Commit Graph

1098 Commits

Author SHA1 Message Date
5c81e01de5 Fix: incorrect async chat streamly output (#11679)
### What problem does this PR solve?

Incorrect async chat streamly output. #11677.

Disable beartype for #11666.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-12-03 11:15:45 +08:00
a6681d6366 Revert "Refa: make RAGFlow more asynchronous 2" (#11669)
Reverts infiniflow/ragflow#11664
2025-12-02 19:42:05 +08:00
627c11c429 Refa: make RAGFlow more asynchronous 2 (#11664)
### What problem does this PR solve?

Make RAGFlow more asynchronous 2. #11551, #11579, #11619.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
- [x] Performance Improvement
2025-12-02 18:57:07 +08:00
4ba17361e9 feat: improve presentation PdfParser (#11639)
The old presentation PdfParser lost table format after parse

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-12-02 17:35:14 +08:00
c946858328 Feat: add mineru auto installer (#11649)
### What problem does this PR solve?

Feat: add mineru auto installer

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-12-02 17:29:26 +08:00
2ffe6f7439 Import rag_tokenizer from Infinity (#11647)
### What problem does this PR solve?

- Original rag/nlp/rag_tokenizer.py is put to Infinity and infinity-sdk
via https://github.com/infiniflow/infinity/pull/3117 .
Import rag_tokenizer from infinity and inherit from
rag_tokenizer.RagTokenizer in new rag/nlp/rag_tokenizer.py.

- Bump infinity to 0.6.8

### Type of change
- [x] Refactoring
2025-12-02 14:59:37 +08:00
a713f54732 Refa: add MiniMax-M2 and remove deprecated MiniMax models (#11642)
### What problem does this PR solve?

Add MiniMax-M2 and remove deprecated models.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
2025-12-02 14:43:44 +08:00
b8c0fb4572 Feat:new api /sequence2txt and update QWenSeq2txt (#11643)
### What problem does this PR solve?
change:
new api /sequence2txt,
update QWenSeq2txt and ZhipuSeq2txt

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-12-02 11:17:31 +08:00
d1e172171f Refactor: better describe how to get prefix for sync data source (#11636)
### What problem does this PR solve?

better describe how to get prefix for sync data source

### Type of change

- [x] Refactoring
2025-12-01 17:46:44 +08:00
81ae6cf78d Feat: support uploading in dialog. (#11634)
### What problem does this PR solve?

#9590

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-12-01 16:54:57 +08:00
41cff3e09e Fix: jina embedding issue (#11628)
### What problem does this PR solve?

Fix: jina embedding issue #11614 
Feat: Add jina embedding v4

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-12-01 14:24:35 +08:00
b6c4722687 Refa: make RAGFlow more asynchronous (#11601)
### What problem does this PR solve?

Try to make this more asynchronous. Verified in chat and agent
scenarios, reducing blocking behavior. #11551, #11579.

However, the impact of these changes still requires further
investigation to ensure everything works as expected.

### Type of change

- [x] Refactoring
2025-12-01 14:24:06 +08:00
6ea4248bdc Feat: support parent-child in search procedure. (#11629)
### What problem does this PR solve?

#7996

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-12-01 14:03:09 +08:00
88a28212b3 Fix: Table parse method issue. (#11627)
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-12-01 12:42:35 +08:00
9d0309aedc Fix: [MinerU] Missing output file (#11623)
### What problem does this PR solve?

Add fallbacks for MinerU output path. #11613, #11620.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-12-01 12:17:43 +08:00
7499608a8b feat: add Redis username support (#11608)
### What problem does this PR solve?

Support for Redis 6+ ACL authentication (username)

close #11606 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
2025-12-01 11:26:20 +08:00
80f6d22d2a Fix typos (#11607)
### What problem does this PR solve?

Fix typos

### Type of change

- [x] Fix typos
2025-12-01 09:49:46 +08:00
14616cf845 Feat: add child parent chunking method in backend. (#11598)
### What problem does this PR solve?

