2496 Commits

Author SHA1 Message Date
Edouard Hur
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
donblack01
b1a46d5adc Fix:when start with source code not in docker env report 'UnicodeDec… (#5802)
### What problem does this PR solve?

fix:when start with  source code not in docker env report
"UnicodeDecodeError: 'gbk' codec can't decode byte 0xad in position 5:
illegal multibyte sequence" in windows

### Type of change

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

Co-authored-by: tangyu <1@1.com>
2025-03-10 11:22:06 +08:00
kaiyuan Zhang
50c510d16b Fix: bugs mentioned by#5760 (#5778)
### What problem does this PR solve?

Fixed the issue of "stop deleting when encountering invalid dataset ID"

#5760

### Type of change

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

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2025-03-10 11:22:06 +08:00
刘安
8a84d1048c
TEST: Added test cases for Delete Dataset HTTP API (#5770)
### What problem does this PR solve?

1. cover dataset deletion endpoints
2. format code with ruff

### Type of change

- [x] add testcases
- [ ] style
2025-03-07 17:44:51 +08:00
Kevin Hu
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
writinwaters
ca39f5204d
Initial draft of Implemnt deep research (#5774)
### What problem does this PR solve?



### Type of change


- [x] Documentation Update
2025-03-07 17:06:49 +08:00
liwenju0
5b0e38060a
Feat:Optimize the table extraction logic in the Markdown parser: (#5663)
Enhance the recognition of both borderless and bordered Markdown tables.
Add support for extracting HTML tables, including various scenarios with
nested HTML tags. Improve performance by using conditional checks to
reduce unnecessary regular expression matching.

### What problem does this PR solve?

Optimize the table extraction logic in the Markdown parser:
Enhance the recognition of both borderless and bordered Markdown tables.
Add support for extracting HTML tables, including various scenarios with
nested HTML tags.
Improve performance by using conditional checks to reduce unnecessary
regular expression matching.

### Type of change

- [x] Performance Improvement

Co-authored-by: wenju.li <wenju.li@deepctr.cn>
2025-03-07 17:02:35 +08:00
hy89
66938e0b68
Feat(api): Add dsl parameters to control whether dsl fields are included (#5769)
1. **Issue**: When calling `list_agent_session` via the HTTP API, users
may only need to display conversation messages, and do not want to see
the associated dsl, which can be very large. Therefore, consider adding
a control option to determine whether the DSL should be returned, with
the default being to return it.

2. **Documentation Discrepancy**: In the HTTP API documentation, under
"List agent sessions," the "Response" section states that the "data"
field is a dictionary when "success" is returned. However, the actual
returned data is a list. This discrepancy has been corrected.
2025-03-07 16:58:00 +08:00
Kevin Hu
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
Kevin Hu
3418984848
Fix: meta fields updata issue, (#5764)
### What problem does this PR solve?

#4789

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-07 16:21:27 +08:00
balibabu
3c79990934
Fix: Fixed the issue that files cannot be uploaded on the file management page. #5730 (#5763)
### What problem does this PR solve?

Fix: Fixed the issue that files cannot be uploaded on the file
management page. #5730

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-07 16:09:20 +08:00
Kevin Hu
da3f279495
Fix: add the validation for parser_config. (#5755)
### What problem does this PR solve?

#5719

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-07 15:34:34 +08:00
Kevin Hu
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
Zanyatta
0e3e129a83
Fix: Resolve inconsistency in APIToken dialog_id field definition (#5749)
The `dialog_id` field was inconsistently defined:
- In the `migrate_db()` function, it was set to `null=True`.
- In the model class, it was defined as `null=False`.

This inconsistency caused an issue during the initial deployment where
the database table did not allow `dialog_id` to be null. As a result,
calling `APITokenService.save(**obj)` in `system_app.py` raised the
following error:

```
peewee.IntegrityError: null value in column "dialog_id" violates not-null constraint
```

### What problem does this PR solve?

Error: peewee.IntegrityError: null value in column "dialog_id" violates
not-null constraint

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-07 13:26:08 +08:00
Kevin Hu
c87b58511e
Fix: API empty field input. (#5748)
### What problem does this PR solve?

#5709

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-07 13:11:07 +08:00
yihong
8d61dcc8ab
Fix: can not upload file close #5730 (#5742)
### 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._

close #5730 

### 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):

Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-03-07 11:24:23 +08:00
Kevin Hu
06b29d7da4
Fix: empty description (#5747)
### What problem does this PR solve?

#5705

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-07 11:23:37 +08:00
balibabu
5229a76f68
Fix: Remove the document language parameter. #5640 (#5728)
### What problem does this PR solve?

Fix: Remove the document language parameter. #5686

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-07 11:03:58 +08:00
刘安
4f9504305a
TEST: Added test cases for Create Dataset HTTP API (#5724)
### What problem does this PR solve?

1. add test cases
2. integrate workflows/tests.yml into CI pipeline

### Type of change

- [x] add testcases
2025-03-06 20:22:17 +08:00
writinwaters
27153dde85
Updated instructions in the UI (#5733)
### What problem does this PR solve?



### Type of change


- [x] Documentation Update
2025-03-06 19:56:15 +08:00
Kevin Hu
9fc7174612
Fix: too long context during KG issue. (#5723)
### What problem does this PR solve?

#5088

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-06 19:21:07 +08:00
Kevin Hu
8fb8374dfc
Fix: delimiter issue. (#5720)
### What problem does this PR solve?

#5704

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-06 17:51:22 +08:00
Kevin Hu
ff35c140dc
Refa: remove dataset language and validate dataset name length. (#5707)
### What problem does this PR solve?

