Yeuoly 403e2d58b9
Introduce Plugins (#13836)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Signed-off-by: -LAN- <laipz8200@outlook.com>
Signed-off-by: xhe <xw897002528@gmail.com>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: takatost <takatost@gmail.com>
Co-authored-by: kurokobo <kuro664@gmail.com>
Co-authored-by: Novice Lee <novicelee@NoviPro.local>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: AkaraChen <akarachen@outlook.com>
Co-authored-by: Yi <yxiaoisme@gmail.com>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: JzoNg <jzongcode@gmail.com>
Co-authored-by: twwu <twwu@dify.ai>
Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com>
Co-authored-by: AkaraChen <85140972+AkaraChen@users.noreply.github.com>
Co-authored-by: NFish <douxc512@gmail.com>
Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com>
Co-authored-by: 非法操作 <hjlarry@163.com>
Co-authored-by: Novice <857526207@qq.com>
Co-authored-by: Hiroki Nagai <82458324+nagaihiroki-git@users.noreply.github.com>
Co-authored-by: Gen Sato <52241300+halogen22@users.noreply.github.com>
Co-authored-by: eux <euxuuu@gmail.com>
Co-authored-by: huangzhuo1949 <167434202+huangzhuo1949@users.noreply.github.com>
Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com>
Co-authored-by: lotsik <lotsik@mail.ru>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: nite-knite <nkCoding@gmail.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: gakkiyomi <gakkiyomi@aliyun.com>
Co-authored-by: CN-P5 <heibai2006@gmail.com>
Co-authored-by: CN-P5 <heibai2006@qq.com>
Co-authored-by: Chuehnone <1897025+chuehnone@users.noreply.github.com>
Co-authored-by: yihong <zouzou0208@gmail.com>
Co-authored-by: Kevin9703 <51311316+Kevin9703@users.noreply.github.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: Boris Feld <lothiraldan@gmail.com>
Co-authored-by: mbo <himabo@gmail.com>
Co-authored-by: mabo <mabo@aeyes.ai>
Co-authored-by: Warren Chen <warren.chen830@gmail.com>
Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com>
Co-authored-by: jiandanfeng <chenjh3@wangsu.com>
Co-authored-by: zhu-an <70234959+xhdd123321@users.noreply.github.com>
Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com>
Co-authored-by: 海狸大師 <86974027+yenslife@users.noreply.github.com>
Co-authored-by: Xu Song <xusong.vip@gmail.com>
Co-authored-by: rayshaw001 <396301947@163.com>
Co-authored-by: Ding Jiatong <dingjiatong@gmail.com>
Co-authored-by: Bowen Liang <liangbowen@gf.com.cn>
Co-authored-by: JasonVV <jasonwangiii@outlook.com>
Co-authored-by: le0zh <newlight@qq.com>
Co-authored-by: zhuxinliang <zhuxinliang@didiglobal.com>
Co-authored-by: k-zaku <zaku99@outlook.jp>
Co-authored-by: luckylhb90 <luckylhb90@gmail.com>
Co-authored-by: hobo.l <hobo.l@binance.com>
Co-authored-by: jiangbo721 <365065261@qq.com>
Co-authored-by: 刘江波 <jiangbo721@163.com>
Co-authored-by: Shun Miyazawa <34241526+miya@users.noreply.github.com>
Co-authored-by: EricPan <30651140+Egfly@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: sino <sino2322@gmail.com>
Co-authored-by: Jhvcc <37662342+Jhvcc@users.noreply.github.com>
Co-authored-by: lowell <lowell.hu@zkteco.in>
Co-authored-by: Boris Polonsky <BorisPolonsky@users.noreply.github.com>
Co-authored-by: Ademílson Tonato <ademilsonft@outlook.com>
Co-authored-by: Ademílson Tonato <ademilson.tonato@refurbed.com>
Co-authored-by: IWAI, Masaharu <iwaim.sub@gmail.com>
Co-authored-by: Yueh-Po Peng (Yabi) <94939112+y10ab1@users.noreply.github.com>
Co-authored-by: Jason <ggbbddjm@gmail.com>
Co-authored-by: Xin Zhang <sjhpzx@gmail.com>
