Commit Graph

584 Commits

Author SHA1 Message Date
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
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
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
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
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
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
1c663b32b9 Fix:signal.SIGUSR1 and signal.SIGUSR2 can't use in window. so don't bind signal.SIGUSR1 and signal.SIGUSR2 in the windows env (#5941)
### What problem does this PR solve?
Fix:signal.SIGUSR1 and signal.SIGUSR2 can't use in window. so don't bind
signal.SIGUSR1 and signal.SIGUSR2 in the windows env

### 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):

Co-authored-by: tangyu <1@1.com>
2025-03-12 09:43:18 +08:00
caecaa7562 Feat: apply LLM to optimize citations. (#5935)
### What problem does this PR solve?

#5905

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-03-11 19:56:21 +08:00
6ec6ca6971 Refactor graphrag to remove redis lock (#5828)
### What problem does this PR solve?

Refactor graphrag to remove redis lock

### Type of change

- [x] Refactoring
2025-03-10 15:15:06 +08:00
15736c57c3 Fix: empty query issue. (#5830)
### What problem does this PR solve?

#5214

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-10 13:56:56 +08:00
b29539b442 Fix: CoHereRerank not respecting base_url when provided (#5784)
### What problem does this PR solve?

vLLM provider with a reranking model does not work : as vLLM uses under
the hood the [CoHereRerank
provider](https://github.com/infiniflow/ragflow/blob/v0.17.0/rag/llm/__init__.py#L250)
with a `base_url`, if this URL [is not passed to the Cohere
client](https://github.com/infiniflow/ragflow/blob/v0.17.0/rag/llm/rerank_model.py#L379-L382)
any attempt will endup on the Cohere SaaS (sending your private api key
in the process) instead of your vLLM instance.

### 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):
2025-03-10 11:22:06 +08:00
2ad852d8df Fix: truncate message issue. (#5776)
### What problem does this PR solve?

Close #5761
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-07 17:41:56 +08:00
64c6cc4cf3 Fix: truncate message issue. (#5765)
### What problem does this PR solve?

Close #5761

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-07 16:33:25 +08:00
b1bbb9e210 Refa: make Rewrite component effective to relative data expression. (#5752)
### What problem does this PR solve?

#5716

### Type of change

- [x] Refactoring
2025-03-07 13:48:13 +08:00
df9b7b2fe9 Fix: rerank issue. (#5696)
### What problem does this PR solve?

#5673

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-06 15:05:19 +08:00
251ba7f058 Refa: remove max tokens since no one needs it. (#5690)
### What problem does this PR solve?

#5646 #5640

### Type of change

- [x] Refactoring
2025-03-06 11:29:40 +08:00
b8da2eeb69 Feat: support huggingface re-rank model. (#5684)
### What problem does this PR solve?

#5658

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-03-06 10:44:04 +08:00
4326873af6 refactor: no need to inherit in python3 clean the code (#5659)
### What problem does this PR solve?

As title

### Type of change


- [x] Refactoring

Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-03-05 18:03:53 +08:00
e5041749a2 Fix: tavily search error. (#5653)
### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-05 17:03:05 +08:00
f65c3ae62b Refactored DocumentService.update_progress (#5642)
### What problem does this PR solve?

Refactored DocumentService.update_progress

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-05 14:48:03 +08:00
b0c21b00d9 Refactor: Optimize error handling and support parsing of XLS(EXCEL97—2003) files. (#5633)
Optimize error handling and support parsing of XLS(EXCEL97—2003) files.
2025-03-05 11:55:27 +08:00
76e8285904 use to_df replace to_pl when get infinity Result (#5604)
### 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

- [x] Performance Improvement

---------

Co-authored-by: wangwei <dwxiayi@163.com>
2025-03-05 09:35:40 +08:00
4d6484b03e Fix nursery.start_soon. Close #5575 (#5591)
### What problem does this PR solve?

Fix nursery.start_soon. Close #5575

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-04 14:46:54 +08:00
c813c1ff4c Made task_executor async to speedup parsing (#5530)
### What problem does this PR solve?

Made task_executor async to speedup parsing

### Type of change

- [x] Performance Improvement
2025-03-03 18:59:49 +08:00
c190086707 Fix: bad case for tokenizer. (#5543)
### What problem does this PR solve?

