": fields.Float} vector_setting_fields = { - 'vector_weight': fields.Float, - 'embedding_model_name': fields.String, - 'embedding_provider_name': fields.String, + "vector_weight": fields.Float, + "embedding_model_name": fields.String, + "embedding_provider_name": fields.String, } weighted_score_fields = { - 'keyword_setting': fields.Nested(keyword_setting_fields), - 'vector_setting': fields.Nested(vector_setting_fields), + "keyword_setting": fields.Nested(keyword_setting_fields), + "vector_setting": fields.Nested(vector_setting_fields), } dataset_retrieval_model_fields = { - 'search_method': fields.String, - 'reranking_enable': fields.Boolean, - 'reranking_mode': fields.String, - 'reranking_model': fields.Nested(reranking_model_fields), - 'weights': fields.Nested(weighted_score_fields, allow_null=True), - 'top_k': fields.Integer, - 'score_threshold_enabled': fields.Boolean, - 'score_threshold': fields.Float + "search_method": fields.String, + "reranking_enable": fields.Boolean, + "reranking_mode": fields.String, + "reranking_model": fields.Nested(reranking_model_fields), + "weights": fields.Nested(weighted_score_fields, allow_null=True), + "top_k": fields.Integer, + "score_threshold_enabled": fields.Boolean, + "score_threshold": fields.Float, } -tag_fields = { - 'id': fields.String, - 'name': fields.String, - 'type': fields.String -} +tag_fields = {"id": fields.String, "name": fields.String, "type": fields.String} dataset_detail_fields = { - 'id': fields.String, - 'name': fields.String, - 'description': fields.String, - 'provider': fields.String, - 'permission': fields.String, - 'data_source_type': fields.String, - 'indexing_technique': fields.String, - 'app_count': fields.Integer, - 'document_count': fields.Integer, - 'word_count': fields.Integer, - 'created_by': fields.String, - 'created_at': TimestampField, - 'updated_by': fields.String, - 'updated_at': TimestampField, - 'embedding_model': fields.String, - 'embedding_model_provider': fields.String, - 'embedding_available': fields.Boolean, - 'retrieval_model_dict': fields.Nested(dataset_retrieval_model_fields), - 'tags': fields.List(fields.Nested(tag_fields)) + "id": fields.String, + "name": fields.String, + "description": fields.String, + "provider": fields.String, + "permission": fields.String, + "data_source_type": fields.String, + "indexing_technique": fields.String, + "app_count": fields.Integer, + "document_count": fields.Integer, + "word_count": fields.Integer, + "created_by": fields.String, + "created_at": TimestampField, + "updated_by": fields.String, + "updated_at": TimestampField, + "embedding_model": fields.String, + "embedding_model_provider": fields.String, + "embedding_available": fields.Boolean, + "retrieval_model_dict": fields.Nested(dataset_retrieval_model_fields), + "tags": fields.List(fields.Nested(tag_fields)), } dataset_query_detail_fields = { @@ -79,7 +70,5 @@ dataset_query_detail_fields = { "source_app_id": fields.String, "created_by_role": fields.String, "created_by": fields.String, - "created_at": TimestampField + "created_at": TimestampField, } - - diff --git a/api/fields/document_fields.py b/api/fields/document_fields.py index e8215255b3..a83ec7bc97 100644 --- a/api/fields/document_fields.py +++ b/api/fields/document_fields.py @@ -4,75 +4,73 @@ from fields.dataset_fields import dataset_fields from libs.helper import TimestampField document_fields = { - 'id': fields.String, - 'position': fields.Integer, - 'data_source_type': fields.String, - 'data_source_info': fields.Raw(attribute='data_source_info_dict'), - 'data_source_detail_dict': fields.Raw(attribute='data_source_detail_dict'), - 'dataset_process_rule_id': fields.String, - 'name': fields.String, - 'created_from': fields.String, - 'created_by': fields.String, - 'created_at': TimestampField, - 'tokens': fields.Integer, - 'indexing_status': fields.String, - 'error': fields.String, - 'enabled': fields.Boolean, - 'disabled_at': TimestampField, - 'disabled_by': fields.String, - 'archived': fields.Boolean, - 'display_status': fields.String, - 'word_count': fields.Integer, - 'hit_count': fields.Integer, - 'doc_form': fields.String, + "id": fields.String, + "position": fields.Integer, + "data_source_type": fields.String, + "data_source_info": fields.Raw(attribute="data_source_info_dict"), + "data_source_detail_dict": fields.Raw(attribute="data_source_detail_dict"), + "dataset_process_rule_id": fields.String, + "name": fields.String, + "created_from": fields.String, + "created_by": fields.String, + "created_at": TimestampField, + "tokens": fields.Integer, + "indexing_status": fields.String, + "error": fields.String, + "enabled": fields.Boolean, + "disabled_at": TimestampField, + "disabled_by": fields.String, + "archived": fields.Boolean, + "display_status": fields.String, + "word_count": fields.Integer, + "hit_count": fields.Integer, + "doc_form": fields.String, } document_with_segments_fields = { - 'id': fields.String, - 'position': fields.Integer, - 'data_source_type': fields.String, - 'data_source_info': fields.Raw(attribute='data_source_info_dict'), - 'data_source_detail_dict': fields.Raw(attribute='data_source_detail_dict'), - 'dataset_process_rule_id': fields.String, - 'name': fields.String, - 'created_from': fields.String, - 'created_by': fields.String, - 'created_at': TimestampField, - 'tokens': fields.Integer, - 'indexing_status': fields.String, - 'error': fields.String, - 'enabled': fields.Boolean, - 'disabled_at': TimestampField, - 'disabled_by': fields.String, - 'archived': fields.Boolean, - 'display_status': fields.String, - 'word_count': fields.Integer, - 'hit_count': fields.Integer, - 'completed_segments': fields.Integer, - 'total_segments': fields.Integer + "id": fields.String, + "position": fields.Integer, + "data_source_type": fields.String, + "data_source_info": fields.Raw(attribute="data_source_info_dict"), + "data_source_detail_dict": fields.Raw(attribute="data_source_detail_dict"), + "dataset_process_rule_id": fields.String, + "name": fields.String, + "created_from": fields.String, + "created_by": fields.String, + "created_at": TimestampField, + "tokens": fields.Integer, + "indexing_status": fields.String, + "error": fields.String, + "enabled": fields.Boolean, + "disabled_at": TimestampField, + "disabled_by": fields.String, + "archived": fields.Boolean, + "display_status": fields.String, + "word_count": fields.Integer, + "hit_count": fields.Integer, + "completed_segments": fields.Integer, + "total_segments": fields.Integer, } dataset_and_document_fields = { - 'dataset': fields.Nested(dataset_fields), - 'documents': fields.List(fields.Nested(document_fields)), - 'batch': fields.String + "dataset": fields.Nested(dataset_fields), + "documents": fields.List(fields.Nested(document_fields)), + "batch": fields.String, } document_status_fields = { - 'id': fields.String, - 'indexing_status': fields.String, - 'processing_started_at': TimestampField, - 'parsing_completed_at': TimestampField, - 'cleaning_completed_at': TimestampField, - 'splitting_completed_at': TimestampField, - 'completed_at': TimestampField, - 'paused_at': TimestampField, - 'error': fields.String, - 'stopped_at': TimestampField, - 'completed_segments': fields.Integer, - 'total_segments': fields.Integer, + "id": fields.String, + "indexing_status": fields.String, + "processing_started_at": TimestampField, + "parsing_completed_at": TimestampField, + "cleaning_completed_at": TimestampField, + "splitting_completed_at": TimestampField, + "completed_at": TimestampField, + "paused_at": TimestampField, + "error": fields.String, + "stopped_at": TimestampField, + "completed_segments": fields.Integer, + "total_segments": fields.Integer, } -document_status_fields_list = { - 'data': fields.List(fields.Nested(document_status_fields)) -} \ No newline at end of file +document_status_fields_list = {"data": fields.List(fields.Nested(document_status_fields))} diff --git a/api/fields/end_user_fields.py b/api/fields/end_user_fields.py index ee630c12c2..99e529f9d1 100644 --- a/api/fields/end_user_fields.py +++ b/api/fields/end_user_fields.py @@ -1,8 +1,8 @@ from flask_restful import fields simple_end_user_fields = { - 'id': fields.String, - 'type': fields.String, - 'is_anonymous': fields.Boolean, - 'session_id': fields.String, + "id": fields.String, + "type": fields.String, + "is_anonymous": fields.Boolean, + "session_id": fields.String, } diff --git a/api/fields/file_fields.py b/api/fields/file_fields.py index 2ef379dabc..e5a03ce77e 100644 --- a/api/fields/file_fields.py +++ b/api/fields/file_fields.py @@ -3,17 +3,17 @@ from flask_restful import fields from libs.helper import TimestampField upload_config_fields = { - 'file_size_limit': fields.Integer, - 'batch_count_limit': fields.Integer, - 'image_file_size_limit': fields.Integer, + "file_size_limit": fields.Integer, + "batch_count_limit": fields.Integer, + "image_file_size_limit": fields.Integer, } file_fields = { - 'id': fields.String, - 'name': fields.String, - 'size': fields.Integer, - 'extension': fields.String, - 'mime_type': fields.String, - 'created_by': fields.String, - 'created_at': TimestampField, -} \ No newline at end of file + "id": fields.String, + "name": fields.String, + "size": fields.Integer, + "extension": fields.String, + "mime_type": fields.String, + "created_by": fields.String, + "created_at": TimestampField, +} diff --git a/api/fields/hit_testing_fields.py b/api/fields/hit_testing_fields.py index 541e56a378..f36e80f8d4 100644 --- a/api/fields/hit_testing_fields.py +++ b/api/fields/hit_testing_fields.py @@ -3,39 +3,39 @@ from flask_restful import fields from libs.helper import TimestampField document_fields = { - 'id': fields.String, - 'data_source_type': fields.String, - 'name': fields.String, - 'doc_type': fields.String, + "id": fields.String, + "data_source_type": fields.String, + "name": fields.String, + "doc_type": fields.String, } segment_fields = { - 'id': fields.String, - 'position': fields.Integer, - 'document_id': fields.String, - 'content': fields.String, - 'answer': fields.String, - 'word_count': fields.Integer, - 'tokens': fields.Integer, - 'keywords': fields.List(fields.String), - 'index_node_id': fields.String, - 'index_node_hash': fields.String, - 'hit_count': fields.Integer, - 'enabled': fields.Boolean, - 'disabled_at': TimestampField, - 'disabled_by': fields.String, - 'status': fields.String, - 'created_by': fields.String, - 'created_at': TimestampField, - 'indexing_at': TimestampField, - 'completed_at': TimestampField, - 'error': fields.String, - 'stopped_at': TimestampField, - 'document': fields.Nested(document_fields), + "id": fields.String, + "position": fields.Integer, + "document_id": fields.String, + "content": fields.String, + "answer": fields.String, + "word_count": fields.Integer, + "tokens": fields.Integer, + "keywords": fields.List(fields.String), + "index_node_id": fields.String, + "index_node_hash": fields.String, + "hit_count": fields.Integer, + "enabled": fields.Boolean, + "disabled_at": TimestampField, + "disabled_by": fields.String, + "status": fields.String, + "created_by": fields.String, + "created_at": TimestampField, + "indexing_at": TimestampField, + "completed_at": TimestampField, + "error": fields.String, + "stopped_at": TimestampField, + "document": fields.Nested(document_fields), } hit_testing_record_fields = { - 'segment': fields.Nested(segment_fields), - 'score': fields.Float, - 'tsne_position': fields.Raw -} \ No newline at end of file + "segment": fields.Nested(segment_fields), + "score": fields.Float, + "tsne_position": fields.Raw, +} diff --git a/api/fields/installed_app_fields.py b/api/fields/installed_app_fields.py index 35cc5a6475..b87cc65324 100644 --- a/api/fields/installed_app_fields.py +++ b/api/fields/installed_app_fields.py @@ -3,23 +3,21 @@ from flask_restful import fields from libs.helper import TimestampField app_fields = { - 'id': fields.String, - 'name': fields.String, - 'mode': fields.String, - 'icon': fields.String, - 'icon_background': fields.String + "id": fields.String, + "name": fields.String, + "mode": fields.String, + "icon": fields.String, + "icon_background": fields.String, } installed_app_fields = { - 'id': fields.String, - 'app': fields.Nested(app_fields), - 'app_owner_tenant_id': fields.String, - 'is_pinned': fields.Boolean, - 'last_used_at': TimestampField, - 'editable': fields.Boolean, - 'uninstallable': fields.Boolean + "id": fields.String, + "app": fields.Nested(app_fields), + "app_owner_tenant_id": fields.String, + "is_pinned": fields.Boolean, + "last_used_at": TimestampField, + "editable": fields.Boolean, + "uninstallable": fields.Boolean, } -installed_app_list_fields = { - 'installed_apps': fields.List(fields.Nested(installed_app_fields)) -} \ No newline at end of file +installed_app_list_fields = {"installed_apps": fields.List(fields.Nested(installed_app_fields))} diff --git a/api/fields/member_fields.py b/api/fields/member_fields.py index d061b59c34..1cf8e408d1 100644 --- a/api/fields/member_fields.py +++ b/api/fields/member_fields.py @@ -2,38 +2,32 @@ from flask_restful import fields from libs.helper import TimestampField -simple_account_fields = { - 'id': fields.String, - 'name': fields.String, - 'email': fields.String -} +simple_account_fields = {"id": fields.String, "name": fields.String, "email": fields.String} account_fields = { - 'id': fields.String, - 'name': fields.String, - 'avatar': fields.String, - 'email': fields.String, - 'is_password_set': fields.Boolean, - 'interface_language': fields.String, - 'interface_theme': fields.String, - 'timezone': fields.String, - 'last_login_at': TimestampField, - 'last_login_ip': fields.String, - 'created_at': TimestampField + "id": fields.String, + "name": fields.String, + "avatar": fields.String, + "email": fields.String, + "is_password_set": fields.Boolean, + "interface_language": fields.String, + "interface_theme": fields.String, + "timezone": fields.String, + "last_login_at": TimestampField, + "last_login_ip": fields.String, + "created_at": TimestampField, } account_with_role_fields = { - 'id': fields.String, - 'name': fields.String, - 'avatar': fields.String, - 'email': fields.String, - 'last_login_at': TimestampField, - 'last_active_at': TimestampField, - 'created_at': TimestampField, - 'role': fields.String, - 'status': fields.String, + "id": fields.String, + "name": fields.String, + "avatar": fields.String, + "email": fields.String, + "last_login_at": TimestampField, + "last_active_at": TimestampField, + "created_at": TimestampField, + "role": fields.String, + "status": fields.String, } -account_with_role_list_fields = { - 'accounts': fields.List(fields.Nested(account_with_role_fields)) -} +account_with_role_list_fields = {"accounts": fields.List(fields.Nested(account_with_role_fields))} diff --git a/api/fields/message_fields.py b/api/fields/message_fields.py index 3116843589..3d2df87afb 100644 --- a/api/fields/message_fields.py +++ b/api/fields/message_fields.py @@ -3,83 +3,79 @@ from flask_restful import fields from fields.conversation_fields import message_file_fields from libs.helper import TimestampField -feedback_fields = { - 'rating': fields.String -} +feedback_fields = {"rating": fields.String} retriever_resource_fields = { - 'id': fields.String, - 'message_id': fields.String, - 'position': fields.Integer, - 'dataset_id': fields.String, - 'dataset_name': fields.String, - 'document_id': fields.String, - 'document_name': fields.String, - 'data_source_type': fields.String, - 'segment_id': fields.String, - 'score': fields.Float, - 'hit_count': fields.Integer, - 'word_count': fields.Integer, - 'segment_position': fields.Integer, - 'index_node_hash': fields.String, - 'content': fields.String, - 'created_at': TimestampField + "id": fields.String, + "message_id": fields.String, + "position": fields.Integer, + "dataset_id": fields.String, + "dataset_name": fields.String, + "document_id": fields.String, + "document_name": fields.String, + "data_source_type": fields.String, + "segment_id": fields.String, + "score": fields.Float, + "hit_count": fields.Integer, + "word_count": fields.Integer, + "segment_position": fields.Integer, + "index_node_hash": fields.String, + "content": fields.String, + "created_at": TimestampField, } -feedback_fields = { - 'rating': fields.String -} +feedback_fields = {"rating": fields.String} agent_thought_fields = { - 'id': fields.String, - 'chain_id': fields.String, - 'message_id': fields.String, - 'position': fields.Integer, - 'thought': fields.String, - 'tool': fields.String, - 'tool_labels': fields.Raw, - 'tool_input': fields.String, - 'created_at': TimestampField, - 'observation': fields.String, - 'files': fields.List(fields.String) + "id": fields.String, + "chain_id": fields.String, + "message_id": fields.String, + "position": fields.Integer, + "thought": fields.String, + "tool": fields.String, + "tool_labels": fields.Raw, + "tool_input": fields.String, + "created_at": TimestampField, + "observation": fields.String, + "files": fields.List(fields.String), } retriever_resource_fields = { - 'id': fields.String, - 'message_id': fields.String, - 'position': fields.Integer, - 'dataset_id': fields.String, - 'dataset_name': fields.String, - 'document_id': fields.String, - 'document_name': fields.String, - 'data_source_type': fields.String, - 'segment_id': fields.String, - 'score': fields.Float, - 'hit_count': fields.Integer, - 'word_count': fields.Integer, - 'segment_position': fields.Integer, - 'index_node_hash': fields.String, - 'content': fields.String, - 'created_at': TimestampField + "id": fields.String, + "message_id": fields.String, + "position": fields.Integer, + "dataset_id": fields.String, + "dataset_name": fields.String, + "document_id": fields.String, + "document_name": fields.String, + "data_source_type": fields.String, + "segment_id": fields.String, + "score": fields.Float, + "hit_count": fields.Integer, + "word_count": fields.Integer, + "segment_position": fields.Integer, + "index_node_hash": fields.String, + "content": fields.String, + "created_at": TimestampField, } message_fields = { - 'id': fields.String, - 'conversation_id': fields.String, - 'inputs': fields.Raw, - 'query': fields.String, - 'answer': fields.String(attribute='re_sign_file_url_answer'), - 'feedback': fields.Nested(feedback_fields, attribute='user_feedback', allow_null=True), - 'retriever_resources': fields.List(fields.Nested(retriever_resource_fields)), - 'created_at': TimestampField, - 'agent_thoughts': fields.List(fields.Nested(agent_thought_fields)), - 'message_files': fields.List(fields.Nested(message_file_fields), attribute='files'), - 'status': fields.String, - 'error': fields.String, + "id": fields.String, + "conversation_id": fields.String, + "inputs": fields.Raw, + "query": fields.String, + "answer": fields.String(attribute="re_sign_file_url_answer"), + "feedback": fields.Nested(feedback_fields, attribute="user_feedback", allow_null=True), + "retriever_resources": fields.List(fields.Nested(retriever_resource_fields)), + "created_at": TimestampField, + "agent_thoughts": fields.List(fields.Nested(agent_thought_fields)), + "message_files": fields.List(fields.Nested(message_file_fields), attribute="files"), + "status": fields.String, + "error": fields.String, } message_infinite_scroll_pagination_fields = { - 'limit': fields.Integer, - 'has_more': fields.Boolean, - 'data': fields.List(fields.Nested(message_fields)) + "limit": fields.Integer, + "has_more": fields.Boolean, + "data": fields.List(fields.Nested(message_fields)), } diff --git a/api/fields/segment_fields.py b/api/fields/segment_fields.py index e41d1a53dd..2dd4cb45be 100644 --- a/api/fields/segment_fields.py +++ b/api/fields/segment_fields.py @@ -3,31 +3,31 @@ from flask_restful import fields from libs.helper import TimestampField segment_fields = { - 'id': fields.String, - 'position': fields.Integer, - 'document_id': fields.String, - 'content': fields.String, - 'answer': fields.String, - 'word_count': fields.Integer, - 'tokens': fields.Integer, - 'keywords': fields.List(fields.String), - 'index_node_id': fields.String, - 'index_node_hash': fields.String, - 'hit_count': fields.Integer, - 'enabled': fields.Boolean, - 'disabled_at': TimestampField, - 'disabled_by': fields.String, - 'status': fields.String, - 'created_by': fields.String, - 'created_at': TimestampField, - 'indexing_at': TimestampField, - 'completed_at': TimestampField, - 'error': fields.String, - 'stopped_at': TimestampField + "id": fields.String, + "position": fields.Integer, + "document_id": fields.String, + "content": fields.String, + "answer": fields.String, + "word_count": fields.Integer, + "tokens": fields.Integer, + "keywords": fields.List(fields.String), + "index_node_id": fields.String, + "index_node_hash": fields.String, + "hit_count": fields.Integer, + "enabled": fields.Boolean, + "disabled_at": TimestampField, + "disabled_by": fields.String, + "status": fields.String, + "created_by": fields.String, + "created_at": TimestampField, + "indexing_at": TimestampField, + "completed_at": TimestampField, + "error": fields.String, + "stopped_at": TimestampField, } segment_list_response = { - 'data': fields.List(fields.Nested(segment_fields)), - 'has_more': fields.Boolean, - 'limit': fields.Integer + "data": fields.List(fields.Nested(segment_fields)), + "has_more": fields.Boolean, + "limit": fields.Integer, } diff --git a/api/fields/tag_fields.py b/api/fields/tag_fields.py index f7e030b738..9af4fc57dd 100644 --- a/api/fields/tag_fields.py +++ b/api/fields/tag_fields.py @@ -1,8 +1,3 @@ from flask_restful import fields -tag_fields = { - 'id': fields.String, - 'name': fields.String, - 'type': fields.String, - 'binding_count': fields.String -} \ No newline at end of file +tag_fields = {"id": fields.String, "name": fields.String, "type": fields.String, "binding_count": fields.String} diff --git a/api/fields/workflow_app_log_fields.py b/api/fields/workflow_app_log_fields.py index e230c159fb..a53b546249 100644 --- a/api/fields/workflow_app_log_fields.py +++ b/api/fields/workflow_app_log_fields.py @@ -7,18 +7,18 @@ from libs.helper import TimestampField workflow_app_log_partial_fields = { "id": fields.String, - "workflow_run": fields.Nested(workflow_run_for_log_fields, attribute='workflow_run', allow_null=True), + "workflow_run": fields.Nested(workflow_run_for_log_fields, attribute="workflow_run", allow_null=True), "created_from": fields.String, "created_by_role": fields.String, - "created_by_account": fields.Nested(simple_account_fields, attribute='created_by_account', allow_null=True), - "created_by_end_user": fields.Nested(simple_end_user_fields, attribute='created_by_end_user', allow_null=True), - "created_at": TimestampField + "created_by_account": fields.Nested(simple_account_fields, attribute="created_by_account", allow_null=True), + "created_by_end_user": fields.Nested(simple_end_user_fields, attribute="created_by_end_user", allow_null=True), + "created_at": TimestampField, } workflow_app_log_pagination_fields = { - 'page': fields.Integer, - 'limit': fields.Integer(attribute='per_page'), - 'total': fields.Integer, - 'has_more': fields.Boolean(attribute='has_next'), - 'data': fields.List(fields.Nested(workflow_app_log_partial_fields), attribute='items') + "page": fields.Integer, + "limit": fields.Integer(attribute="per_page"), + "total": fields.Integer, + "has_more": fields.Boolean(attribute="has_next"), + "data": fields.List(fields.Nested(workflow_app_log_partial_fields), attribute="items"), } diff --git a/api/fields/workflow_fields.py b/api/fields/workflow_fields.py index c1dd0e184a..240b8f2eb0 100644 --- a/api/fields/workflow_fields.py +++ b/api/fields/workflow_fields.py @@ -13,43 +13,43 @@ class EnvironmentVariableField(fields.Raw): # Mask secret variables values in environment_variables if isinstance(value, SecretVariable): return { - 'id': value.id, - 'name': value.name, - 'value': encrypter.obfuscated_token(value.value), - 'value_type': value.value_type.value, + "id": value.id, + "name": value.name, + "value": encrypter.obfuscated_token(value.value), + "value_type": value.value_type.value, } if isinstance(value, Variable): return { - 'id': value.id, - 'name': value.name, - 'value': value.value, - 'value_type': value.value_type.value, + "id": value.id, + "name": value.name, + "value": value.value, + "value_type": value.value_type.value, } if isinstance(value, dict): - value_type = value.get('value_type') + value_type = value.get("value_type") if value_type not in ENVIRONMENT_VARIABLE_SUPPORTED_TYPES: - raise ValueError(f'Unsupported environment variable value type: {value_type}') + raise ValueError(f"Unsupported environment variable value type: {value_type}") return value conversation_variable_fields = { - 'id': fields.String, - 'name': fields.String, - 'value_type': fields.String(attribute='value_type.value'), - 'value': fields.Raw, - 'description': fields.String, + "id": fields.String, + "name": fields.String, + "value_type": fields.String(attribute="value_type.value"), + "value": fields.Raw, + "description": fields.String, } workflow_fields = { - 'id': fields.String, - 'graph': fields.Raw(attribute='graph_dict'), - 