Commit Graph

2539 Commits

Author SHA1 Message Date
3e19044dee Feat: add OCR's muti-gpus and parallel processing support (#5972)
### What problem does this PR solve?

Add OCR's muti-gpus and parallel processing support

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

@yuzhichang I've tried to resolve the comments in #5697. OCR jobs can
now be done on both CPU and GPU. ( By the way, I've encountered a
“Generate embedding error” issue #5954 that might be due to my outdated
GPUs? idk. ) Please review it and give me suggestions.

GPU:

![gpu_ocr](https://github.com/user-attachments/assets/0ee2ecfb-a665-4e50-8bc7-15941b9cd80e)

![smi](https://github.com/user-attachments/assets/a2312f8c-cf24-443d-bf89-bec50503546d)

CPU:

![cpu_ocr](https://github.com/user-attachments/assets/1ba6bb0b-94df-41ea-be79-790096da4bf1)
2025-03-17 11:58:40 +08:00
8495036ff9 Feat: Limit view with more knowledge when list knowledge so many (#6093)
### What problem does this PR solve?

Limit view with more knowledge when list knowledge so many.

### Type of change

- [x] Refactoring
2025-03-17 10:50:25 +08:00
7f701a5756 Test: update test cases per pr #6095 to fix issue #6039 (#6143)
### What problem does this PR solve?

update test case per pr #6095 to fix issue #6039

### Type of change

- [x] update test case
2025-03-17 10:49:40 +08:00
634e7a41c5 Doc: Update readme document (#6052)
### What problem does this PR solve?

Added GPU startup script in the readme document

### Type of change

- [x] Documentation Update
2025-03-17 09:51:13 +08:00
d1d651080a Test: Added test cases for Update Documents HTTP API (#6106)
### What problem does this PR solve?

cover [update documents
endpoints](https://ragflow.io/docs/dev/http_api_reference#update-document)

### Type of change

- [x] add test cases
2025-03-17 09:36:32 +08:00
0fa44c5dd3 Fix: update link of deploy_local_llm.mdx (#6110)
### What problem does this PR solve?

Links of [How to integrate with
Ollama](https://github.com/infiniflow/ragflow/blob/main/docs/guides/models/deploy_local_llm.mdx)
need to be update after #5555

```
https://github.com/infiniflow/ragflow/blob/main/docs/guides/deploy_local_llm.mdx
->
https://github.com/infiniflow/ragflow/blob/main/docs/guides/models/deploy_local_llm.mdx
```



### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

Signed-off-by: jingfelix <jingfelix@outlook.com>
2025-03-17 09:35:37 +08:00
89a69eed72 Introduced task priority (#6118)
### What problem does this PR solve?

Introduced task priority

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-03-14 23:43:46 +08:00
1842ca0334 Fix: Fixed the issue that events cannot be triggered after the shadcn-ui dialog is closed #3221. (#6108)
### What problem does this PR solve?

Fix: Fixed the issue that events cannot be triggered after the shadcn-ui
dialog is closed #3221.

Refer to [Combobox in a form in a dialog isn't working.
#1748](https://github.com/shadcn-ui/ui/issues/1748#issuecomment-2720130543)

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-14 17:36:24 +08:00
e5a8b23684 Fix: empty tag field issue. (#6103)
### What problem does this PR solve?

#6102

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-14 17:35:57 +08:00
4fffee6695 Regards kb_id at ElasticSearch insert, update, delete. (#6105)
### What problem does this PR solve?

Regards kb_id at ElasticSearch insert, update, delete. Close #6066

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-14 17:34:02 +08:00
485bc7d7d6 Fix: limit the depth of DFS (#6101)
### What problem does this PR solve?

#6085

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-14 17:10:38 +08:00
b5ba8b783a Refa: enlarge http body size. (#6100)
### What problem does this PR solve?



### Type of change


- [x] Refactoring
2025-03-14 16:47:39 +08:00
d7774cf049 Fix: fix document concurrent upload issue (#6095)
### What problem does this PR solve?

Resolve document concurrent upload issue. #6039 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-14 16:31:44 +08:00
9d94acbedb Fix: Knowledge base page cannot upload folders #6062 (#6096)
### What problem does this PR solve?

Fix: Knowledge base page cannot upload folders #6062

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-14 16:17:10 +08:00
b77e844fc3 Fix: none parse_config updating. (#6092)
### What problem does this PR solve?

