### What problem does this PR solve?
Fix HTTP API Create/Update dataset parser config default value error
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Hello, we are using ragflow as a backend service, so we need to manage
agents from our own frontend. So adding these http APIs to manage
agents.
The code logic is copied and modified from the `rm` and `save` methods
in `api/apps/canvas_app.py`.
btw, I found that the `save` method in `canvas_app.py` actually allows
to modify an agent to an existing title, so I kept the behavior in the
http api. I'm not sure if this is intentional.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
This PR introduces Pydantic-based validation for the update dataset HTTP
API, improving code clarity and robustness. Key changes include:
1. Pydantic Validation
2. Error Handling
3. Test Updates
4. Documentation Updates
5. fix bug: #5915
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Documentation Update
- [x] Refactoring
### What problem does this PR solve?
1. The MySQL instance is configured with max_connections=1000,
but our connection pool was limited to max_connections: 100.
This mismatch caused connection pool exhaustion during performance
testing.
2. Increase stale_timeout to resolve#6548
### Type of change
- [x] Performance Improvement
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Kb detail supports return document total size now.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/7519
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Add `/login/channels` route and improve auth logic to support frontend
integration with third-party login providers:
- Add `/login/channels` route to provide authentication channel list
with `display_name` and `icon`
- Optimize user info parsing logic by prioritizing `avatar_url` and
falling back to `picture`
- Simplify OIDC token validation by removing unnecessary `kid` checks
- Ensure `client_id` is safely cast to string during `audience`
validation
- Fix typo
---
- Related pull request: #7379
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
Fix:When sharing the knowledge base of multiple tenants with one person,
when this person queries the knowledge base of both tenants, they will
only query the question of the first person's knowledge base
Co-authored-by: 杜有强 <duyq@internal.ths.com.cn>
### What problem does this PR solve?
1. Add delete_by_ids method
2. Add get_doc_ids_by_doc_names
3. Improve user_canvan_version's logic (avoid O(n) db IO)
4. Improve document delete logic (avoid O(n) db IO)
### Type of change
- [x] Performance Improvement
### What problem does this PR solve?
Fix: After deleting the file from the file management menu, it was not
removed from the MinIO bucket.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
Co-authored-by: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>
### What problem does this PR solve?
Fix `filed_map` was incorrectly persisted. #7412
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
change create dataset delimiter default value to r'\n'
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/7407
Based on this context, I think there should be some reasons that let
some LLMs have a mismatch (add the wrong "@xxx"),
So I think when use fid can not fetch llm then tried to just use name
should can fetch it.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Remove unnecessary parameter restrictions in dataset creation API
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
When you removed any document in a knowledge base using knowledge graph,
the graph's `removed_kwd` is set to "Y".
However, in the function `graphrag.utils.get_gaph`, `rebuild_graph`
method is passed and directly return `None` while `removed_kwd=Y`,
making residual part of the graph abandoned (but old entity data still
exist in db).
Besides, infinity instance actually pass deleting graph components'
`source_id` when removing document. It may cause wrong graph after
rebuild.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR introduces Pydantic-based validation for the create dataset HTTP
API, improving code clarity and robustness. Key changes include:
1. Pydantic Validation
2. Error Handling
3. Test Updates
4. Documentation
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Documentation Update
- [x] Refactoring
### What problem does this PR solve?
Add support for OAuth2 and OpenID Connect (OIDC) authentication,
allowing OAuth/OIDC authentication using the specified routes:
- `/login/<channel>`: Initiates the OAuth flow for the specified channel
- `/oauth/callback/<channel>`: Handles the OAuth callback after
successful authentication
The callback URL should be configured in your OAuth provider as:
```
https://your-app.com/oauth/callback/<channel>
```
For detailed instructions on configuring **service_conf.yaml.template**,
see: `./api/apps/auth/README.md#usage`.
- Related issues
#3495
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
### What problem does this PR solve?
When updating a chat assistant using API,if the dataset attached by the
current chat assistant is not empty，setting dataset to
null("dataset_ids":[]) will cause update failure：'dataset_ids' can't be
empty
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
In the generate_confirmation_token method, a spelling error was found
with 'tenent_id'. The correct spelling should be 'tenant_id'.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
Co-authored-by: shengliang xiao <shengliangxiao2024@gmail.com>
### What problem does this PR solve?
Enhance capability of `list_docs`.
Breaking change: change method from `GET` to `POST`.
### Type of change
- [x] Refactoring
- [x] Enhancement with breaking change
### What problem does this PR solve?
This PR adds the support for latest OpenSearch2.19.1 as the store engine
& search engine option for RAGFlow.
### Main Benefit
1. OpenSearch2.19.1 is licensed under the [Apache v2.0 License] which is
much better than Elasticsearch
2. For search, OpenSearch2.19.1 supports full-text
search、vector_search、hybrid_search those are similar with Elasticsearch
on schema
3. For store, OpenSearch2.19.1 stores text、vector those are quite
simliar with Elasticsearch on schema
### Changes
- Support opensearch_python_connetor. I make a lot of adaptions since
the schema and api/method between ES and Opensearch differs in many
ways(especially the knn_search has a significant gap) :
rag/utils/opensearch_coon.py
- Support static config adaptions by changing:
conf/service_conf.yaml、api/settings.py、rag/settings.py
- Supprt some store&search schema changes between OpenSearch and ES:
conf/os_mapping.json
- Support OpenSearch python sdk : pyproject.toml
- Support docker config for OpenSearch2.19.1 :
docker/.env、docker/docker-compose-base.yml、docker/service_conf.yaml.template
### How to use
- I didn't change the priority that ES as the default doc/search engine.