'features': fields.Raw(attribute='features_dict'), - 'hash': fields.String(attribute='unique_hash'), - 'created_by': fields.Nested(simple_account_fields, attribute='created_by_account'), - 'created_at': TimestampField, - 'updated_by': fields.Nested(simple_account_fields, attribute='updated_by_account', allow_null=True), - 'updated_at': TimestampField, - 'tool_published': fields.Boolean, - 'environment_variables': fields.List(EnvironmentVariableField()), - 'conversation_variables': fields.List(fields.Nested(conversation_variable_fields)), + "id": fields.String, + "graph": fields.Raw(attribute="graph_dict"), + "features": fields.Raw(attribute="features_dict"), + "hash": fields.String(attribute="unique_hash"), + "created_by": fields.Nested(simple_account_fields, attribute="created_by_account"), + "created_at": TimestampField, + "updated_by": fields.Nested(simple_account_fields, attribute="updated_by_account", allow_null=True), + "updated_at": TimestampField, + "tool_published": fields.Boolean, + "environment_variables": fields.List(EnvironmentVariableField()), + "conversation_variables": fields.List(fields.Nested(conversation_variable_fields)), } diff --git a/api/fields/workflow_run_fields.py b/api/fields/workflow_run_fields.py index 3e798473cd..1413adf719 100644 --- a/api/fields/workflow_run_fields.py +++ b/api/fields/workflow_run_fields.py @@ -13,7 +13,7 @@ workflow_run_for_log_fields = { "total_tokens": fields.Integer, "total_steps": fields.Integer, "created_at": TimestampField, - "finished_at": TimestampField + "finished_at": TimestampField, } workflow_run_for_list_fields = { @@ -24,9 +24,9 @@ workflow_run_for_list_fields = { "elapsed_time": fields.Float, "total_tokens": fields.Integer, "total_steps": fields.Integer, - "created_by_account": fields.Nested(simple_account_fields, attribute='created_by_account', allow_null=True), + "created_by_account": fields.Nested(simple_account_fields, attribute="created_by_account", allow_null=True), "created_at": TimestampField, - "finished_at": TimestampField + "finished_at": TimestampField, } advanced_chat_workflow_run_for_list_fields = { @@ -39,40 +39,40 @@ advanced_chat_workflow_run_for_list_fields = { "elapsed_time": fields.Float, "total_tokens": fields.Integer, "total_steps": fields.Integer, - "created_by_account": fields.Nested(simple_account_fields, attribute='created_by_account', allow_null=True), + "created_by_account": fields.Nested(simple_account_fields, attribute="created_by_account", allow_null=True), "created_at": TimestampField, - "finished_at": TimestampField + "finished_at": TimestampField, } advanced_chat_workflow_run_pagination_fields = { - 'limit': fields.Integer(attribute='limit'), - 'has_more': fields.Boolean(attribute='has_more'), - 'data': fields.List(fields.Nested(advanced_chat_workflow_run_for_list_fields), attribute='data') + "limit": fields.Integer(attribute="limit"), + "has_more": fields.Boolean(attribute="has_more"), + "data": fields.List(fields.Nested(advanced_chat_workflow_run_for_list_fields), attribute="data"), } workflow_run_pagination_fields = { - 'limit': fields.Integer(attribute='limit'), - 'has_more': fields.Boolean(attribute='has_more'), - 'data': fields.List(fields.Nested(workflow_run_for_list_fields), attribute='data') + "limit": fields.Integer(attribute="limit"), + "has_more": fields.Boolean(attribute="has_more"), + "data": fields.List(fields.Nested(workflow_run_for_list_fields), attribute="data"), } workflow_run_detail_fields = { "id": fields.String, "sequence_number": fields.Integer, "version": fields.String, - "graph": fields.Raw(attribute='graph_dict'), - "inputs": fields.Raw(attribute='inputs_dict'), + "graph": fields.Raw(attribute="graph_dict"), + "inputs": fields.Raw(attribute="inputs_dict"), "status": fields.String, - "outputs": fields.Raw(attribute='outputs_dict'), + "outputs": fields.Raw(attribute="outputs_dict"), "error": fields.String, "elapsed_time": fields.Float, "total_tokens": fields.Integer, "total_steps": fields.Integer, "created_by_role": fields.String, - "created_by_account": fields.Nested(simple_account_fields, attribute='created_by_account', allow_null=True), - "created_by_end_user": fields.Nested(simple_end_user_fields, attribute='created_by_end_user', allow_null=True), + "created_by_account": fields.Nested(simple_account_fields, attribute="created_by_account", allow_null=True), + "created_by_end_user": fields.Nested(simple_end_user_fields, attribute="created_by_end_user", allow_null=True), "created_at": TimestampField, - "finished_at": TimestampField + "finished_at": TimestampField, } workflow_run_node_execution_fields = { @@ -82,21 +82,21 @@ workflow_run_node_execution_fields = { "node_id": fields.String, "node_type": fields.String, "title": fields.String, - "inputs": fields.Raw(attribute='inputs_dict'), - "process_data": fields.Raw(attribute='process_data_dict'), - "outputs": fields.Raw(attribute='outputs_dict'), + "inputs": fields.Raw(attribute="inputs_dict"), + "process_data": fields.Raw(attribute="process_data_dict"), + "outputs": fields.Raw(attribute="outputs_dict"), "status": fields.String, "error": fields.String, "elapsed_time": fields.Float, - "execution_metadata": fields.Raw(attribute='execution_metadata_dict'), + "execution_metadata": fields.Raw(attribute="execution_metadata_dict"), "extras": fields.Raw, "created_at": TimestampField, "created_by_role": fields.String, - "created_by_account": fields.Nested(simple_account_fields, attribute='created_by_account', allow_null=True), - "created_by_end_user": fields.Nested(simple_end_user_fields, attribute='created_by_end_user', allow_null=True), - "finished_at": TimestampField + "created_by_account": fields.Nested(simple_account_fields, attribute="created_by_account", allow_null=True), + "created_by_end_user": fields.Nested(simple_end_user_fields, attribute="created_by_end_user", allow_null=True), + "finished_at": TimestampField, } workflow_run_node_execution_list_fields = { - 'data': fields.List(fields.Nested(workflow_run_node_execution_fields)), + "data": fields.List(fields.Nested(workflow_run_node_execution_fields)), } diff --git a/api/libs/bearer_data_source.py b/api/libs/bearer_data_source.py index 04de1fb6da..ab6e398eb9 100644 --- a/api/libs/bearer_data_source.py +++ b/api/libs/bearer_data_source.py @@ -2,10 +2,10 @@ from abc import abstractmethod import requests -from api.models.source import DataSourceBearerBinding from flask_login import current_user from extensions.ext_database import db +from models.source import DataSourceBearerBinding class BearerDataSource: @@ -25,7 +25,7 @@ class FireCrawlDataSource(BearerDataSource): TEST_CRAWL_SITE_URL = "https://www.google.com" FIRECRAWL_API_VERSION = "v0" - test_api_endpoint = self.api_base_url.rstrip('/') + f"/{FIRECRAWL_API_VERSION}/scrape" + test_api_endpoint = self.api_base_url.rstrip("/") + f"/{FIRECRAWL_API_VERSION}/scrape" headers = { "Authorization": f"Bearer {self.api_key}", @@ -45,9 +45,9 @@ class FireCrawlDataSource(BearerDataSource): data_source_binding = DataSourceBearerBinding.query.filter( db.and_( DataSourceBearerBinding.tenant_id == current_user.current_tenant_id, - DataSourceBearerBinding.provider == 'firecrawl', + DataSourceBearerBinding.provider == "firecrawl", DataSourceBearerBinding.endpoint_url == self.api_base_url, - DataSourceBearerBinding.bearer_key == self.api_key + DataSourceBearerBinding.bearer_key == self.api_key, ) ).first() if data_source_binding: @@ -56,9 +56,9 @@ class FireCrawlDataSource(BearerDataSource): else: new_data_source_binding = DataSourceBearerBinding( tenant_id=current_user.current_tenant_id, - provider='firecrawl', + provider="firecrawl", endpoint_url=self.api_base_url, - bearer_key=self.api_key + bearer_key=self.api_key, ) db.session.add(new_data_source_binding) db.session.commit() diff --git a/api/libs/exception.py b/api/libs/exception.py index 567062f064..5970269ecd 100644 --- a/api/libs/exception.py +++ b/api/libs/exception.py @@ -4,7 +4,7 @@ from werkzeug.exceptions import HTTPException class BaseHTTPException(HTTPException): - error_code: str = 'unknown' + error_code: str = "unknown" data: Optional[dict] = None def __init__(self, description=None, response=None): @@ -14,4 +14,4 @@ class BaseHTTPException(HTTPException): "code": self.error_code, "message": self.description, "status": self.code, - } \ No newline at end of file + } diff --git a/api/libs/external_api.py b/api/libs/external_api.py index 677ff0fc5b..179617ac0a 100644 --- a/api/libs/external_api.py +++ b/api/libs/external_api.py @@ -10,7 +10,6 @@ from core.errors.error import AppInvokeQuotaExceededError class ExternalApi(Api): - def handle_error(self, e): """Error handler for the API transforms a raised exception into a Flask response, with the appropriate HTTP status code and body. @@ -29,54 +28,57 @@ class ExternalApi(Api): status_code = e.code default_data = { - 'code': re.sub(r'(? self.max_length: - error = ('Invalid {arg}: {val}. {arg} cannot exceed length {length}' - .format(arg=self.argument, val=value, length=self.max_length)) + error = "Invalid {arg}: {val}. {arg} cannot exceed length {length}".format( + arg=self.argument, val=value, length=self.max_length + ) raise ValueError(error) return value class float_range: - """ Restrict input to an float in a range (inclusive) """ - def __init__(self, low, high, argument='argument'): + """Restrict input to an float in a range (inclusive)""" + + def __init__(self, low, high, argument="argument"): self.low = low self.high = high self.argument = argument @@ -99,15 +100,16 @@ class float_range: def __call__(self, value): value = _get_float(value) if value < self.low or value > self.high: - error = ('Invalid {arg}: {val}. {arg} must be within the range {lo} - {hi}' - .format(arg=self.argument, val=value, lo=self.low, hi=self.high)) + error = "Invalid {arg}: {val}. {arg} must be within the range {lo} - {hi}".format( + arg=self.argument, val=value, lo=self.low, hi=self.high + ) raise ValueError(error) return value class datetime_string: - def __init__(self, format, argument='argument'): + def __init__(self, format, argument="argument"): self.format = format self.argument = argument @@ -115,8 +117,9 @@ class datetime_string: try: datetime.strptime(value, self.format) except ValueError: - error = ('Invalid {arg}: {val}. {arg} must be conform to the format {format}' - .format(arg=self.argument, val=value, format=self.format)) + error = "Invalid {arg}: {val}. {arg} must be conform to the format {format}".format( + arg=self.argument, val=value, format=self.format + ) raise ValueError(error) return value @@ -126,14 +129,14 @@ def _get_float(value): try: return float(value) except (TypeError, ValueError): - raise ValueError('{} is not a valid float'.format(value)) + raise ValueError("{} is not a valid float".format(value)) + def timezone(timezone_string): if timezone_string and timezone_string in available_timezones(): return timezone_string - error = ('{timezone_string} is not a valid timezone.' - .format(timezone_string=timezone_string)) + error = "{timezone_string} is not a valid timezone.".format(timezone_string=timezone_string) raise ValueError(error) @@ -147,8 +150,8 @@ def generate_string(n): def get_remote_ip(request) -> str: - if request.headers.get('CF-Connecting-IP'): - return request.headers.get('Cf-Connecting-Ip') + if request.headers.get("CF-Connecting-IP"): + return request.headers.get("Cf-Connecting-Ip") elif request.headers.getlist("X-Forwarded-For"): return request.headers.getlist("X-Forwarded-For")[0] else: @@ -156,54 +159,45 @@ def get_remote_ip(request) -> str: def generate_text_hash(text: str) -> str: - hash_text = str(text) + 'None' + hash_text = str(text) + "None" return sha256(hash_text.encode()).hexdigest() def compact_generate_response(response: Union[dict, RateLimitGenerator]) -> Response: if isinstance(response, dict): - return Response(response=json.dumps(response), status=200, mimetype='application/json') + return Response(response=json.dumps(response), status=200, mimetype="application/json") else: + def generate() -> Generator: yield from response - return Response(stream_with_context(generate()), status=200, - mimetype='text/event-stream') + return Response(stream_with_context(generate()), status=200, mimetype="text/event-stream") class TokenManager: - @classmethod def generate_token(cls, account: Account, token_type: str, additional_data: dict = None) -> str: old_token = cls._get_current_token_for_account(account.id, token_type) if old_token: if isinstance(old_token, bytes): - old_token = old_token.decode('utf-8') + old_token = old_token.decode("utf-8") cls.revoke_token(old_token, token_type) token = str(uuid.uuid4()) - token_data = { - 'account_id': account.id, - 'email': account.email, - 'token_type': token_type - } + token_data = {"account_id": account.id, "email": account.email, "token_type": token_type} if additional_data: token_data.update(additional_data) - expiry_hours = current_app.config[f'{token_type.upper()}_TOKEN_EXPIRY_HOURS'] + expiry_hours = current_app.config[f"{token_type.upper()}_TOKEN_EXPIRY_HOURS"] token_key = cls._get_token_key(token, token_type) - redis_client.setex( - token_key, - expiry_hours * 60 * 60, - json.dumps(token_data) - ) + redis_client.setex(token_key, expiry_hours * 60 * 60, json.dumps(token_data)) cls._set_current_token_for_account(account.id, token, token_type, expiry_hours) return token @classmethod def _get_token_key(cls, token: str, token_type: str) -> str: - return f'{token_type}:token:{token}' + return f"{token_type}:token:{token}" @classmethod def revoke_token(cls, token: str, token_type: str): @@ -233,7 +227,7 @@ class TokenManager: @classmethod def _get_account_token_key(cls, account_id: str, token_type: str) -> str: - return f'{token_type}:account:{account_id}' + return f"{token_type}:account:{account_id}" class RateLimiter: @@ -250,7 +244,7 @@ class RateLimiter: current_time = int(time.time()) window_start_time = current_time - self.time_window - redis_client.zremrangebyscore(key, '-inf', window_start_time) + redis_client.zremrangebyscore(key, "-inf", window_start_time) attempts = redis_client.zcard(key) if attempts and int(attempts) >= self.max_attempts: diff --git a/api/libs/infinite_scroll_pagination.py b/api/libs/infinite_scroll_pagination.py index a1cb7b78fc..133ccb1883 100644 --- a/api/libs/infinite_scroll_pagination.py +++ b/api/libs/infinite_scroll_pagination.py @@ -1,4 +1,3 @@ - class InfiniteScrollPagination: def __init__(self, data, limit, has_more): self.data = data diff --git a/api/libs/json_in_md_parser.py b/api/libs/json_in_md_parser.py index 2cf023a399..41d6905899 100644 --- a/api/libs/json_in_md_parser.py +++ b/api/libs/json_in_md_parser.py @@ -10,13 +10,13 @@ def parse_json_markdown(json_string: str) -> dict: end_index = json_string.find("```", start_index + len("```json")) if start_index != -1 and end_index != -1: - extracted_content = json_string[start_index + len("```json"):end_index].strip() + extracted_content = json_string[start_index + len("```json") : end_index].strip() # Parse the JSON string into a Python dictionary parsed = json.loads(extracted_content) elif start_index != -1 and end_index == -1 and json_string.endswith("``"): end_index = json_string.find("``", start_index + len("```json")) - extracted_content = json_string[start_index + len("```json"):end_index].strip() + extracted_content = json_string[start_index + len("```json") : end_index].strip() # Parse the JSON string into a Python dictionary parsed = json.loads(extracted_content) @@ -37,7 +37,6 @@ def parse_and_check_json_markdown(text: str, expected_keys: list[str]) -> dict: for key in expected_keys: if key not in json_obj: raise OutputParserException( - f"Got invalid return object. Expected key `{key}` " - f"to be present, but got {json_obj}" + f"Got invalid return object. Expected key `{key}` " f"to be present, but got {json_obj}" ) return json_obj diff --git a/api/libs/login.py b/api/libs/login.py index 14085fe603..7f05eb8404 100644 --- a/api/libs/login.py +++ b/api/libs/login.py @@ -51,27 +51,29 @@ def login_required(func): @wraps(func) def decorated_view(*args, **kwargs): - auth_header = request.headers.get('Authorization') - admin_api_key_enable = os.getenv('ADMIN_API_KEY_ENABLE', default='False') - if admin_api_key_enable.lower() == 'true': + auth_header = request.headers.get("Authorization") + admin_api_key_enable = os.getenv("ADMIN_API_KEY_ENABLE", default="False") + if admin_api_key_enable.lower() == "true": if auth_header: - if ' ' not in auth_header: - raise Unauthorized('Invalid Authorization header format. Expected \'Bearer \' format.') + if " " not in auth_header: + raise Unauthorized("Invalid Authorization header format. Expected 'Bearer ' format.") auth_scheme, auth_token = auth_header.split(None, 1) auth_scheme = auth_scheme.lower() - if auth_scheme != 'bearer': - raise Unauthorized('Invalid Authorization header format. Expected \'Bearer \' format.') - admin_api_key = os.getenv('ADMIN_API_KEY') + if auth_scheme != "bearer": + raise Unauthorized("Invalid Authorization header format. Expected 'Bearer ' format.") + admin_api_key = os.getenv("ADMIN_API_KEY") if admin_api_key: - if os.getenv('ADMIN_API_KEY') == auth_token: - workspace_id = request.headers.get('X-WORKSPACE-ID') + if os.getenv("ADMIN_API_KEY") == auth_token: + workspace_id = request.headers.get("X-WORKSPACE-ID") if workspace_id: - tenant_account_join = db.session.query(Tenant, TenantAccountJoin) \ - .filter(Tenant.id == workspace_id) \ - .filter(TenantAccountJoin.tenant_id == Tenant.id) \ - .filter(TenantAccountJoin.role == 'owner') \ + tenant_account_join = ( + db.session.query(Tenant, TenantAccountJoin) + .filter(Tenant.id == workspace_id) + .filter(TenantAccountJoin.tenant_id == Tenant.id) + .filter(TenantAccountJoin.role == "owner") .one_or_none() + ) if tenant_account_join: tenant, ta = tenant_account_join account = Account.query.filter_by(id=ta.account_id).first() diff --git a/api/libs/oauth.py b/api/libs/oauth.py index dacdee0bc1..d8ce1a1e66 100644 --- a/api/libs/oauth.py +++ b/api/libs/oauth.py @@ -35,31 +35,31 @@ class OAuth: class GitHubOAuth(OAuth): - _AUTH_URL = 'https://github.com/login/oauth/authorize' - _TOKEN_URL = 'https://github.com/login/oauth/access_token' - _USER_INFO_URL = 'https://api.github.com/user' - _EMAIL_INFO_URL = 'https://api.github.com/user/emails' + _AUTH_URL = "https://github.com/login/oauth/authorize" + _TOKEN_URL = "https://github.com/login/oauth/access_token" + _USER_INFO_URL = "https://api.github.com/user" + _EMAIL_INFO_URL = "https://api.github.com/user/emails" def get_authorization_url(self): params = { - 'client_id': self.client_id, - 'redirect_uri': self.redirect_uri, - 'scope': 'user:email' # Request only basic user information + "client_id": self.client_id, + "redirect_uri": self.redirect_uri, + "scope": "user:email", # Request only basic user information } return f"{self._AUTH_URL}?{urllib.parse.urlencode(params)}" def get_access_token(self, code: str): data = { - 'client_id': self.client_id, - 'client_secret': self.client_secret, - 'code': code, - 'redirect_uri': self.redirect_uri + "client_id": self.client_id, + "client_secret": self.client_secret, + "code": code, + "redirect_uri": self.redirect_uri, } - headers = {'Accept': 'application/json'} + headers = {"Accept": "application/json"} response = requests.post(self._TOKEN_URL, data=data, headers=headers) response_json = response.json() - access_token = response_json.get('access_token') + access_token = response_json.get("access_token") if not access_token: raise ValueError(f"Error in GitHub OAuth: {response_json}") @@ -67,55 +67,51 @@ class GitHubOAuth(OAuth): return access_token def get_raw_user_info(self, token: str): - headers = {'Authorization': f"token {token}"} + headers = {"Authorization": f"token {token}"} response = requests.get(self._USER_INFO_URL, headers=headers) response.raise_for_status() user_info = response.json() email_response = requests.get(self._EMAIL_INFO_URL, headers=headers) email_info = email_response.json() - primary_email = next((email for email in email_info if email['primary'] == True), None) + primary_email = next((email for email in email_info if email["primary"] == True), None) - return {**user_info, 'email': primary_email['email']} + return {**user_info, "email": primary_email["email"]} def _transform_user_info(self, raw_info: dict) -> OAuthUserInfo: - email = raw_info.get('email') + email = raw_info.get("email") if not email: email = f"{raw_info['id']}+{raw_info['login']}@users.noreply.github.com" - return OAuthUserInfo( - id=str(raw_info['id']), - name=raw_info['name'], - email=email - ) + return OAuthUserInfo(id=str(raw_info["id"]), name=raw_info["name"], email=email) class GoogleOAuth(OAuth): - _AUTH_URL = 'https://accounts.google.com/o/oauth2/v2/auth' - _TOKEN_URL = 'https://oauth2.googleapis.com/token' - _USER_INFO_URL = 'https://www.googleapis.com/oauth2/v3/userinfo' + _AUTH_URL = "https://accounts.google.com/o/oauth2/v2/auth" + _TOKEN_URL = "https://oauth2.googleapis.com/token" + _USER_INFO_URL = "https://www.googleapis.com/oauth2/v3/userinfo" def get_authorization_url(self): params = { - 'client_id': self.client_id, - 'response_type': 'code', - 'redirect_uri': self.redirect_uri, - 'scope': 'openid email' + "client_id": self.client_id, + "response_type": "code", + "redirect_uri": self.redirect_uri, + "scope": "openid email", } return f"{self._AUTH_URL}?{urllib.parse.urlencode(params)}" def get_access_token(self, code: str): data = { - 'client_id': self.client_id, - 'client_secret': self.client_secret, - 'code': code, - 'grant_type': 'authorization_code', - 'redirect_uri': self.redirect_uri + "client_id": self.client_id, + "client_secret": self.client_secret, + "code": code, + "grant_type": "authorization_code", + "redirect_uri": self.redirect_uri, } - headers = {'Accept': 'application/json'} + headers = {"Accept": "application/json"} response = requests.post(self._TOKEN_URL, data=data, headers=headers) response_json = response.json() - access_token = response_json.get('access_token') + access_token = response_json.get("access_token") if not access_token: raise ValueError(f"Error in Google OAuth: {response_json}") @@ -123,16 +119,10 @@ class GoogleOAuth(OAuth): return access_token def get_raw_user_info(self, token: str): - headers = {'Authorization': f"Bearer {token}"} + headers = {"Authorization": f"Bearer {token}"} response = requests.get(self._USER_INFO_URL, headers=headers) response.raise_for_status() return response.json() def _transform_user_info(self, raw_info: dict) -> OAuthUserInfo: - return OAuthUserInfo( - id=str(raw_info['sub']), - name=None, - email=raw_info['email'] - ) - - + return OAuthUserInfo(id=str(raw_info["sub"]), name=None, email=raw_info["email"]) diff --git a/api/libs/oauth_data_source.py b/api/libs/oauth_data_source.py index 358858ceb1..6da1a6d39b 100644 --- a/api/libs/oauth_data_source.py +++ b/api/libs/oauth_data_source.py @@ -21,53 +21,49 @@ class OAuthDataSource: class NotionOAuth(OAuthDataSource): - _AUTH_URL = 'https://api.notion.com/v1/oauth/authorize' - _TOKEN_URL = 'https://api.notion.com/v1/oauth/token' + _AUTH_URL = "https://api.notion.com/v1/oauth/authorize" + _TOKEN_URL = "https://api.notion.com/v1/oauth/token" _NOTION_PAGE_SEARCH = "https://api.notion.com/v1/search" _NOTION_BLOCK_SEARCH = "https://api.notion.com/v1/blocks" _NOTION_BOT_USER = "https://api.notion.com/v1/users/me" def get_authorization_url(self): params = { - 'client_id': self.client_id, - 'response_type': 'code', - 'redirect_uri': self.redirect_uri, - 'owner': 'user' + "client_id": self.client_id, + "response_type": "code", + "redirect_uri": self.redirect_uri, + "owner": "user", } return f"{self._AUTH_URL}?