Co-authored-by: yjc980121 <3898524+yjc980121@users.noreply.github.com>
Co-authored-by: heyszt <36215648+hieheihei@users.noreply.github.com>
Co-authored-by: Abdullah AlOsaimi <osaimiacc@gmail.com>
Co-authored-by: Abdullah AlOsaimi <189027247+osaimi@users.noreply.github.com>
Co-authored-by: Yingchun Lai <laiyingchun@apache.org>
Co-authored-by: Hash Brown <hi@xzd.me>
Co-authored-by: zuodongxu <192560071+zuodongxu@users.noreply.github.com>
Co-authored-by: Masashi Tomooka <tmokmss@users.noreply.github.com>
Co-authored-by: aplio <ryo.091219@gmail.com>
Co-authored-by: Obada Khalili <54270856+obadakhalili@users.noreply.github.com>
Co-authored-by: Nam Vu <zuzoovn@gmail.com>
Co-authored-by: Kei YAMAZAKI <1715090+kei-yamazaki@users.noreply.github.com>
Co-authored-by: TechnoHouse <13776377+deephbz@users.noreply.github.com>
Co-authored-by: Riddhimaan-Senapati <114703025+Riddhimaan-Senapati@users.noreply.github.com>
Co-authored-by: MaFee921 <31881301+2284730142@users.noreply.github.com>
Co-authored-by: te-chan <t-nakanome@sakura-is.co.jp>
Co-authored-by: HQidea <HQidea@users.noreply.github.com>
Co-authored-by: Joshbly <36315710+Joshbly@users.noreply.github.com>
Co-authored-by: xhe <xw897002528@gmail.com>
Co-authored-by: weiwenyan-dev <154779315+weiwenyan-dev@users.noreply.github.com>
Co-authored-by: ex_wenyan.wei <ex_wenyan.wei@tcl.com>
Co-authored-by: engchina <12236799+engchina@users.noreply.github.com>
Co-authored-by: engchina <atjapan2015@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: 呆萌闷油瓶 <253605712@qq.com>
Co-authored-by: Kemal <kemalmeler@outlook.com>
Co-authored-by: Lazy_Frog <4590648+lazyFrogLOL@users.noreply.github.com>
Co-authored-by: Yi Xiao <54782454+YIXIAO0@users.noreply.github.com>
Co-authored-by: Steven sun <98230804+Tuyohai@users.noreply.github.com>
Co-authored-by: steven <sunzwj@digitalchina.com>
Co-authored-by: Kalo Chin <91766386+fdb02983rhy@users.noreply.github.com>
Co-authored-by: Katy Tao <34019945+KatyTao@users.noreply.github.com>
Co-authored-by: depy <42985524+h4ckdepy@users.noreply.github.com>
Co-authored-by: 胡春东 <gycm520@gmail.com>
Co-authored-by: Junjie.M <118170653@qq.com>
Co-authored-by: MuYu <mr.muzea@gmail.com>
Co-authored-by: Naoki Takashima <39912547+takatea@users.noreply.github.com>
Co-authored-by: Summer-Gu <37869445+gubinjie@users.noreply.github.com>
Co-authored-by: Fei He <droxer.he@gmail.com>
Co-authored-by: ybalbert001 <120714773+ybalbert001@users.noreply.github.com>
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
Co-authored-by: douxc <7553076+douxc@users.noreply.github.com>
Co-authored-by: liuzhenghua <1090179900@qq.com>
Co-authored-by: Wu Jiayang <62842862+Wu-Jiayang@users.noreply.github.com>
Co-authored-by: Your Name <you@example.com>
Co-authored-by: kimjion <45935338+kimjion@users.noreply.github.com>
Co-authored-by: AugNSo <song.tiankai@icloud.com>
Co-authored-by: llinvokerl <38915183+llinvokerl@users.noreply.github.com>
Co-authored-by: liusurong.lsr <liusurong.lsr@alibaba-inc.com>
Co-authored-by: Vasu Negi <vasu-negi@users.noreply.github.com>
Co-authored-by: Hundredwz <1808096180@qq.com>
Co-authored-by: Xiyuan Chen <52963600+GareArc@users.noreply.github.com>
2025-02-17 17:05:13 +08:00

283 lines
12 KiB
Python

import datetime
import json
from flask import request
from flask_login import current_user # type: ignore
from flask_restful import Resource, marshal_with, reqparse # type: ignore
from sqlalchemy import select
from sqlalchemy.orm import Session
from werkzeug.exceptions import NotFound
from controllers.console import api