Only if in docker/.env , we set DOC_ENGINE=${DOC_ENGINE:-opensearch}, it
will work.
### Others
Our team tested a lot of docs in our environment by using OpenSearch as
the vector database ,it works very well.
All the conifg for OpenSearch is necessary.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
### What problem does this PR solve?
Some models force thinking, resulting in the absence of the think tag in
the returned content
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
The knowledge_graph chunk method is deprecated and should no longer be
used. #7184.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
Enhance capability of `list_kbs`.
Breaking change: change method from `GET` to `POST`.
### Type of change
- [x] Refactoring
- [x] Enhancement with breaking change
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/7083
Internal due to when returning from ES, fields changed to str, so the
bool conversion does not work as expected.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Related Issue:
https://github.com/infiniflow/ragflow/issues/6548
### Related PR:
https://github.com/infiniflow/ragflow/pull/6861
### Environment:
Commit version:
[[48730e0](48730e00a8)]
### Bug Description:
Unexpected `pymysql.err.InterfaceError: (0, '') `when using Peewee +
PyMySQL + PooledMySQLDatabase after a long-running `chat streamly`
operation.
This is a common issue with Peewee + PyMySQL + connection pooling: you
end up using a connection that was silently closed by the server, but
Peewee doesn't realize it's dead.
**I found that the error only occurs during longer streaming outputs**
and is unrelated to the database connection context, so it's likely
because:
- The prolonged streaming response caused the database connection to
time out
- The original database connection might have been disconnected by the
server during the streaming process
### Why This Happens
This error happens even when using `@DB.connection_context() `after the
stream is done. After investigation, I found this is caused by MySQL
connection pools that appear to be open but are actually dead (expired
due to` wait_timeout`).
1. `@DB.connection_context()` (as a decorator or context manager) pulls
a connection from the pool.
2. If this connection was idle and expired on the MySQL server (e.g.,
due to `wait_timeout`), but not closed in Python, it will still be
considered “open” (`DB.is_closed() == False`).
3. The real error will occur only when I execute a SQL command (such as
.`get_or_none()`), and PyMySQL tries to send it to the server via a
broken socket.
### Changes Made:
1. I implemented manual connection checks before executing SQL:
```
try:
DB.execute_sql("SELECT 1")
except Exception:
print("Connection dead, reconnecting...")
DB.close()
DB.connect()
```
2. Delayed the token count update until after the streaming response is
completed to ensure the streaming output isn't interrupted by database
operations.
```
total_tokens = 0
for txt in chat_streamly(system, history, gen_conf):
if isinstance(txt, int):
total_tokens = txt
......
break
......
if total_tokens > 0:
if not TenantLLMService.increase_usage(self.tenant_id, self.llm_type, txt, self.llm_name):
logging.error("LLMBundle.chat_streamly can't update token usage for {}/CHAT llm_name: {}, content: {}".format(self.tenant_id, self.llm_name, txt))
```
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/6905
When deleting a document will check before removing it from storage
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add fallback for bad citation output. #6948
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix update_progress issue introduced by #6975
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
ragflow: v0.17 also encountered this problem. #1453 The task table shows
that the actual task has been completed. Since the process_msg of the
task is not synchronized to the document table, there is no progress
update on the page.
This may be caused by the lock not being released when the exception
occurs.
ragflow：v0.17同样碰到这个问题， 看task表实际任务已经完成，由于没有把task的process_msg同步给document表,
所以在页面看没有进度更新。
可能是这里异常时没有释放锁导致的。
```/api/ragflow_server.py
def update_progress():
lock_value = str(uuid.uuid4())
redis_lock = RedisDistributedLock("update_progress", lock_value=lock_value, timeout=60)
logging.info(f"update_progress lock_value: {lock_value}")
while not stop_event.is_set():
try:
if redis_lock.acquire():
DocumentService.update_progress()
redis_lock.release()
stop_event.wait(6)
except Exception:
logging.exception("update_progress exception")
++ if redis_lock.acquired:
++ redis_lock.release()
```
### What problem does this PR solve?
Fix KB update_time changed whenever system relaunched. #6953
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: remove deprecated KB updating `permission` field. #6911
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
resolve this issue：https://github.com/infiniflow/ragflow/issues/6876
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: wenju.li <wenju.li@deepctr.cn>
### What problem does this PR solve?
The old logic filters out all assistant messages from messages, which,
in multi-turn conversations, results in only user messages being
retained. This leads to an error in locally deployed models:
Conversation roles must alternate user/assistant/user/assistant/...
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
This PR introduces **primitive support for function calls**,
enabling the system to handle basic function call capabilities.
However, this feature is currently experimental and **not yet enabled
for general use**, as it is only supported by a subset of models,
namely, Qwen and OpenAI models.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fixes#6548
Add exception handling to prevent exceptions from propagating back to
the web, which may lead to failure in displaying conversation content.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
Co-authored-by: cm <caiming@sict.ac.cn>