{urllib.parse.urlencode(params)}" def get_access_token(self, code: str): - data = { - 'code': code, - 'grant_type': 'authorization_code', - 'redirect_uri': self.redirect_uri - } - headers = {'Accept': 'application/json'} + data = {"code": code, "grant_type": "authorization_code", "redirect_uri": self.redirect_uri} + headers = {"Accept": "application/json"} auth = (self.client_id, self.client_secret) response = requests.post(self._TOKEN_URL, data=data, auth=auth, headers=headers) response_json = response.json() - access_token = response_json.get('access_token') + access_token = response_json.get("access_token") if not access_token: raise ValueError(f"Error in Notion OAuth: {response_json}") - workspace_name = response_json.get('workspace_name') - workspace_icon = response_json.get('workspace_icon') - workspace_id = response_json.get('workspace_id') + workspace_name = response_json.get("workspace_name") + workspace_icon = response_json.get("workspace_icon") + workspace_id = response_json.get("workspace_id") # get all authorized pages pages = self.get_authorized_pages(access_token) source_info = { - 'workspace_name': workspace_name, - 'workspace_icon': workspace_icon, - 'workspace_id': workspace_id, - 'pages': pages, - 'total': len(pages) + "workspace_name": workspace_name, + "workspace_icon": workspace_icon, + "workspace_id": workspace_id, + "pages": pages, + "total": len(pages), } # save data source binding data_source_binding = DataSourceOauthBinding.query.filter( db.and_( DataSourceOauthBinding.tenant_id == current_user.current_tenant_id, - DataSourceOauthBinding.provider == 'notion', - DataSourceOauthBinding.access_token == access_token + DataSourceOauthBinding.provider == "notion", + DataSourceOauthBinding.access_token == access_token, ) ).first() if data_source_binding: @@ -79,7 +75,7 @@ class NotionOAuth(OAuthDataSource): tenant_id=current_user.current_tenant_id, access_token=access_token, source_info=source_info, - provider='notion' + provider="notion", ) db.session.add(new_data_source_binding) db.session.commit() @@ -91,18 +87,18 @@ class NotionOAuth(OAuthDataSource): # get all authorized pages pages = self.get_authorized_pages(access_token) source_info = { - 'workspace_name': workspace_name, - 'workspace_icon': workspace_icon, - 'workspace_id': workspace_id, - 'pages': pages, - 'total': len(pages) + "workspace_name": workspace_name, + "workspace_icon": workspace_icon, + "workspace_id": workspace_id, + "pages": pages, + "total": len(pages), } # save data source binding data_source_binding = DataSourceOauthBinding.query.filter( db.and_( DataSourceOauthBinding.tenant_id == current_user.current_tenant_id, - DataSourceOauthBinding.provider == 'notion', - DataSourceOauthBinding.access_token == access_token + DataSourceOauthBinding.provider == "notion", + DataSourceOauthBinding.access_token == access_token, ) ).first() if data_source_binding: @@ -114,7 +110,7 @@ class NotionOAuth(OAuthDataSource): tenant_id=current_user.current_tenant_id, access_token=access_token, source_info=source_info, - provider='notion' + provider="notion", ) db.session.add(new_data_source_binding) db.session.commit() @@ -124,9 +120,9 @@ class NotionOAuth(OAuthDataSource): data_source_binding = DataSourceOauthBinding.query.filter( db.and_( DataSourceOauthBinding.tenant_id == current_user.current_tenant_id, - DataSourceOauthBinding.provider == 'notion', + DataSourceOauthBinding.provider == "notion", DataSourceOauthBinding.id == binding_id, - DataSourceOauthBinding.disabled == False + DataSourceOauthBinding.disabled == False, ) ).first() if data_source_binding: @@ -134,17 +130,17 @@ class NotionOAuth(OAuthDataSource): pages = self.get_authorized_pages(data_source_binding.access_token) source_info = data_source_binding.source_info new_source_info = { - 'workspace_name': source_info['workspace_name'], - 'workspace_icon': source_info['workspace_icon'], - 'workspace_id': source_info['workspace_id'], - 'pages': pages, - 'total': len(pages) + "workspace_name": source_info["workspace_name"], + "workspace_icon": source_info["workspace_icon"], + "workspace_id": source_info["workspace_id"], + "pages": pages, + "total": len(pages), } data_source_binding.source_info = new_source_info data_source_binding.disabled = False db.session.commit() else: - raise ValueError('Data source binding not found') + raise ValueError("Data source binding not found") def get_authorized_pages(self, access_token: str): pages = [] @@ -152,143 +148,121 @@ class NotionOAuth(OAuthDataSource): database_results = self.notion_database_search(access_token) # get page detail for page_result in page_results: - page_id = page_result['id'] - page_name = 'Untitled' - for key in page_result['properties']: - if 'title' in page_result['properties'][key] and page_result['properties'][key]['title']: - title_list = page_result['properties'][key]['title'] - if len(title_list) > 0 and 'plain_text' in title_list[0]: - page_name = title_list[0]['plain_text'] - page_icon = page_result['icon'] + page_id = page_result["id"] + page_name = "Untitled" + for key in page_result["properties"]: + if "title" in page_result["properties"][key] and page_result["properties"][key]["title"]: + title_list = page_result["properties"][key]["title"] + if len(title_list) > 0 and "plain_text" in title_list[0]: + page_name = title_list[0]["plain_text"] + page_icon = page_result["icon"] if page_icon: - icon_type = page_icon['type'] - if icon_type == 'external' or icon_type == 'file': - url = page_icon[icon_type]['url'] - icon = { - 'type': 'url', - 'url': url if url.startswith('http') else f'https://www.notion.so{url}' - } + icon_type = page_icon["type"] + if icon_type == "external" or icon_type == "file": + url = page_icon[icon_type]["url"] + icon = {"type": "url", "url": url if url.startswith("http") else f"https://www.notion.so{url}"} else: - icon = { - 'type': 'emoji', - 'emoji': page_icon[icon_type] - } + icon = {"type": "emoji", "emoji": page_icon[icon_type]} else: icon = None - parent = page_result['parent'] - parent_type = parent['type'] - if parent_type == 'block_id': + parent = page_result["parent"] + parent_type = parent["type"] + if parent_type == "block_id": parent_id = self.notion_block_parent_page_id(access_token, parent[parent_type]) - elif parent_type == 'workspace': - parent_id = 'root' + elif parent_type == "workspace": + parent_id = "root" else: parent_id = parent[parent_type] page = { - 'page_id': page_id, - 'page_name': page_name, - 'page_icon': icon, - 'parent_id': parent_id, - 'type': 'page' + "page_id": page_id, + "page_name": page_name, + "page_icon": icon, + "parent_id": parent_id, + "type": "page", } pages.append(page) # get database detail for database_result in database_results: - page_id = database_result['id'] - if len(database_result['title']) > 0: - page_name = database_result['title'][0]['plain_text'] + page_id = database_result["id"] + if len(database_result["title"]) > 0: + page_name = database_result["title"][0]["plain_text"] else: - page_name = 'Untitled' - page_icon = database_result['icon'] + page_name = "Untitled" + page_icon = database_result["icon"] if page_icon: - icon_type = page_icon['type'] - if icon_type == 'external' or icon_type == 'file': - url = page_icon[icon_type]['url'] - icon = { - 'type': 'url', - 'url': url if url.startswith('http') else f'https://www.notion.so{url}' - } + icon_type = page_icon["type"] + if icon_type == "external" or icon_type == "file": + url = page_icon[icon_type]["url"] + icon = {"type": "url", "url": url if url.startswith("http") else f"https://www.notion.so{url}"} else: - icon = { - 'type': icon_type, - icon_type: page_icon[icon_type] - } + icon = {"type": icon_type, icon_type: page_icon[icon_type]} else: icon = None - parent = database_result['parent'] - parent_type = parent['type'] - if parent_type == 'block_id': + parent = database_result["parent"] + parent_type = parent["type"] + if parent_type == "block_id": parent_id = self.notion_block_parent_page_id(access_token, parent[parent_type]) - elif parent_type == 'workspace': - parent_id = 'root' + elif parent_type == "workspace": + parent_id = "root" else: parent_id = parent[parent_type] page = { - 'page_id': page_id, - 'page_name': page_name, - 'page_icon': icon, - 'parent_id': parent_id, - 'type': 'database' + "page_id": page_id, + "page_name": page_name, + "page_icon": icon, + "parent_id": parent_id, + "type": "database", } pages.append(page) return pages def notion_page_search(self, access_token: str): - data = { - 'filter': { - "value": "page", - "property": "object" - } - } + data = {"filter": {"value": "page", "property": "object"}} headers = { - 'Content-Type': 'application/json', - 'Authorization': f"Bearer {access_token}", - 'Notion-Version': '2022-06-28', + "Content-Type": "application/json", + "Authorization": f"Bearer {access_token}", + "Notion-Version": "2022-06-28", } response = requests.post(url=self._NOTION_PAGE_SEARCH, json=data, headers=headers) response_json = response.json() - results = response_json.get('results', []) + results = response_json.get("results", []) return results def notion_block_parent_page_id(self, access_token: str, block_id: str): headers = { - 'Authorization': f"Bearer {access_token}", - 'Notion-Version': '2022-06-28', + "Authorization": f"Bearer {access_token}", + "Notion-Version": "2022-06-28", } - response = requests.get(url=f'{self._NOTION_BLOCK_SEARCH}/{block_id}', headers=headers) + response = requests.get(url=f"{self._NOTION_BLOCK_SEARCH}/{block_id}", headers=headers) response_json = response.json() - parent = response_json['parent'] - parent_type = parent['type'] - if parent_type == 'block_id': + parent = response_json["parent"] + parent_type = parent["type"] + if parent_type == "block_id": return self.notion_block_parent_page_id(access_token, parent[parent_type]) return parent[parent_type] def notion_workspace_name(self, access_token: str): headers = { - 'Authorization': f"Bearer {access_token}", - 'Notion-Version': '2022-06-28', + "Authorization": f"Bearer {access_token}", + "Notion-Version": "2022-06-28", } response = requests.get(url=self._NOTION_BOT_USER, headers=headers) response_json = response.json() - if 'object' in response_json and response_json['object'] == 'user': - user_type = response_json['type'] + if "object" in response_json and response_json["object"] == "user": + user_type = response_json["type"] user_info = response_json[user_type] - if 'workspace_name' in user_info: - return user_info['workspace_name'] - return 'workspace' + if "workspace_name" in user_info: + return user_info["workspace_name"] + return "workspace" def notion_database_search(self, access_token: str): - data = { - 'filter': { - "value": "database", - "property": "object" - } - } + data = {"filter": {"value": "database", "property": "object"}} headers = { - 'Content-Type': 'application/json', - 'Authorization': f"Bearer {access_token}", - 'Notion-Version': '2022-06-28', + "Content-Type": "application/json", + "Authorization": f"Bearer {access_token}", + "Notion-Version": "2022-06-28", } response = requests.post(url=self._NOTION_PAGE_SEARCH, json=data, headers=headers) response_json = response.json() - results = response_json.get('results', []) + results = response_json.get("results", []) return results diff --git a/api/libs/passport.py b/api/libs/passport.py index 34bdc55997..8df4f529bc 100644 --- a/api/libs/passport.py +++ b/api/libs/passport.py @@ -9,14 +9,14 @@ class PassportService: self.sk = dify_config.SECRET_KEY def issue(self, payload): - return jwt.encode(payload, self.sk, algorithm='HS256') + return jwt.encode(payload, self.sk, algorithm="HS256") def verify(self, token): try: - return jwt.decode(token, self.sk, algorithms=['HS256']) + return jwt.decode(token, self.sk, algorithms=["HS256"]) except jwt.exceptions.InvalidSignatureError: - raise Unauthorized('Invalid token signature.') + raise Unauthorized("Invalid token signature.") except jwt.exceptions.DecodeError: - raise Unauthorized('Invalid token.') + raise Unauthorized("Invalid token.") except jwt.exceptions.ExpiredSignatureError: - raise Unauthorized('Token has expired.') + raise Unauthorized("Token has expired.") diff --git a/api/libs/password.py b/api/libs/password.py index cdd1d69dbf..cfcc0db22d 100644 --- a/api/libs/password.py +++ b/api/libs/password.py @@ -5,6 +5,7 @@ import re password_pattern = r"^(?=.*[a-zA-Z])(?=.*\d).