from controllers.console.wraps import account_initialization_required, setup_required
from core.indexing_runner import IndexingRunner
from core.rag.extractor.entity.extract_setting import ExtractSetting
from core.rag.extractor.notion_extractor import NotionExtractor
from extensions.ext_database import db
from fields.data_source_fields import integrate_list_fields, integrate_notion_info_list_fields
from libs.login import login_required
from models import DataSourceOauthBinding, Document
from services.dataset_service import DatasetService, DocumentService
from tasks.document_indexing_sync_task import document_indexing_sync_task
class DataSourceApi(Resource):
@setup_required
@login_required
@account_initialization_required
@marshal_with(integrate_list_fields)
def get(self):
# get workspace data source integrates
data_source_integrates = (
db.session.query(DataSourceOauthBinding)
.filter(
DataSourceOauthBinding.tenant_id == current_user.current_tenant_id,
DataSourceOauthBinding.disabled == False,
)
.all()
)
base_url = request.url_root.rstrip("/")
data_source_oauth_base_path = "/console/api/oauth/data-source"
providers = ["notion"]
integrate_data = []
for provider in providers:
# existing_integrate = next((ai for ai in data_source_integrates if ai.provider == provider), None)
existing_integrates = filter(lambda item: item.provider == provider, data_source_integrates)
if existing_integrates:
for existing_integrate in list(existing_integrates):
integrate_data.append(
{
"id": existing_integrate.id,
"provider": provider,
"created_at": existing_integrate.created_at,
"is_bound": True,
"disabled": existing_integrate.disabled,
"source_info": existing_integrate.source_info,
"link": f"{base_url}{data_source_oauth_base_path}/{provider}",
}
)
else:
integrate_data.append(
{
"id": None,
"provider": provider,
"created_at": None,
"source_info": None,
"is_bound": False,
"disabled": None,
"link": f"{base_url}{data_source_oauth_base_path}/{provider}",
}
)
return {"data": integrate_data}, 200
@setup_required
@login_required
@account_initialization_required
def patch(self, binding_id, action):
binding_id = str(binding_id)
action = str(action)
with Session(db.engine) as session:
data_source_binding = session.execute(
select(DataSourceOauthBinding).filter_by(id=binding_id)
).scalar_one_or_none()
if data_source_binding is None:
raise NotFound("Data source binding not found.")
# enable binding
if action == "enable":
if data_source_binding.disabled:
data_source_binding.disabled = False
data_source_binding.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
db.session.add(data_source_binding)
db.session.commit()
else:
raise ValueError("Data source is not disabled.")
# disable binding
if action == "disable":
if not data_source_binding.disabled:
data_source_binding.disabled = True
data_source_binding.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
db.session.add(data_source_binding)
db.session.commit()
else:
raise ValueError("Data source is disabled.")
return {"result": "success"}, 200
class DataSourceNotionListApi(Resource):
@setup_required
@login_required
@account_initialization_required
@marshal_with(integrate_notion_info_list_fields)
def get(self):
dataset_id = request.args.get("dataset_id", default=None, type=str)
exist_page_ids = []
with Session(db.engine) as session:
# import notion in the exist dataset
if dataset_id:
dataset = DatasetService.get_dataset(dataset_id)
if not dataset:
raise NotFound("Dataset not found.")
if dataset.data_source_type != "notion_import":
raise ValueError("Dataset is not notion type.")