#7996

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-28 19:25:32 +08:00
dbdda0fbab Feat: optimize meta filter generation for better structure handling (#11586)
### What problem does this PR solve?

optimize meta filter generation for better structure handling

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-28 13:30:53 +08:00
cf7fdd274b Feat: add gmail connector (#11549)
### 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] New Feature (non-breaking change which adds functionality)
2025-11-28 13:09:40 +08:00
982ed233a2 Fix: doc_aggs not correctly returned when no chunks retrieved. (#11578)
### What problem does this PR solve?

Fix: doc_aggs not correctly returned when no chunks retrieved.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-28 13:09:05 +08:00
8604c4f57c Feat: add GPT-5.1, GPT‑5.1 Instant and Claude-Opus-4.5 (#11559)
### What problem does this PR solve?

Add GPT-5.1, GPT‑5.1 Instant and Claude-Opus-4.5. #11548

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-27 17:59:17 +08:00
856201c0f2 Fix ft_title_rag_fine (#11555)
### What problem does this PR solve?

Fix ft_title_rag_fine

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-27 10:26:08 +08:00
9d8b96c1d0 Feat: add context for figure and table (#11547)
### What problem does this PR solve?

Add context for figure table.



![demo_figure_table_context](https://github.com/user-attachments/assets/61b37fac-e22e-40a4-9665-9396c7b4103e)


`==================()` for demonstrating purpose. 
### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-27 10:21:44 +08:00
12979a3f21 feat: improve metadata handling in connector service (#11421)
### What problem does this PR solve?

- Update sync data source to handle metadata properly

### Type of change

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

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2025-11-26 19:55:48 +08:00
2fd5ac1031 Feat: Add Webdav storage as data source (#11422)
### What problem does this PR solve?

This PR adds webdav storage as data source for data sync service.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-26 14:14:42 +08:00
40e84ca41a Use Infinity single-field-multi-index (#11444)
### What problem does this PR solve?

Use Infinity single-field-multi-index

### Type of change

- [x] Refactoring
- [x] Performance Improvement
2025-11-26 11:06:37 +08:00
74e0b58d89 Fix: excel default optimization. (#11519)
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-25 19:54:20 +08:00
7c20c964b4 Fix: incorrect image merging for naive markdown parser (#11520)
### What problem does this PR solve?

Fix incorrect image merging for naive markdown parser. #9349 


[ragflow_readme.webm](https://github.com/user-attachments/assets/ca3f1e18-72b6-4a4c-80db-d03da9adf8dc)

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-25 19:54:06 +08:00
915e385244 Fix: uv lock updates (#11511)
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-25 16:01:12 +08:00
f5faf0c94f Feat: support operator in/not in for metadata filter. (#11503)
### What problem does this PR solve?

#11376 #11378

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-25 12:44:26 +08:00
bcd70affb5 Fix: unexpected parameter. (#11497)
### What problem does this PR solve?

#11489

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-25 11:17:27 +08:00
41665b0865 Refactor: Email parser use with to handle buffer (#11496)
### What problem does this PR solve?
 Email parser use with to handle buffer

### Type of change

- [x] Refactoring
2025-11-25 10:03:37 +08:00
d1744aaaf3 Feat: add datasource Dropbox (#11488)
### What problem does this PR solve?

Add datasource Dropbox.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-25 09:40:03 +08:00
f0a14f5fce Add Moodle data source integration (#11325)
### What problem does this PR solve?

This PR adds a native Moodle connector to sync content (courses,
resources, forums, assignments, pages, books) into RAGFlow.

### Type of change

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

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2025-11-21 19:58:49 +08:00
174a2578e8 Feat: add auth header for Ollama chat model (#11452)
### What problem does this PR solve?

Add auth header for Ollama chat model. #11350

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-21 19:47:06 +08:00
db0f6840d9 Feat: ignore chunk size when using custom delimiters (#11434)
### What problem does this PR solve?