{8,}$" + def valid_password(password): # Define a regex pattern for password rules pattern = password_pattern @@ -12,11 +13,11 @@ def valid_password(password): if re.match(pattern, password) is not None: return password - raise ValueError('Not a valid password.') + raise ValueError("Not a valid password.") def hash_password(password_str, salt_byte): - dk = hashlib.pbkdf2_hmac('sha256', password_str.encode('utf-8'), salt_byte, 10000) + dk = hashlib.pbkdf2_hmac("sha256", password_str.encode("utf-8"), salt_byte, 10000) return binascii.hexlify(dk) diff --git a/api/libs/rsa.py b/api/libs/rsa.py index 9f29c58812..a578bf3e56 100644 --- a/api/libs/rsa.py +++ b/api/libs/rsa.py @@ -48,7 +48,7 @@ def encrypt(text, public_key): def get_decrypt_decoding(tenant_id): filepath = "privkeys/{tenant_id}".format(tenant_id=tenant_id) + "/private.pem" - cache_key = 'tenant_privkey:{hash}'.format(hash=hashlib.sha3_256(filepath.encode()).hexdigest()) + cache_key = "tenant_privkey:{hash}".format(hash=hashlib.sha3_256(filepath.encode()).hexdigest()) private_key = redis_client.get(cache_key) if not private_key: try: @@ -66,12 +66,12 @@ def get_decrypt_decoding(tenant_id): def decrypt_token_with_decoding(encrypted_text, rsa_key, cipher_rsa): if encrypted_text.startswith(prefix_hybrid): - encrypted_text = encrypted_text[len(prefix_hybrid):] + encrypted_text = encrypted_text[len(prefix_hybrid) :] - enc_aes_key = encrypted_text[:rsa_key.size_in_bytes()] - nonce = encrypted_text[rsa_key.size_in_bytes():rsa_key.size_in_bytes() + 16] - tag = encrypted_text[rsa_key.size_in_bytes() + 16:rsa_key.size_in_bytes() + 32] - ciphertext = encrypted_text[rsa_key.size_in_bytes() + 32:] + enc_aes_key = encrypted_text[: rsa_key.size_in_bytes()] + nonce = encrypted_text[rsa_key.size_in_bytes() : rsa_key.size_in_bytes() + 16] + tag = encrypted_text[rsa_key.size_in_bytes() + 16 : rsa_key.size_in_bytes() + 32] + ciphertext = encrypted_text[rsa_key.size_in_bytes() + 32 :] aes_key = cipher_rsa.decrypt(enc_aes_key) diff --git a/api/libs/smtp.py b/api/libs/smtp.py index bf3a1a92e9..bd7de7dd68 100644 --- a/api/libs/smtp.py +++ b/api/libs/smtp.py @@ -5,7 +5,9 @@ from email.mime.text import MIMEText class SMTPClient: - def __init__(self, server: str, port: int, username: str, password: str, _from: str, use_tls=False, opportunistic_tls=False): + def __init__( + self, server: str, port: int, username: str, password: str, _from: str, use_tls=False, opportunistic_tls=False + ): self.server = server self.port = port self._from = _from @@ -25,17 +27,17 @@ class SMTPClient: smtp = smtplib.SMTP_SSL(self.server, self.port, timeout=10) else: smtp = smtplib.SMTP(self.server, self.port, timeout=10) - + if self.username and self.password: smtp.login(self.username, self.password) msg = MIMEMultipart() - msg['Subject'] = mail['subject'] - msg['From'] = self._from - msg['To'] = mail['to'] - msg.attach(MIMEText(mail['html'], 'html')) + msg["Subject"] = mail["subject"] + msg["From"] = self._from + msg["To"] = mail["to"] + msg.attach(MIMEText(mail["html"], "html")) - smtp.sendmail(self._from, mail['to'], msg.as_string()) + smtp.sendmail(self._from, mail["to"], msg.as_string()) except smtplib.SMTPException as e: logging.error(f"SMTP error occurred: {str(e)}") raise diff --git a/api/migrations/versions/2024_08_14_1354-8782057ff0dc_add_conversations_dialogue_count.py b/api/migrations/versions/2024_08_14_1354-8782057ff0dc_add_conversations_dialogue_count.py new file mode 100644 index 0000000000..eba78e2e77 --- /dev/null +++ b/api/migrations/versions/2024_08_14_1354-8782057ff0dc_add_conversations_dialogue_count.py @@ -0,0 +1,33 @@ +"""add conversations.dialogue_count + +Revision ID: 8782057ff0dc +Revises: 63a83fcf12ba +Create Date: 2024-08-14 13:54:25.161324 + +""" +import sqlalchemy as sa +from alembic import op + +import models as models + +# revision identifiers, used by Alembic. +revision = '8782057ff0dc' +down_revision = '63a83fcf12ba' +branch_labels = None +depends_on = None + + +def upgrade(): + # ### commands auto generated by Alembic - please adjust! ### + with op.batch_alter_table('conversations', schema=None) as batch_op: + batch_op.add_column(sa.Column('dialogue_count', sa.Integer(), server_default='0', nullable=False)) + + # ### end Alembic commands ### + + +def downgrade(): + # ### commands auto generated by Alembic - please adjust! ### + with op.batch_alter_table('conversations', schema=None) as batch_op: + batch_op.drop_column('dialogue_count') + + # ### end Alembic commands ### diff --git a/api/models/__init__.py b/api/models/__init__.py index f831356841..4012611471 100644 --- a/api/models/__init__.py +++ b/api/models/__init__.py @@ -1,10 +1,10 @@ from enum import Enum -from .model import AppMode +from .model import App, AppMode, Message from .types import StringUUID -from .workflow import ConversationVariable, WorkflowNodeExecutionStatus +from .workflow import ConversationVariable, Workflow, WorkflowNodeExecutionStatus -__all__ = ['ConversationVariable', 'StringUUID', 'AppMode', 'WorkflowNodeExecutionStatus'] +__all__ = ['ConversationVariable', 'StringUUID', 'AppMode', 'WorkflowNodeExecutionStatus', 'Workflow', 'App', 'Message'] class CreatedByRole(Enum): diff --git a/api/models/model.py b/api/models/model.py index 9909b10dc0..5426d3bc83 100644 --- a/api/models/model.py +++ b/api/models/model.py @@ -7,6 +7,7 @@ from typing import Optional from flask import request from flask_login import UserMixin from sqlalchemy import Float, func, text +from sqlalchemy.orm import Mapped, mapped_column from configs import dify_config from core.file.tool_file_parser import ToolFileParser @@ -512,12 +513,12 @@ class Conversation(db.Model): from_account_id = db.Column(StringUUID) read_at = db.Column(db.DateTime) read_account_id = db.Column(StringUUID) + dialogue_count: Mapped[int] = mapped_column(default=0) created_at = db.Column(db.DateTime, nullable=False, server_default=db.text('CURRENT_TIMESTAMP(0)')) updated_at = db.Column(db.DateTime, nullable=False, server_default=db.text('CURRENT_TIMESTAMP(0)')) messages = db.relationship("Message", backref="conversation", lazy='select', passive_deletes="all") - message_annotations = db.relationship("MessageAnnotation", backref="conversation", lazy='select', - passive_deletes="all") + message_annotations = db.relationship("MessageAnnotation", backref="conversation", lazy='select', passive_deletes="all") is_deleted = db.Column(db.Boolean, nullable=False, server_default=db.text('false')) diff --git a/api/poetry.lock b/api/poetry.lock index 89d017f656..358f9f8510 100644 --- a/api/poetry.lock +++ b/api/poetry.lock @@ -2100,6 +2100,44 @@ primp = ">=0.5.5" dev = ["mypy (>=1.11.0)", "pytest (>=8.3.1)", "pytest-asyncio (>=0.23.8)", "ruff (>=0.5.5)"] lxml = ["lxml (>=5.2.2)"] +[[package]] +name = "elastic-transport" +version = "8.15.0" +description = "Transport classes and utilities shared among Python Elastic client libraries" +optional = false +python-versions = ">=3.8" +files = [ + {file = "elastic_transport-8.15.0-py3-none-any.whl", hash = "sha256:d7080d1dada2b4eee69e7574f9c17a76b42f2895eff428e562f94b0360e158c0"}, + {file = "elastic_transport-8.15.0.tar.gz", hash = "sha256:85d62558f9baafb0868c801233a59b235e61d7b4804c28c2fadaa866b6766233"}, +] + +[package.dependencies] +certifi = "*" +urllib3 = ">=1.26.2,<3" + +[package.extras] +develop = ["aiohttp", "furo", "httpx", "opentelemetry-api", "opentelemetry-sdk", "orjson", "pytest", "pytest-asyncio", "pytest-cov", "pytest-httpserver", "pytest-mock", "requests", "respx", "sphinx (>2)", "sphinx-autodoc-typehints", "trustme"] + +[[package]] +name = "elasticsearch" +version = "8.14.0" +description = "Python client for Elasticsearch" +optional = false +python-versions = ">=3.7" +files = [ + {file = "elasticsearch-8.14.0-py3-none-any.whl", hash = "sha256:cef8ef70a81af027f3da74a4f7d9296b390c636903088439087b8262a468c130"}, + {file = "elasticsearch-8.14.0.tar.gz", hash = "sha256:aa2490029dd96f4015b333c1827aa21fd6c0a4d223b00dfb0fe933b8d09a511b"}, +] + +[package.dependencies] +elastic-transport = ">=8.13,<9" + +[package.extras] +async = ["aiohttp (>=3,<4)"] +orjson = ["orjson (>=3)"] +requests = ["requests (>=2.4.0,!=2.32.2,<3.0.0)"] +vectorstore-mmr = ["numpy (>=1)", "simsimd (>=3)"] + [[package]] name = "emoji" version = "2.12.1" @@ -9546,4 +9584,4 @@ cffi = ["cffi (>=1.11)"] [metadata] lock-version = "2.0" python-versions = ">=3.10,<3.13" -content-hash = "2b822039247a445f72e04e967aef84f841781e2789b70071acad022f36ba26a5" +content-hash = "05dfa6b9bce9ed8ac21caf58eff1596f146080ab2ab6987924b189be673c22cf" diff --git a/api/pyproject.toml b/api/pyproject.toml index 058d67c42f..60c1c86d07 100644 --- a/api/pyproject.toml +++ b/api/pyproject.toml @@ -69,7 +69,16 @@ ignore = [ ] [tool.ruff.format] -quote-style = "single" +exclude = [ + "core/**/*.py", + "controllers/**/*.py", + "models/**/*.py", + "migrations/**/*", + "services/**/*.py", + "tasks/**/*.py", + "tests/**/*.py", + "configs/**/*.py", +] [tool.pytest_env] OPENAI_API_KEY = "sk-IamNotARealKeyJustForMockTestKawaiiiiiiiiii" @@ -181,6 +190,7 @@ zhipuai = "1.0.7" rank-bm25 = "~0.2.2" openpyxl = "^3.1.5" kaleido = "0.2.1" +elasticsearch = "8.14.0" ############################################################ # Tool dependencies required by tool implementations diff --git a/api/schedule/clean_embedding_cache_task.py b/api/schedule/clean_embedding_cache_task.py index ccc1062266..67d0706828 100644 --- a/api/schedule/clean_embedding_cache_task.py +++ b/api/schedule/clean_embedding_cache_task.py @@ -11,27 +11,32 @@ from extensions.ext_database import db from models.dataset import Embedding -@app.celery.task(queue='dataset') +@app.celery.task(queue="dataset") def clean_embedding_cache_task(): - click.echo(click.style('Start clean embedding cache.', fg='green')) + click.echo(click.style("Start clean embedding cache.", fg="green")) clean_days = int(dify_config.CLEAN_DAY_SETTING) start_at = time.perf_counter() thirty_days_ago = datetime.datetime.now() - datetime.timedelta(days=clean_days) while True: try: - embedding_ids = db.session.query(Embedding.id).filter(Embedding.created_at < thirty_days_ago) \ - .order_by(Embedding.created_at.desc()).limit(100).all() + embedding_ids = ( + db.session.query(Embedding.id) + .filter(Embedding.created_at < thirty_days_ago) + .order_by(Embedding.created_at.desc()) + .limit(100) + .all() + ) embedding_ids = [embedding_id[0] for embedding_id in embedding_ids] except NotFound: break if embedding_ids: for embedding_id in embedding_ids: - db.session.execute(text( - "DELETE FROM embeddings WHERE id = :embedding_id" - ), {'embedding_id': embedding_id}) + db.session.execute( + text("DELETE FROM embeddings WHERE id = :embedding_id"), {"embedding_id": embedding_id} + ) db.session.commit() else: break end_at = time.perf_counter() - click.echo(click.style('Cleaned embedding cache from db success latency: {}'.format(end_at - start_at), fg='green')) + click.echo(click.style("Cleaned embedding cache from db success latency: {}".format(end_at - start_at), fg="green")) diff --git a/api/schedule/clean_unused_datasets_task.py b/api/schedule/clean_unused_datasets_task.py index b2b2f82b78..3d799bfd4e 100644 --- a/api/schedule/clean_unused_datasets_task.py +++ b/api/schedule/clean_unused_datasets_task.py @@ -12,9 +12,9 @@ from extensions.ext_database import db from models.dataset import Dataset, DatasetQuery, Document -@app.celery.task(queue='dataset') +@app.celery.task(queue="dataset") def clean_unused_datasets_task(): - click.echo(click.style('Start clean unused datasets indexes.', fg='green')) + click.echo(click.style("Start clean unused datasets indexes.", fg="green")) clean_days = dify_config.CLEAN_DAY_SETTING start_at = time.perf_counter() thirty_days_ago = datetime.datetime.now() - datetime.timedelta(days=clean_days) @@ -22,40 +22,44 @@ def clean_unused_datasets_task(): while True: try: # Subquery for counting new documents - document_subquery_new = db.session.query( - Document.dataset_id, - func.count(Document.id).label('document_count') - ).filter( - Document.indexing_status == 'completed', - Document.enabled == True, - Document.archived == False, - Document.updated_at > thirty_days_ago - ).group_by(Document.dataset_id).subquery() + document_subquery_new = ( + db.session.query(Document.dataset_id, func.count(Document.id).label("document_count")) + .filter( + Document.indexing_status == "completed", + Document.enabled == True, + Document.archived == False, + Document.updated_at > thirty_days_ago, + ) + .group_by(Document.dataset_id) + .subquery() + ) # Subquery for counting old documents - document_subquery_old = db.session.query( - Document.dataset_id, - func.count(Document.id).label('document_count') - ).filter( - Document.indexing_status == 'completed', - Document.enabled == True, - Document.archived == False, - Document.updated_at < thirty_days_ago - ).group_by(Document.dataset_id).subquery() + document_subquery_old = ( + db.session.query(Document.dataset_id, func.count(Document.id).label("document_count")) + .filter( + Document.indexing_status == "completed", + Document.enabled == True, + Document.archived == False, + Document.updated_at < thirty_days_ago, + ) + .group_by(Document.dataset_id) + .subquery() + ) # Main query with join and filter - datasets = (db.session.query(Dataset) - .outerjoin( - document_subquery_new, Dataset.id == document_subquery_new.c.dataset_id - ).outerjoin( - document_subquery_old, Dataset.id == document_subquery_old.c.dataset_id - ).filter( - Dataset.created_at < thirty_days_ago, - func.coalesce(document_subquery_new.c.document_count, 0) == 0, - func.coalesce(document_subquery_old.c.document_count, 0) > 0 - ).order_by( - Dataset.created_at.desc() - ).paginate(page=page, per_page=50)) + datasets = ( + db.session.query(Dataset) + .outerjoin(document_subquery_new, Dataset.id == document_subquery_new.c.dataset_id) + .outerjoin(document_subquery_old, Dataset.id == document_subquery_old.c.dataset_id) + .filter( + Dataset.created_at < thirty_days_ago, + func.coalesce(document_subquery_new.c.document_count, 0) == 0, + func.coalesce(document_subquery_old.c.document_count, 0) > 0, + ) + .order_by(Dataset.created_at.desc()) + .paginate(page=page, per_page=50) + ) except NotFound: break @@ -63,10 +67,11 @@ def clean_unused_datasets_task(): break page += 1 for dataset in datasets: - dataset_query = db.session.query(DatasetQuery).filter( - DatasetQuery.created_at > thirty_days_ago, - DatasetQuery.dataset_id == dataset.id - ).all() + dataset_query = ( + db.session.query(DatasetQuery) + .filter(DatasetQuery.created_at > thirty_days_ago, DatasetQuery.dataset_id == dataset.id) + .all() + ) if not dataset_query or len(dataset_query) == 0: try: # remove index @@ -74,17 +79,14 @@ def clean_unused_datasets_task(): index_processor.clean(dataset, None) # update document - update_params = { - Document.enabled: False - } + update_params = {Document.enabled: False} Document.query.filter_by(dataset_id=dataset.id).update(update_params) db.session.commit() - click.echo(click.style('Cleaned unused dataset {} from db success!'