fix: resolve “has no attribute 'max_length'” error in keyword_extraction (#7903)
### What problem does this PR solve?
**Issue Description:**
When using the `/api/retrieval` endpoint with a POST request and setting
the `keyword` parameter to `true`, the system invokes the
`model_instance` method from `TenantLLMService` to create a `chat_mdl`
instance. Subsequently, it calls the `keyword_extraction` method to
extract keywords.
However, within the `keyword_extraction` method, the `chat` function of
the LLM attempts to access the `chat_mdl.max_length` attribute to
validate input length. This results in the following error:
```
AttributeError: 'SILICONFLOWChat' object has no attribute 'max_length'
```
**Proposed Solution:**
Upon reviewing other parts of the codebase where `chat_mdl` instances
are created, it appears that utilizing `LLMBundle` for instantiation is
more appropriate. `LLMBundle` includes the `max_length` attribute, which
should resolve the encountered error.
### 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?
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>
Feat: Improve 'user_canvan_version' delete and 'document' delete performance (#6553)
### 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
[BREAKING CHANGE] GET to POST: enhance document list capability (#7349)
### 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?
1. Refactor error message
2. Fix knowledges are created on ES and can't be found in Infinity. The
document chunk fetch error.
### Type of change
- [x] Fix bug
- [x] Refactoring
---------
Signed-off-by: jinhai <haijin.chn@gmail.com>
### What problem does this PR solve?
Added static check at PR CI
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
Fix logs. Use dict.pop instead of del. Close #3473 (#3484)
### What problem does this PR solve?
Fix logs. Use dict.pop instead of del.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Move settings initialization after module init phase (#3438)
### What problem does this PR solve?
1. Module init won't connect database any more.
2. Config in settings need to be used with settings.CONFIG_NAME
### Type of change
- [x] Refactoring
Signed-off-by: jinhai <haijin.chn@gmail.com>
### What problem does this PR solve?
Integration with Infinity
- Replaced ELASTICSEARCH with dataStoreConn
- Renamed deleteByQuery with delete
- Renamed bulk to upsertBulk
- getHighlight, getAggregation
- Fix KGSearch.search
- Moved Dealer.sql_retrieval to es_conn.py
### Type of change
- [x] Refactoring
Bug fix - email processing could be run now from API (#2613)
### What problem does this PR solve?
If .eml file is uploaded, there is always General method chosen for
email processing, even if parsing_method is defined in the request. This
change solves this issue.
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Adam Kobus <adam.kobus@gitlab.eleader.biz>
Storage: Rename all the variables about get file to storage from minio. (#2497)
https://github.com/infiniflow/ragflow/issues/2496
### 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
- [x] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
Storage: Support the s3, azure blob as the object storage of ragflow. (#2278)
### What problem does this PR solve?
issue: https://github.com/infiniflow/ragflow/issues/2277
_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)
- [x] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Supports use API to get doc info by doc ids
### What problem does this PR solve?
feat: Supports use API to get doc info by doc ids
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Format file format from Windows/dos to Unix (#1949)
### What problem does this PR solve?
Related source file is in Windows/DOS format, they are format to Unix
format.
### Type of change
- [x] Refactoring
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Fix retrieval API error and add multi-kb search (#1928)
### What problem does this PR solve?
Type of change
Bug Fix (Import necessary class for retrieval API )
New Feature (Add multi-KB search to retrieval API)
fix: Fix for Empty Reference Array Causing Errors (#1652)
### What problem does this PR solve?
This pull request addresses an issue where the reference is an empty
array ([]) in specific cases, leading to errors in the application. When
the reference is empty, the code attempts to call the get method on a
list, resulting in the following error message:
``` json
{"retcode": 500, "retmsg": "'list' object has no attribute 'get'", "data": {"answer": "**ERROR**: 'list' object has no attribute 'get'", "reference": []}}
```
### 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?
fix api reference empty bug
```
for chunk_i in answer['reference'].get('chunks',[]):
^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'list' object has no attribute 'get'
```
```
return np.array([d["relevance_score"] for d in res["results"]]), res["meta"]["tokens"]["input_tokens"]+res["meta"]["tokens"]["output_tokens"]
~~~^^^^^^^^^^^
KeyError: 'results'
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Delete files from a knowledge base.
#717
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Yongteng Lei
Qidi Cao
Stephen Hu
Zhichang Yu
Kevin Hu
Jin Hai
adam-kobus
lidp
Fachuan Bai
wwwlll
wwwlll
Valdanito
Myth
Kung Quang