#6081

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-14 16:06:16 +08:00
a6ab2c71c3 Refa: enlarge default max request body size. (#6088)
### What problem does this PR solve?


### Type of change


- [x] Refactoring
2025-03-14 15:21:08 +08:00
5c8ad6702a Fix: check the file name length. (#6083)
### What problem does this PR solve?

#6060

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-14 15:01:37 +08:00
f0601afa75 Doc: update launch from source. (#6074)
### What problem does this PR solve?

#6050

### Type of change

- [x] Documentation Update

---------

Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
2025-03-14 14:20:18 +08:00
56e984f657 Fix: Prevent password boxes other than login passwords from displaying passwords saved in the browser's password manager by default. #6033 (#6084)
### What problem does this PR solve?

Fix: Prevent password boxes other than login passwords from displaying
passwords saved in the browser's password manager by default. #6033

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-03-14 14:15:43 +08:00
5d75b6be62 Fix executor name (#6080)
### What problem does this PR solve?

Fix executor name

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-14 14:13:47 +08:00
12c3023a22 Fix: remove NaN output of components. (#6079)
### What problem does this PR solve?

#6065

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-14 13:58:42 +08:00
56b228f187 Refa: remove max toekns for image2txt models. (#6078)
### What problem does this PR solve?

#6063

### Type of change


- [x] Refactoring
2025-03-14 13:51:45 +08:00
42eb99554f Feat: add token comsumption & speed to little lamp. (#6077)
### What problem does this PR solve?

#6059

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-03-14 13:37:31 +08:00
c85b468b8d Feat: Change “Document parser” to "PDF parser" #6072 (#6073)
### What problem does this PR solve?

Feat: Change “Document parser” to "PDF parser" #6072

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-03-14 12:03:35 +08:00
7463241896 Fix: empty doc id validation. (#6064)
### What problem does this PR solve?

#6031

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-14 11:45:44 +08:00
c00def5b71 Fix 6030 (#6070)
### What problem does this PR solve?

Close #6030 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-14 11:29:22 +08:00
f16418ccf7 Feat: Add deepseek to llm_factories (#6051)
### What problem does this PR solve?

AWS Bedrock has made deepseek-r1 available on its serverless inference.

This adds the R1 serverless model for use via the bedrock model
abilities.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-03-14 10:35:44 +08:00
2d4a60cae6 Fix: Reduce excessive IO operations by loading LLM factory configurations (#6047)
…ions

### What problem does this PR solve?

This PR fixes an issue where the application was repeatedly reading the
llm_factories.json file from disk in multiple places, which could lead
to "Too many open files" errors under high load conditions. The fix
centralizes the file reading operation in the settings.py module and
stores the data in a global variable that can be accessed by other
modules.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [x] Performance Improvement
- [ ] Other (please describe):
2025-03-14 09:54:38 +08:00
47926f7d21 Improve API Documentation, Standardize Error Handling, and Enhance Comments (#5990)
### What problem does this PR solve?  
- The API documentation lacks detailed error code explanations. Added
error code tables to `python_api_reference.md` and
`http_api_reference.md` to clarify possible error codes and their
meanings.
- Error handling in the codebase is inconsistent. Standardized error
handling logic in `sdk/python/ragflow_sdk/modules/chunk.py`.
- Improved API comments by adding standardized docstrings to enhance
code readability and maintainability.

### Type of change  
- [x] Documentation Update  
- [x] Refactoring
2025-03-13 19:06:50 +08:00
940072592f Fix: chat_completion answer data incorrect (#6041)
### What problem does this PR solve?

fix chat_completion answer data incorrect

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

Co-authored-by: renqi <renqi08266@fxomail.com>
2025-03-13 18:59:59 +08:00
4ff609b6a8 Fix: optimize OCR garbage identification to reduce unnecessary filtering (#6027)
### What problem does this PR solve?

Optimize OCR garbage identification to reduce unnecessary filtering.
#5713

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-13 18:48:32 +08:00
0a877941f4 Test: Added test cases for Download Documents HTTP API (#6032)
### What problem does this PR solve?

cover [download docments
endpoints](https://ragflow.io/docs/dev/http_api_reference#download-document)

### Type of change

- [x] add test cases
2025-03-13 18:32:57 +08:00
baf3b9be7c Added 0.17.2 release notes (#6028)
### What problem does this PR solve?