.format(dataset.id), - fg='green')) + click.echo(click.style("Cleaned unused dataset {} from db success!".format(dataset.id), fg="green")) except Exception as e: click.echo( - click.style('clean dataset index error: {} {}'.format(e.__class__.__name__, str(e)), - fg='red')) + click.style("clean dataset index error: {} {}".format(e.__class__.__name__, str(e)), fg="red") + ) end_at = time.perf_counter() - click.echo(click.style('Cleaned unused dataset from db success latency: {}'.format(end_at - start_at), fg='green')) + click.echo(click.style("Cleaned unused dataset from db success latency: {}".format(end_at - start_at), fg="green")) diff --git a/api/services/app_dsl_service.py b/api/services/app_dsl_service.py index e16e5c715c..bfb160b3e4 100644 --- a/api/services/app_dsl_service.py +++ b/api/services/app_dsl_service.py @@ -13,9 +13,9 @@ from services.workflow_service import WorkflowService logger = logging.getLogger(__name__) -current_dsl_version = "0.1.0" +current_dsl_version = "0.1.1" dsl_to_dify_version_mapping: dict[str, str] = { - "0.1.0": "0.6.0", # dsl version -> from dify version + "0.1.1": "0.6.0", # dsl version -> from dify version } @@ -285,6 +285,8 @@ class AppDslService: # sync draft workflow environment_variables_list = workflow_data.get('environment_variables') or [] environment_variables = [factory.build_variable_from_mapping(obj) for obj in environment_variables_list] + conversation_variables_list = workflow_data.get('conversation_variables') or [] + conversation_variables = [factory.build_variable_from_mapping(obj) for obj in conversation_variables_list] draft_workflow = workflow_service.sync_draft_workflow( app_model=app_model, graph=workflow_data.get('graph', {}), @@ -292,6 +294,7 @@ class AppDslService: unique_hash=unique_hash, account=account, environment_variables=environment_variables, + conversation_variables=conversation_variables, ) return draft_workflow diff --git a/api/tests/integration_tests/model_runtime/__mock/huggingface_tei.py b/api/tests/integration_tests/model_runtime/__mock/huggingface_tei.py index 2f66d707ca..c2fe95974b 100644 --- a/api/tests/integration_tests/model_runtime/__mock/huggingface_tei.py +++ b/api/tests/integration_tests/model_runtime/__mock/huggingface_tei.py @@ -1,5 +1,4 @@ - -from api.core.model_runtime.model_providers.huggingface_tei.tei_helper import TeiModelExtraParameter +from core.model_runtime.model_providers.huggingface_tei.tei_helper import TeiModelExtraParameter class MockTEIClass: @@ -12,7 +11,7 @@ class MockTEIClass: model_type = 'embedding' return TeiModelExtraParameter(model_type=model_type, max_input_length=512, max_client_batch_size=1) - + @staticmethod def invoke_tokenize(server_url: str, texts: list[str]) -> list[list[dict]]: # Use space as token separator, and split the text into tokens diff --git a/api/tests/integration_tests/model_runtime/huggingface_tei/test_embeddings.py b/api/tests/integration_tests/model_runtime/huggingface_tei/test_embeddings.py index da65c7dfc7..ed371fbc07 100644 --- a/api/tests/integration_tests/model_runtime/huggingface_tei/test_embeddings.py +++ b/api/tests/integration_tests/model_runtime/huggingface_tei/test_embeddings.py @@ -1,12 +1,12 @@ import os import pytest -from api.core.model_runtime.model_providers.huggingface_tei.text_embedding.text_embedding import TeiHelper from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult from core.model_runtime.errors.validate import CredentialsValidateFailedError from core.model_runtime.model_providers.huggingface_tei.text_embedding.text_embedding import ( HuggingfaceTeiTextEmbeddingModel, + TeiHelper, ) from tests.integration_tests.model_runtime.__mock.huggingface_tei import MockTEIClass diff --git a/api/tests/integration_tests/vdb/elasticsearch/__init__.py b/api/tests/integration_tests/vdb/elasticsearch/__init__.py new file mode 100644 index 0000000000..e69de29bb2 diff --git a/api/tests/integration_tests/vdb/elasticsearch/test_elasticsearch.py b/api/tests/integration_tests/vdb/elasticsearch/test_elasticsearch.py new file mode 100644 index 0000000000..b1c1cc10d9 --- /dev/null +++ b/api/tests/integration_tests/vdb/elasticsearch/test_elasticsearch.py @@ -0,0 +1,25 @@ +from core.rag.datasource.vdb.elasticsearch.elasticsearch_vector import ElasticSearchConfig, ElasticSearchVector +from tests.integration_tests.vdb.test_vector_store import ( + AbstractVectorTest, + setup_mock_redis, +) + + +class ElasticSearchVectorTest(AbstractVectorTest): + def __init__(self): + super().__init__() + self.attributes = ['doc_id', 'dataset_id', 'document_id', 'doc_hash'] + self.vector = ElasticSearchVector( + index_name=self.collection_name.lower(), + config=ElasticSearchConfig( + host='http://localhost', + port='9200', + username='elastic', + password='elastic' + ), + attributes=self.attributes + ) + + +def test_elasticsearch_vector(setup_mock_redis): + ElasticSearchVectorTest().run_all_tests() diff --git a/api/tests/integration_tests/workflow/nodes/test_llm.py b/api/tests/integration_tests/workflow/nodes/test_llm.py index c5b17083c5..95965fcefb 100644 --- a/api/tests/integration_tests/workflow/nodes/test_llm.py +++ b/api/tests/integration_tests/workflow/nodes/test_llm.py @@ -235,4 +235,4 @@ def test_execute_llm_with_jinja2(setup_code_executor_mock, setup_openai_mock): assert result.status == WorkflowNodeExecutionStatus.SUCCEEDED assert 'sunny' in json.dumps(result.process_data) - assert 'what\'s the weather today?' in json.dumps(result.process_data) \ No newline at end of file + assert 'what\'s the weather today?' in json.dumps(result.process_data) diff --git a/api/tests/integration_tests/workflow/nodes/test_parameter_extractor.py b/api/tests/integration_tests/workflow/nodes/test_parameter_extractor.py index fddcacdf54..2261f7debb 100644 --- a/api/tests/integration_tests/workflow/nodes/test_parameter_extractor.py +++ b/api/tests/integration_tests/workflow/nodes/test_parameter_extractor.py @@ -362,7 +362,7 @@ def test_extract_json_response(): { "location": "kawaii" } - hello world. + hello world. """) assert result['location'] == 'kawaii' @@ -444,4 +444,4 @@ def test_chat_parameter_extractor_with_memory(setup_anthropic_mock): assert latest_role != prompt.get('role') if prompt.get('role') in ['user', 'assistant']: - latest_role = prompt.get('role') \ No newline at end of file + latest_role = prompt.get('role') diff --git a/api/tests/unit_tests/core/app/segments/test_factory.py b/api/tests/unit_tests/core/app/segments/test_factory.py index a8429b9c1b..afd0fa50b5 100644 --- a/api/tests/unit_tests/core/app/segments/test_factory.py +++ b/api/tests/unit_tests/core/app/segments/test_factory.py @@ -3,12 +3,9 @@ from uuid import uuid4 import pytest from core.app.segments import ( - ArrayFileVariable, ArrayNumberVariable, ArrayObjectVariable, ArrayStringVariable, - FileSegment, - FileVariable, FloatVariable, IntegerVariable, ObjectSegment, @@ -149,83 +146,6 @@ def test_array_object_variable(): assert isinstance(variable.value[1]['key2'], int) -def test_file_variable(): - mapping = { - 'id': str(uuid4()), - 'value_type': 'file', - 'name': 'test_file', - 'description': 'Description of the variable.', - 'value': { - 'id': str(uuid4()), - 'tenant_id': 'tenant_id', - 'type': 'image', - 'transfer_method': 'local_file', - 'url': 'url', - 'related_id': 'related_id', - 'extra_config': { - 'image_config': { - 'width': 100, - 'height': 100, - }, - }, - 'filename': 'filename', - 'extension': 'extension', - 'mime_type': 'mime_type', - }, - } - variable = factory.build_variable_from_mapping(mapping) - assert isinstance(variable, FileVariable) - - -def test_array_file_variable(): - mapping = { - 'id': str(uuid4()), - 'value_type': 'array[file]', - 'name': 'test_array_file', - 'description': 'Description of the variable.', - 'value': [ - { - 'id': str(uuid4()), - 'tenant_id': 'tenant_id', - 'type': 'image', - 'transfer_method': 'local_file', - 'url': 'url', - 'related_id': 'related_id', - 'extra_config': { - 'image_config': { - 'width': 100, - 'height': 100, - }, - }, - 'filename': 'filename', - 'extension': 'extension', - 'mime_type': 'mime_type', - }, - { - 'id': str(uuid4()), - 'tenant_id': 'tenant_id', - 'type': 'image', - 'transfer_method': 'local_file', - 'url': 'url', - 'related_id': 'related_id', - 'extra_config': { - 'image_config': { - 'width': 100, - 'height': 100, - }, - }, - 'filename': 'filename', - 'extension': 'extension', - 'mime_type': 'mime_type', - }, - ], - } - variable = factory.build_variable_from_mapping(mapping) - assert isinstance(variable, ArrayFileVariable) - assert isinstance(variable.value[0], FileSegment) - assert isinstance(variable.value[1], FileSegment) - - def test_variable_cannot_large_than_5_kb(): with pytest.raises(VariableError): factory.build_variable_from_mapping( diff --git a/api/tests/unit_tests/core/app/segments/test_segment.py b/api/tests/unit_tests/core/app/segments/test_segment.py index 414404b7d0..7e3e69ffbf 100644 --- a/api/tests/unit_tests/core/app/segments/test_segment.py +++ b/api/tests/unit_tests/core/app/segments/test_segment.py @@ -1,7 +1,7 @@ from core.app.segments import SecretVariable, StringSegment, parser from core.helper import encrypter -from core.workflow.entities.node_entities import SystemVariable from core.workflow.entities.variable_pool import VariablePool +from core.workflow.enums import SystemVariable def test_segment_group_to_text(): diff --git a/api/tests/unit_tests/core/workflow/nodes/test_answer.py b/api/tests/unit_tests/core/workflow/nodes/test_answer.py new file mode 100644 index 0000000000..4617b6a42f --- /dev/null +++ b/api/tests/unit_tests/core/workflow/nodes/test_answer.py @@ -0,0 +1,45 @@ +from unittest.mock import MagicMock + +from core.app.entities.app_invoke_entities import InvokeFrom +from core.workflow.entities.variable_pool import VariablePool +from core.workflow.enums import SystemVariable +from core.workflow.nodes.answer.answer_node import AnswerNode +from core.workflow.nodes.base_node import UserFrom +from extensions.ext_database import db +from models.workflow import WorkflowNodeExecutionStatus + + +def test_execute_answer(): + node = AnswerNode( + tenant_id='1', + app_id='1', + workflow_id='1', + user_id='1', + user_from=UserFrom.ACCOUNT, + invoke_from=InvokeFrom.DEBUGGER, + config={ + 'id': 'answer', + 'data': { + 'title': '123', + 'type': 'answer', + 'answer': 'Today\'s weather is {{#start.weather#}}\n{{#llm.text#}}\n{{img}}\nFin.' + } + } + ) + + # construct variable pool + pool = VariablePool(system_variables={ + SystemVariable.FILES: [], + SystemVariable.USER_ID: 'aaa' + }, user_inputs={}, environment_variables=[]) + pool.add(['start', 'weather'], 'sunny') + pool.add(['llm', 'text'], 'You are a helpful AI.') + + # Mock db.session.close() + db.session.close = MagicMock() + + # execute node + result = node._run(pool) + + assert result.status == WorkflowNodeExecutionStatus.SUCCEEDED + assert result.outputs['answer'] == "Today's weather is sunny\nYou are a helpful AI.