Ignore chunk size when using custom delimiter.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-21 14:36:26 +08:00
971c1bcba7 Fix: missing parameters in by_plaintext method for PDF naive mode (#11408)
### What problem does this PR solve?

FIx: missing parameters in by_plaintext method for PDF naive mode

### Type of change

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

---------

Co-authored-by: lih <dev_lih@139.com>
2025-11-21 09:33:36 +08:00
d3d2ccc76c Feat: add more chunking method (#11413)
### What problem does this PR solve?

Feat: add more chunking method #11311

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-20 19:07:17 +08:00
b846a0f547 Fix: incorrect retrieval total count with pagination enabled (#11400)
### What problem does this PR solve?

Incorrect retrieval total count with pagination enabled.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-20 15:35:09 +08:00
06cef71ba6 Feat: add or logic operations for meta data filters. (#11404)
### What problem does this PR solve?

#11376 #11387

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-20 14:31:12 +08:00
420c97199a Feat: Add TCADP parser for PPTX and spreadsheet document types. (#11041)
### What problem does this PR solve?

- Added TCADP Parser configuration fields to PDF, PPT, and spreadsheet
parsing forms
- Implemented support for setting table result type (Markdown/HTML) and
Markdown image response type (URL/Text)
- Updated TCADP Parser to handle return format settings from
configuration or parameters
- Enhanced frontend to dynamically show TCADP options based on selected
parsing method
- Modified backend to pass format parameters when calling TCADP API
- Optimized form default value logic for TCADP configuration items
- Updated multilingual resource files for new configuration options

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-20 10:08:42 +08:00
38234aca53 feat: add OceanBase doc engine (#11228)
### What problem does this PR solve?

Add OceanBase doc engine. Close #5350

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-20 10:00:14 +08:00
1c06ec39ca fix cohere rerank base_url default (#11353)
### What problem does this PR solve?

**Cohere rerank base_url default handling**

- Background: When no rerank base URL is configured, the settings
pipeline was passing an empty string through RERANK_CFG →
TenantLLMService → CoHereRerank, so the Cohere client received
base_url="" and produced “missing protocol” errors during rerank calls.

- What changed: The CoHereRerank constructor now only forwards base_url
to the Cohere client when it isn’t empty/whitespace, causing the client
to fall back to its default API endpoint otherwise.

- Why it matters: This prevents invalid URL construction in the rerank
workflow and keeps tests/sanity checks that rely on the default Cohere
endpoint from failing when no custom base URL is specified.

### Type of change

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

Co-authored-by: Philipp Heyken Soares <philipp.heyken-soares@am.ai>
2025-11-20 09:46:39 +08:00
e8fe580d7a Feat: add Gemini 3 Pro preview (#11361)
### What problem does this PR solve?

Add Gemini 3 Pro preview.

Change `GenerativeModel` to `genai`.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-19 13:17:22 +08:00
d1716d865a Feat: Alter flask to Quart for async API serving. (#11275)
### What problem does this PR solve?

#11277

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-18 17:05:16 +08:00
fea157ba08 Fix: manual parser with mineru (#11336)
### What problem does this PR solve?

Fix: manual parser with mineru #11320
Fix: missing parameter in mineru #11334
Fix: add outlines parameter for pdf parsers

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-18 15:22:52 +08:00
0db00f70b2 Fix: add describe_image_with_prompt for ZHIPU AI (#11317)
### What problem does this PR solve?

Fix: add describe_image_with_prompt for ZHIPU AI  #11289 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-18 13:09:39 +08:00
3fcf2ee54c feat: add new LLM provider Jiekou.AI (#11300)
### 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] New Feature (non-breaking change which adds functionality)

Co-authored-by: Jason <ggbbddjm@gmail.com>
2025-11-17 19:47:46 +08:00
7264fb6978 Fix: concat images in word document. (#11310)
### What problem does this PR solve?

Fix: concat images in word document. Partially solved issues in #11063 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-17 19:38:26 +08:00