#5492

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-03 15:36:16 +08:00
8a2542157f Fix: possible memory leaks close #5277 (#5500)
### What problem does this PR solve?

close #5277 by make sure the file close

### Type of change

- [x] Performance Improvement

---------

Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-03-03 10:26:45 +08:00
21943ce0e2 Refine error message while embedding model error, (#5490)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2025-02-28 17:52:38 +08:00
b418ce5643 Fix table parser issue. (#5482)
### What problem does this PR solve?

#1475
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-28 16:09:12 +08:00
85924e898e Fix: enhance aliyun oss access with adding prefix path (#5475)
### What problem does this PR solve?

Enhance aliyun oss access with adding prefix path.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-28 15:00:00 +08:00
622b72db4b Fix: add ctrl+c signal for better exit (#5469)
### What problem does this PR solve?

This patch add signal for ctrl + c that can exit the code friendly
cause code base use thread daemon can not exit friendly for being
started.

how to reproduce
1. docker-compose -f docker/docker-compose-base.yml up
2. other window `bash docker/launch_backend_service.sh`
3. stop 1 first
4. try to stop 2 then two thread can not exit which must use `kill pid`

This patch fix it 
and should fix most the related issues in the `issues`

### Type of change

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

---------

Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-02-28 14:52:40 +08:00
651422127c Feat: Accessing Alibaba Cloud OSS with Amazon S3 SDK (#5438)
Accessing Alibaba Cloud OSS with Amazon S3 SDK
2025-02-27 17:02:42 +08:00
4c9a3e918f Fix: add image2text issue. (#5431)
### What problem does this PR solve?

#5356

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-27 14:06:49 +08:00
fa76974e24 Fix issue of ask API. (#5400)
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-26 19:45:22 +08:00
0284248c93 Fix: correct wrong vLLM rerank model (#5399)
### What problem does this PR solve?

Correct wrong vLLM rerank model #4316 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-26 18:59:36 +08:00
cdcaae17c6 Feat: add VLLM (#5380)
### What problem does this PR solve?

Read to add VLMM.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-02-26 16:04:53 +08:00
96e9d50060 Let parallism of RAPTOR controlable. (#5379)
### What problem does this PR solve?

#4874
### Type of change

- [x] Refactoring
2025-02-26 15:58:06 +08:00
4f40f685d9 Code refactor (#5371)
### What problem does this PR solve?

#5173

### Type of change

- [x] Refactoring
2025-02-26 15:40:52 +08:00
ffb4cda475 Run keyword_extraction, question_proposal, content_tagging in thread pool (#5376)
### What problem does this PR solve?

Run keyword_extraction, question_proposal, content_tagging in threads

### Type of change

- [x] Performance Improvement
2025-02-26 15:21:14 +08:00
4e2afcd3b8 Fix FlagRerank max_length issue. (#5366)
### What problem does this PR solve?

#5352

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-26 11:01:13 +08:00
53b9e7b52f Add tavily as web searh tool. (#5349)
### What problem does this PR solve?

#5198

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-02-26 10:21:04 +08:00
955801db2e Resolve super class invokation error. (#5337)
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-25 17:42:29 +08:00
daddfc9e1b Remove dup gb2312, solve currupt error. (#5326)
### What problem does this PR solve?

#5252 
#5325

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-25 12:22:37 +08:00
db42d0e0ae Optimize ocr (#5297)
### What problem does this PR solve?

Introduced OCR.recognize_batch

### Type of change

- [x] Performance Improvement
2025-02-24 16:21:55 +08:00
df3d0f61bd Fix base url missing for deepseek from Tongyi. (#5294)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-24 15:43:32 +08:00
ec96426c00 Tongyi adapts deepseek. (#5285)
### What problem does this PR solve?


### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-02-24 14:04:25 +08:00
9aa222f738 Let list_chat go without kb checking. (#5280)
### What problem does this PR solve?

#5278 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-24 13:21:05 +08:00
569e40544d Refactor rerank model with dynamic batch processing and memory manage… (#5273)
…ment

### What problem does this PR solve?
Issue:https://github.com/infiniflow/ragflow/issues/5262
### Type of change

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

Co-authored-by: wenju.li <wenju.li@deepctr.cn>
2025-02-24 11:32:08 +08:00
4f2816c01c Add support to boto3 default connection (#5246)
### What problem does this PR solve?
 
This pull request includes changes to the initialization logic of the
`ChatModel` and `EmbeddingModel` classes to enhance the handling of AWS
credentials.

Use cases:
- Use env variables for credentials instead of managing them on the DB 
- Easy connection when deploying on an AWS machine

### Type of change

- [X] New Feature (non-breaking change which adds functionality)
2025-02-24 11:01:14 +08:00