documents = session.execute(
select(Document).filter_by(
dataset_id=dataset_id,
tenant_id=current_user.current_tenant_id,
data_source_type="notion_import",
enabled=True,
)
).all()
if documents:
for document in documents:
data_source_info = json.loads(document.data_source_info)
exist_page_ids.append(data_source_info["notion_page_id"])
# get all authorized pages
data_source_bindings = session.scalars(
select(DataSourceOauthBinding).filter_by(
tenant_id=current_user.current_tenant_id, provider="notion", disabled=False
)
).all()
if not data_source_bindings:
return {"notion_info": []}, 200
pre_import_info_list = []
for data_source_binding in data_source_bindings:
source_info = data_source_binding.source_info
pages = source_info["pages"]
# Filter out already bound pages
for page in pages:
if page["page_id"] in exist_page_ids:
page["is_bound"] = True
else:
page["is_bound"] = False
pre_import_info = {
"workspace_name": source_info["workspace_name"],
"workspace_icon": source_info["workspace_icon"],
"workspace_id": source_info["workspace_id"],
"pages": pages,
}
pre_import_info_list.append(pre_import_info)
return {"notion_info": pre_import_info_list}, 200
class DataSourceNotionApi(Resource):
@setup_required
@login_required
@account_initialization_required
def get(self, workspace_id, page_id, page_type):
workspace_id = str(workspace_id)
page_id = str(page_id)
with Session(db.engine) as session:
data_source_binding = session.execute(
select(DataSourceOauthBinding).filter(
db.and_(
DataSourceOauthBinding.tenant_id == current_user.current_tenant_id,
DataSourceOauthBinding.provider == "notion",
DataSourceOauthBinding.disabled == False,
DataSourceOauthBinding.source_info["workspace_id"] == f'"{workspace_id}"',
)
)
).scalar_one_or_none()
if not data_source_binding:
raise NotFound("Data source binding not found.")
extractor = NotionExtractor(
notion_workspace_id=workspace_id,
notion_obj_id=page_id,
notion_page_type=page_type,
notion_access_token=data_source_binding.access_token,
tenant_id=current_user.current_tenant_id,
)
text_docs = extractor.extract()
return {"content": "\n".join([doc.page_content for doc in text_docs])}, 200
@setup_required
@login_required
@account_initialization_required
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("notion_info_list", type=list, required=True, nullable=True, location="json")
parser.add_argument("process_rule", type=dict, required=True, nullable=True, location="json")
parser.add_argument("doc_form", type=str, default="text_model", required=False, nullable=False, location="json")
parser.add_argument(
"doc_language", type=str, default="English", required=False, nullable=False, location="json"
)
args = parser.parse_args()
# validate args
DocumentService.estimate_args_validate(args)
notion_info_list = args["notion_info_list"]
extract_settings = []
for notion_info in notion_info_list:
workspace_id = notion_info["workspace_id"]
for page in notion_info["pages"]:
extract_setting = ExtractSetting(
datasource_type="notion_import",
notion_info={
"notion_workspace_id": workspace_id,
"notion_obj_id": page["page_id"],
"notion_page_type": page["type"],
"tenant_id": current_user.current_tenant_id,
},
document_model=args["doc_form"],
)
extract_settings.append(extract_setting)
indexing_runner = IndexingRunner()
response = indexing_runner.indexing_estimate(
current_user.current_tenant_id,
extract_settings,
args["process_rule"],
args["doc_form"],
args["doc_language"],
)
return response.model_dump(), 200
class DataSourceNotionDatasetSyncApi(Resource):
@setup_required
@login_required
@account_initialization_required
def get(self, dataset_id):
dataset_id_str = str(dataset_id)
dataset = DatasetService.get_dataset(dataset_id_str)
if dataset is None:
raise NotFound("Dataset not found.")
documents = DocumentService.get_document_by_dataset_id(dataset_id_str)
for document in documents:
document_indexing_sync_task.delay(dataset_id_str, document.id)
return 200
class DataSourceNotionDocumentSyncApi(Resource):
@setup_required
@login_required
@account_initialization_required
def get(self, dataset_id, document_id):
dataset_id_str = str(dataset_id)
document_id_str = str(document_id)
dataset = DatasetService.get_dataset(dataset_id_str)
if dataset is None:
raise NotFound("Dataset not found.")
document = DocumentService.get_document(dataset_id_str, document_id_str)
if document is None:
raise NotFound("Document not found.")
document_indexing_sync_task.delay(dataset_id_str, document_id_str)
return 200
api.add_resource(DataSourceApi, "/data-source/integrates", "/data-source/integrates/<uuid:binding_id>/<string:action>")
api.add_resource(DataSourceNotionListApi, "/notion/pre-import/pages")
api.add_resource(
DataSourceNotionApi,
"/notion/workspaces/<uuid:workspace_id>/pages/<uuid:page_id>/<string:page_type>/preview",
"/datasets/notion-indexing-estimate",
)
api.add_resource(DataSourceNotionDatasetSyncApi, "/datasets/<uuid:dataset_id>/notion/sync")
api.add_resource(
DataSourceNotionDocumentSyncApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/notion/sync"
)