\n{{img}}\nFin." diff --git a/dev/pytest/pytest_vdb.sh b/dev/pytest/pytest_vdb.sh index c954c528fb..0b23200dc3 100755 --- a/dev/pytest/pytest_vdb.sh +++ b/dev/pytest/pytest_vdb.sh @@ -7,4 +7,5 @@ pytest api/tests/integration_tests/vdb/chroma \ api/tests/integration_tests/vdb/pgvector \ api/tests/integration_tests/vdb/qdrant \ api/tests/integration_tests/vdb/weaviate \ + api/tests/integration_tests/vdb/elasticsearch \ api/tests/integration_tests/vdb/test_vector_store.py \ No newline at end of file diff --git a/dev/reformat b/dev/reformat index f50ccb04c4..ad83e897d9 100755 --- a/dev/reformat +++ b/dev/reformat @@ -11,5 +11,8 @@ fi # run ruff linter ruff check --fix ./api +# run ruff formatter +ruff format ./api + # run dotenv-linter linter dotenv-linter ./api/.env.example ./web/.env.example diff --git a/docker-legacy/docker-compose.yaml b/docker-legacy/docker-compose.yaml index 807946f3fe..aed2586053 100644 --- a/docker-legacy/docker-compose.yaml +++ b/docker-legacy/docker-compose.yaml @@ -2,7 +2,7 @@ version: '3' services: # API service api: - image: langgenius/dify-api:0.6.16 + image: langgenius/dify-api:0.7.0 restart: always environment: # Startup mode, 'api' starts the API server. @@ -169,6 +169,11 @@ services: CHROMA_DATABASE: default_database CHROMA_AUTH_PROVIDER: chromadb.auth.token_authn.TokenAuthClientProvider CHROMA_AUTH_CREDENTIALS: xxxxxx + # ElasticSearch Config + ELASTICSEARCH_HOST: 127.0.0.1 + ELASTICSEARCH_PORT: 9200 + ELASTICSEARCH_USERNAME: elastic + ELASTICSEARCH_PASSWORD: elastic # Mail configuration, support: resend, smtp MAIL_TYPE: '' # default send from email address, if not specified @@ -224,7 +229,7 @@ services: # worker service # The Celery worker for processing the queue. worker: - image: langgenius/dify-api:0.6.16 + image: langgenius/dify-api:0.7.0 restart: always environment: CONSOLE_WEB_URL: '' @@ -371,6 +376,11 @@ services: CHROMA_DATABASE: default_database CHROMA_AUTH_PROVIDER: chromadb.auth.token_authn.TokenAuthClientProvider CHROMA_AUTH_CREDENTIALS: xxxxxx + # ElasticSearch Config + ELASTICSEARCH_HOST: 127.0.0.1 + ELASTICSEARCH_PORT: 9200 + ELASTICSEARCH_USERNAME: elastic + ELASTICSEARCH_PASSWORD: elastic # Notion import configuration, support public and internal NOTION_INTEGRATION_TYPE: public NOTION_CLIENT_SECRET: you-client-secret @@ -390,7 +400,7 @@ services: # Frontend web application. web: - image: langgenius/dify-web:0.6.16 + image: langgenius/dify-web:0.7.0 restart: always environment: # The base URL of console application api server, refers to the Console base URL of WEB service if console domain is diff --git a/docker/.env.example b/docker/.env.example index 6fee8b4b3c..03e1e4e50e 100644 --- a/docker/.env.example +++ b/docker/.env.example @@ -303,7 +303,7 @@ TENCENT_COS_SCHEME=your-scheme # ------------------------------ # The type of vector store to use. -# Supported values are `weaviate`, `qdrant`, `milvus`, `myscale`, `relyt`, `pgvector`, `chroma`, `opensearch`, `tidb_vector`, `oracle`, `tencent`. +# Supported values are `weaviate`, `qdrant`, `milvus`, `myscale`, `relyt`, `pgvector`, `chroma`, `opensearch`, `tidb_vector`, `oracle`, `tencent`, `elasticsearch`. VECTOR_STORE=weaviate # The Weaviate endpoint URL. Only available when VECTOR_STORE is `weaviate`. @@ -396,6 +396,12 @@ TENCENT_VECTOR_DB_DATABASE=dify TENCENT_VECTOR_DB_SHARD=1 TENCENT_VECTOR_DB_REPLICAS=2 +# ElasticSearch configuration, only available when VECTOR_STORE is `elasticsearch` +ELASTICSEARCH_HOST=0.0.0.0 +ELASTICSEARCH_PORT=9200 +ELASTICSEARCH_USERNAME=elastic +ELASTICSEARCH_PASSWORD=elastic + # ------------------------------ # Knowledge Configuration # ------------------------------ diff --git a/docker/docker-compose.yaml b/docker/docker-compose.yaml index 2b10fbc2cc..fc50cea920 100644 --- a/docker/docker-compose.yaml +++ b/docker/docker-compose.yaml @@ -35,11 +35,6 @@ x-shared-env: &shared-api-worker-env SQLALCHEMY_POOL_SIZE: ${SQLALCHEMY_POOL_SIZE:-30} SQLALCHEMY_POOL_RECYCLE: ${SQLALCHEMY_POOL_RECYCLE:-3600} SQLALCHEMY_ECHO: ${SQLALCHEMY_ECHO:-false} - POSTGRES_MAX_CONNECTIONS: ${POSTGRES_MAX_CONNECTIONS:-100} - POSTGRES_SHARED_BUFFERS: ${POSTGRES_SHARED_BUFFERS:-128MB} - POSTGRES_WORK_MEM: ${POSTGRES_WORK_MEM:-4MB} - POSTGRES_MAINTENANCE_WORK_MEM: ${POSTGRES_MAINTENANCE_WORK_MEM:-64MB} - POSTGRES_EFFECTIVE_CACHE_SIZE: ${POSTGRES_EFFECTIVE_CACHE_SIZE:-4096MB} REDIS_HOST: ${REDIS_HOST:-redis} REDIS_PORT: ${REDIS_PORT:-6379} REDIS_USERNAME: ${REDIS_USERNAME:-} @@ -125,6 +120,11 @@ x-shared-env: &shared-api-worker-env CHROMA_DATABASE: ${CHROMA_DATABASE:-default_database} CHROMA_AUTH_PROVIDER: ${CHROMA_AUTH_PROVIDER:-chromadb.auth.token_authn.TokenAuthClientProvider} CHROMA_AUTH_CREDENTIALS: ${CHROMA_AUTH_CREDENTIALS:-} + ELASTICSEARCH_HOST: ${ELASTICSEARCH_HOST:-0.0.0.0} + ELASTICSEARCH_PORT: ${ELASTICSEARCH_PORT:-9200} + ELASTICSEARCH_USERNAME: ${ELASTICSEARCH_USERNAME:-elastic} + ELASTICSEARCH_PASSWORD: ${ELASTICSEARCH_PASSWORD:-elastic} + KIBANA_PORT: ${KIBANA_PORT:-5601} # AnalyticDB configuration ANALYTICDB_KEY_ID: ${ANALYTICDB_KEY_ID:-} ANALYTICDB_KEY_SECRET: ${ANALYTICDB_KEY_SECRET:-} @@ -187,7 +187,7 @@ x-shared-env: &shared-api-worker-env services: # API service api: - image: langgenius/dify-api:0.6.16 + image: langgenius/dify-api:0.7.0 restart: always environment: # Use the shared environment variables. @@ -207,7 +207,7 @@ services: # worker service # The Celery worker for processing the queue. worker: - image: langgenius/dify-api:0.6.16 + image: langgenius/dify-api:0.7.0 restart: always environment: # Use the shared environment variables. @@ -226,7 +226,7 @@ services: # Frontend web application. web: - image: langgenius/dify-web:0.6.16 + image: langgenius/dify-web:0.7.0 restart: always environment: CONSOLE_API_URL: ${CONSOLE_API_URL:-} @@ -583,7 +583,7 @@ services: # MyScale vector database myscale: container_name: myscale - image: myscale/myscaledb:1.6 + image: myscale/myscaledb:1.6.4 profiles: - myscale restart: always @@ -595,6 +595,61 @@ services: ports: - "${MYSCALE_PORT:-8123}:${MYSCALE_PORT:-8123}" + # https://www.elastic.co/guide/en/elasticsearch/reference/current/settings.html + # https://www.elastic.co/guide/en/elasticsearch/reference/current/docker.html#docker-prod-prerequisites + elasticsearch: + image: docker.elastic.co/elasticsearch/elasticsearch:8.14.3 + container_name: elasticsearch + profiles: + - elasticsearch + restart: always + volumes: + - dify_es01_data:/usr/share/elasticsearch/data + environment: + - ELASTIC_PASSWORD=${ELASTICSEARCH_PASSWORD:-elastic} + - cluster.name=dify-es-cluster + - node.name=dify-es0 + - discovery.type=single-node + - xpack.license.self_generated.type=trial + - xpack.security.enabled=true + - xpack.security.enrollment.enabled=false + - xpack.security.http.ssl.enabled=false + ports: + - ${ELASTICSEARCH_PORT:-9200}:9200 + healthcheck: + test: ["CMD", "curl", "-s", "http://localhost:9200/_cluster/health?pretty"] + interval: 30s + timeout: 10s + retries: 50 + + # https://www.elastic.co/guide/en/kibana/current/docker.html + # https://www.elastic.co/guide/en/kibana/current/settings.html + kibana: + image: docker.elastic.co/kibana/kibana:8.14.3 + container_name: kibana + profiles: + - elasticsearch + depends_on: + - elasticsearch + restart: always + environment: + - XPACK_ENCRYPTEDSAVEDOBJECTS_ENCRYPTIONKEY=d1a66dfd-c4d3-4a0a-8290-2abcb83ab3aa + - NO_PROXY=localhost,127.0.0.1,elasticsearch,kibana + - XPACK_SECURITY_ENABLED=true + - XPACK_SECURITY_ENROLLMENT_ENABLED=false + - XPACK_SECURITY_HTTP_SSL_ENABLED=false + - XPACK_FLEET_ISAIRGAPPED=true + - I18N_LOCALE=zh-CN + - SERVER_PORT=5601 + - ELASTICSEARCH_HOSTS="http://elasticsearch:9200" + ports: + - ${KIBANA_PORT:-5601}:5601 + healthcheck: + test: [ "CMD-SHELL", "curl -s http://localhost:5601 >/dev/null || exit 1" ] + interval: 30s + timeout: 10s + retries: 3 + # unstructured . # (if used, you need to set ETL_TYPE to Unstructured in the api & worker service.) unstructured: @@ -618,3 +673,4 @@ networks: volumes: oradata: + dify_es01_data: diff --git a/sdks/php-client/dify-client.php b/sdks/php-client/dify-client.php index c5ddcc3a87..69208de7ed 100644 --- a/sdks/php-client/dify-client.php +++ b/sdks/php-client/dify-client.php @@ -9,9 +9,9 @@ class DifyClient { protected $base_url; protected $client; - public function __construct($api_key) { + public function __construct($api_key, $base_url = null) { $this->api_key = $api_key; - $this->base_url = "https://api.dify.ai/v1/"; + $this->base_url = $base_url ?? "https://api.dify.ai/v1/"; $this->client = new Client([ 'base_uri' => $this->base_url, 'headers' => [ @@ -80,6 +80,25 @@ class DifyClient { return $multipart; } + + + public function text_to_audio($text, $user, $streaming = false) { + $data = [ + 'text' => $text, + 'user' => $user, + 'streaming' => $streaming + ]; + + return $this->send_request('POST', 'text-to-audio', $data); + } + + public function get_meta($user) { + $params = [ + 'user' => $user + ]; + + return $this->send_request('GET', 'meta',null, $params); + } } class CompletionClient extends DifyClient { @@ -126,6 +145,16 @@ class ChatClient extends DifyClient { return $this->send_request('GET', 'messages', null, $params); } + + public function stop_message($task_id, $user) { + $data = ['user' => $user]; + return $this->send_request('POST', "chat-messages/{$task_id}/stop", $data); + } + + + + + public function get_conversations($user, $first_id = null, $limit = null, $pinned = null) { $params = [ 'user' => $user, @@ -143,4 +172,23 @@ class ChatClient extends DifyClient { ]; return $this->send_request('PATCH', "conversations/{$conversation_id}", $data); } + + public function audio_to_text($audio_file, $user) { + $data = [ + 'user' => $user, + ]; + $options = [ + 'multipart' => $this->prepareMultipart($data, $files) + ]; + return $this->file_client->request('POST', 'audio-to-text', $options); + + } + + + public function get_suggestions($message_id, $user) { + $params = [ + 'user' => $user + ] + return $this->send_request('GET', "messages/{$message_id}/suggested", null, $params); + } } diff --git a/sdks/python-client/dify_client/client.py b/sdks/python-client/dify_client/client.py index 22d4e6189a..c8cf197723 100644 --- a/sdks/python-client/dify_client/client.py +++ b/sdks/python-client/dify_client/client.py @@ -43,6 +43,18 @@ class DifyClient: "user": user } return self._send_request_with_files("POST", "/files/upload", data=data, files=files) + + def text_to_audio(self, text:str, user:str, streaming:bool=False): + data = { + "text": text, + "user": user, + "streaming": streaming + } + return self._send_request("POST", "/text-to-audio", data=data) + + def get_meta(self,user): + params = { "user": user} + return self._send_request("GET", f"/meta", params=params) class CompletionClient(DifyClient): @@ -71,6 +83,12 @@ class ChatClient(DifyClient): return self._send_request("POST", "/chat-messages", data, stream=True if response_mode == "streaming" else False) + def stop_message(self, task_id, user): + data = {"user": user} + return self._send_request("POST", f"/chat-messages/{task_id}/stop", data) + + + def get_conversation_messages(self, user, conversation_id=None, first_id=None, limit=None): params = {"user": user} @@ -91,3 +109,14 @@ class ChatClient(DifyClient): def rename_conversation(self, conversation_id, name, user): data = {"name": name, "user": user} return self._send_request("POST", f"/conversations/{conversation_id}/name", data) + + def audio_to_text(self, audio_file, user): + data = {"user": user} + files = {"audio_file": audio_file} + return self._send_request_with_files("POST", "/audio-to-text", data, files) + + + def get_suggested(self, message_id, user:str): + params = {"user": user} + return self._send_request("GET", f"/messages/{message_id}/suggested", params=params) + diff --git a/web/app/(commonLayout)/datasets/template/template.en.mdx b/web/app/(commonLayout)/datasets/template/template.en.mdx index 36395d391d..44c5964d77 100644 --- a/web/app/(commonLayout)/datasets/template/template.en.mdx +++ b/web/app/(commonLayout)/datasets/template/template.en.mdx @@ -922,6 +922,9 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from Knowledge ID + + Document ID + Document Segment ID @@ -965,6 +968,9 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from Knowledge ID + + Document ID + Document Segment ID diff --git a/web/app/(commonLayout)/datasets/template/template.zh.mdx b/web/app/(commonLayout)/datasets/template/template.zh.mdx index a624c0594f..9f79b0f900 100644 --- a/web/app/(commonLayout)/datasets/template/template.zh.mdx +++ b/web/app/(commonLayout)/datasets/template/template.zh.mdx @@ -922,6 +922,9 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from 知识库 ID + + 文档 ID + 文档分段ID @@ -965,6 +968,9 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from 知识库 ID + + 文档 ID + 文档分段ID diff --git a/web/app/components/base/chat/chat/chat-input.tsx b/web/app/components/base/chat/chat/chat-input.tsx index 6d15010f85..fcf9b2c23f 100644 --- a/web/app/components/base/chat/chat/chat-input.tsx +++ b/web/app/components/base/chat/chat/chat-input.tsx @@ -49,6 +49,7 @@ const ChatInput: FC = ({ const { t } = useTranslation() const { notify } = useContext(ToastContext) const [voiceInputShow, setVoiceInputShow] = useState(false) + const textAreaRef = useRef(null) const { files, onUpload, @@ -176,6 +177,7 @@ const ChatInput: FC = ({ ) }