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)
Fix: update broken create agent session due to v0.20.0 changes (#9445)
### What problem does this PR solve?
Update broken create agent session due to v0.20.0 changes. #9383
**NOTE: A session ID is no longer required to interact with the agent.**
See: #9241, #9309.
### 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)
Feat: allows setting multiple types of default models in service config (#9404)
### What problem does this PR solve?
Allows set multiple types of default models in service config.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Fix KeyError in session listing endpoint when accessing conversation reference (#9419)
- Add type and boundary checks for conv["reference"] access
- Prevent KeyError: 0 when reference list is empty or malformed
- Ensure reference is list type before indexing
- Handle cases where reference items are None or missing chunks
- Maintains backward compatibility with existing data structures
This resolves crashes in /api/v1/agents/<agent_id>/sessions endpoint
when conversation reference data is not properly structured.
### What problem does this PR solve?
This PR fixes a critical `KeyError: 0` that occurs in the
`/api/v1/agents/<agent_id>/sessions` endpoint when the system attempts
to access conversation reference data that is not properly structured.
**Background Context:**
The `list_agent_session` method in `api/apps/sdk/session.py` assumes
that `conv["reference"]` is always a properly indexed list with valid
dictionary structures. However, in real-world scenarios, this data can
be:
- Not a list type (could be None, string, or other types)
- An empty list when `chunk_num` tries to access index 0
- Contains None values or malformed dictionary structures
- Missing expected "chunks" keys in reference items
**Impact Before Fix:**
When malformed reference data is encountered, the API crashes with:
```json
{
"code": 100,
"data": null,
"message": "KeyError(0)"
}
```
**Solution:**
Added comprehensive safety checks including type validation, boundary
checking, null safety, and structure validation to ensure the API
gracefully handles all reference data formats while maintaining backward
compatibility.
### 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):
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: handle missing dataset_ids when creating chat assistant (#9324)
- Root cause: accessing req.get("dataset_ids") returns None when the key
is absent, causing KeyError.
- Fix: use req.get("dataset_ids", []) to default to empty list.
Revert: revert token_required decorator of agent_bot completions and inputs (#9332)
### What problem does this PR solve?
Revert token_required decorator of agent_bot completions and inputs.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [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: virtual file cannot be displayed in KB (#9282)
### What problem does this PR solve?
Fix virtual file cannot be displayed in KB. #9265
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Refactor:Improve the logic so that it does not decode base 64 for the test image each time (#9264)
### What problem does this PR solve?
Improve the logic so that it does not decode base 64 for the test image
each time
### Type of change
- [x] Refactoring
- [x] Performance Improvement
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Fix: fix mismatch of assitant message and its reference (#9233)
### What problem does this PR solve?
#9232
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
1. When creating a new session, initialize an empty reference that
includes both the app api and sdk API.
2. Fix the logic when retrieving references for historical messages: the
number of dialogue messages and reference messages may differ, but it
should match the number of assistant messages.
Co-authored-by: Li Ye <liye@unittec.com>
Feat: list documents supports range filtering (#9214)
### What problem does this PR solve?
list_document supports range filtering.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
fix #8424 NPE in dify_retrieval.py, add log exception (#9212)
### What problem does this PR solve?
fix #8424 NPE in dify_retrieval.py, add log exception
### 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)
Fix: list tags api by using tenant id instead of user id (#9103)
### What problem does this PR solve?
The index name of the tag chunks is generated by the tenant id of the
knowledge base, so it should use the tenant id instead of the current
user id in the listing tags API.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Feat: Add industry-related search keyword generation function (#9156)
### What problem does this PR solve?
Add industry-related search keyword generation function
- When generating search keywords, support for specific industries has
been added
- If the "industry" parameter is provided, industry-specific
restrictions will be added to the prompt
- This change can help users generate more precise search keywords
within specific industries
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### 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)
Refa: Update base64 test image with new sample data (#9115)
### What problem does this PR solve?
Replace the placeholder test image in base64_image.py with a new sample
image data string.
### Type of change
- [x] Refactoring
Fix : API /document/thumbnails using wrong method to get ''doc_ids' (#9097)
### What problem does this PR solve?
doc_ids is a list , should use request.args.getlist("doc_ids")
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Feat: parsing supports jsonl or ldjson format (#9087)
### What problem does this PR solve?
Supports jsonl or ldjson format. Feature request from
[discussion](https://github.com/orgs/infiniflow/discussions/8774).
### 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>
Refa: validation utils to use Pydantic v2 style models (#9037)
### What problem does this PR solve?
- Update BaseModel to use model_config instead of Config class
- Replace StrEnum with Literal types for method fields
- Convert Field declarations to Annotated style
### Type of change
- [x] Refactoring
Yongteng Lei
Kevin Hu
balibabu
Mckennasora
Stephen Hu
jiasu
so95
sinopec
Jay Xu
He Wang
天海蒼灆
Liu An
kuschzzp
wenxuan.zhang
Zhichang Yu