### Type of change

- [x] Documentation Update
v0.17.2
2025-03-13 15:59:58 +08:00
4df4bf68a2 DOCS: for release. (#6023)
### What problem does this PR solve?


### Type of change

- [x] Documentation Update
2025-03-13 15:09:29 +08:00
471bd92b4c Fix: empty api-key causes problems. (#6022)
### What problem does this PR solve?
#5926

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-13 14:57:47 +08:00
3af1063737 Feat: Set the default value of Chunk token number to 512 #6016 (#6017)
### What problem does this PR solve?

Feat: Set the default value of Chunk token number to 512 #6016

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-03-13 14:51:55 +08:00
9c8060f619 0.17.1 release notes (#6021)
### What problem does this PR solve?



### Type of change

- [x] Documentation Update
2025-03-13 14:43:24 +08:00
e213873852 Optimize graphrag cache get entity (#6018)
### What problem does this PR solve?

Optimize graphrag cache get entity

### Type of change

- [x] Performance Improvement
2025-03-13 14:37:59 +08:00
56acb340d2 Test: update test cases per issue #5920 #5923 (#6007)
### What problem does this PR solve?

update test cases per issue #5920 #5923

### Type of change

- [x] update test case
2025-03-13 10:53:07 +08:00
e05cdc2f9c Fix: encode detect error. (#6006)
### What problem does this PR solve?

#5967

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-13 10:47:58 +08:00
3571270191 Refa: refine the context window size warning. (#5993)
### What problem does this PR solve?


### Type of change
- [x] Refactoring
2025-03-12 19:40:54 +08:00
bd5eb47441 TEST: Added test cases for Upload Documents HTTP API (#5991)
### What problem does this PR solve?

cover upload docments endpoints

### Type of change

- [x] add test cases
2025-03-12 19:38:52 +08:00
7cd37c37cd Feat: add CSV file parsing support (#5989)
### What problem does this PR solve?

Add CSV file parsing support #4552, #5849, #5870

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-03-12 19:20:50 +08:00
d660f6b9a5 Feat: add use KG to retrieval component. (#5988)
### What problem does this PR solve?

#5973

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-03-12 19:10:07 +08:00
80389ae61e Feat: Alter Item to TransferListItemType #3221 (#5986)
### What problem does this PR solve?

Feat: Alter Item to TransferListItemType #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-03-12 18:54:41 +08:00
6e13922bdc Feat: Add qwq model support to Tongyi-Qianwen factory (#5981)
### What problem does this PR solve?

add qwq model support to Tongyi-Qianwen factory
https://github.com/infiniflow/ragflow/issues/5869

### Type of change

- [x] New Feature (non-breaking change which adds functionality)


![image](https://github.com/user-attachments/assets/49f5c6a0-ecaf-41dd-a23a-2009f854d62c)


![image](https://github.com/user-attachments/assets/93ffa303-920e-4942-8188-bcd6b7209204)


![1741774779438](https://github.com/user-attachments/assets/25f2fd1d-8640-4df0-9a08-78ee9daaa8fe)


![image](https://github.com/user-attachments/assets/4763cf6c-1f76-43c4-80ee-74dfd666a184)

Co-authored-by: zhaozhicheng <zhicheng.zhao@fastonetech.com>
2025-03-12 18:54:15 +08:00
c57f16d16f Feat: Why can't Retrieval component support internet web search. #5973 (#5978)
### What problem does this PR solve?

Feat: Why can't Retrieval component support internet web search. #5973

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-03-12 18:47:22 +08:00
3c43a7aee8 For an Agent with an Input Begin value, on the first call the return … (#5957)
…session_id does not exist in the session

For an Agent with an Input Begin value, on the first call the return
session_id does not exist in the session

### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-12 17:01:44 +08:00
dd8779b257 Feat: Retrieval supports internet search. (#5974)
### What problem does this PR solve?

#5973

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-03-12 16:51:01 +08:00
46bdfb9661 TEST: Remove unstable assertion introduced in PR #5924 (#5968)
### What problem does this PR solve?

Remove unstable assertion introduced in PR #5924

### Type of change

- [x] update test cases
2025-03-12 16:09:45 +08:00