#5686
#5702

### Type of change

- [x] Refactoring
2025-03-06 17:08:28 +08:00
Kevin Hu
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
Kevin Hu
48f3f49e80
Fix: docs inconsistency. (#5695)
### What problem does this PR solve?

#5662

### Type of change

- [x] Documentation Update
2025-03-06 11:48:31 +08:00
balibabu
94d7af00b8
Fix: Remove the max token parameter. #5640 #5646 (#5693)
### What problem does this PR solve?

Fix: Remove the max token parameter. #5640 #5646

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-06 11:44:27 +08:00
Kevin Hu
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
非法操作
28296955f1
Minor: improve tips display (#5631)
### What problem does this PR solve?

1. Add the missing translations.  
![CleanShot 2025-03-05 at 10 29
32](https://github.com/user-attachments/assets/85e95372-07d9-47a1-82cf-6eb4d0e1c831)

2. Shorten overly long tips.  
![CleanShot 2025-03-05 at 10 34
49](https://github.com/user-attachments/assets/fae8ce4c-6495-4abf-958d-2febeb38b893)

### 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
- [x] Other (please describe):
2025-03-06 11:03:49 +08:00
balibabu
1b2fc3cc9a
Feat: Add rerank option to huggingface's model type drop-down box. #5658 (#5689)
### What problem does this PR solve?

Feat: Add rerank option to huggingface's model type drop-down box. #5658

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-03-06 11:03:08 +08:00
Kevin Hu
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
writinwaters
5f62f0c9d7
Miscellaneous updates (#5670)
### What problem does this PR solve?

#5625 #5614 

### Type of change


- [x] Documentation Update
2025-03-06 09:55:27 +08:00
balibabu
a54843cc65
Feat: Use react-hook-form to synchronize the data of the categorize form to the agent node. #3221 (#5665)
### What problem does this PR solve?

Feat: Use react-hook-form to synchronize the data of the categorize form
to the agent node. #3221

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-03-05 19:43:08 +08:00
yihong
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
Kevin Hu
a64f4539e7
Docs: updates. (#5661)
### What problem does this PR solve?



### Type of change

- [x] Documentation Update
2025-03-05 17:54:34 +08:00
Kevin Hu
ec68ab1c8c
Fix: search citation issue. (#5657)
### What problem does this PR solve?
#5649
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-05 17:25:47 +08:00
Kevin Hu
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
郭大鹏
78b2e0be89
fix: issue #5600 (#5645)
fix: issue https://github.com/infiniflow/ragflow/issues/5600

### What problem does this PR solve?

close issue https://github.com/infiniflow/ragflow/issues/5600 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-05 16:50:37 +08:00
balibabu
b6aded378d
Feat: The parsing method is paper and needs to display Document parser. #5467 (#5652)
### What problem does this PR solve?

Feat: The parsing method is paper and needs to display Document parser.
#5467

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-03-05 16:25:34 +08:00
Omar Leonardo Sanchez Granados
11e3f5e8b2
Feat: Upload file UI/UX enhancements (#5359)
### What problem does this PR solve?

Modifies the UX for uploading process on the website.

- Adds option to parse on creation the files
- Adds progress bar to display progress of chunk
- Adds per file feedback on uploading operation

#### Screenshots:

- Show files uploading:

![image](https://github.com/user-attachments/assets/a5693f42-8232-4d5c-a240-20ed343634a5)

- Errors on specific files

![image](https://github.com/user-attachments/assets/986a7f54-ab32-4634-89ab-a098fe1954aa)


### Type of change

- [X] New Feature (non-breaking change which adds functionality)
2025-03-05 15:20:32 +08:00
Zhichang Yu
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
Kevin Hu
02c955babb
Fix: parameter error. (#5641)
### What problem does this PR solve?

#5600

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-05 14:37:51 +08:00
非法操作
ca04ae9540
Minor: improve doc and rm unused file (#5634)
### What problem does this PR solve?

The `ocr.res` file is already included in the model directory
`rag/res/deepdoc`, but it doesn't seem to be utilized here.

### Type of change

- [x] Documentation Update
2025-03-05 12:59:54 +08:00
hy89
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
非法操作
47684fa17c
Fix: image file can't preview (#5626)
### What problem does this PR solve?

![CleanShot 2025-03-05 at 10 12
28](https://github.com/user-attachments/assets/412b1663-5d65-4dca-9137-63d0ec5eaadd)
the preview botton of image not work for me.

request url:
`http://127.0.0.1:9222/document/af570920f80e11efb8e967fd67f0d8c7?ext=jpg&prefix=file`
response: `{"code":401,"data":null,"message":"<Unauthorized '401:
Unauthorized'>"}`


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-05 11:30:41 +08:00
yihong
148a7e7002
fix: issue #5600 (#5620)
### What problem does this PR solve?

close issue #5600 

### Type of change

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

Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-03-05 11:10:04 +08:00
汪威
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
kunyi-yang
555c70672e
Fix:Fix the bug of incorrectly gets the APIToken. (#5597)
### What problem does this PR solve?

Fix the issue where, when getting a user's APIToken, if the user is part
of another user's team, it incorrectly gets the Team owner's APIToken
instead.


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-04 19:35:42 +08:00
balibabu
850e218051
Feat: Render DynamicCategorize with shadcn-ui. #3221 (#5610)
### What problem does this PR solve?

Feat: Render DynamicCategorize with shadcn-ui. #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-03-04 19:31:32 +08:00
writinwaters
fb4b5b0a06
Added 0.17.0 release notes (#5608)
### What problem does this PR solve?



### Type of change


- [x] Documentation Update
2025-03-04 19:21:28 +08:00
balibabu
f256e1a59a
Feat: Render MessageForm with shadcn-ui. #3221 (#5596)
### What problem does this PR solve?

Feat: Render MessageForm with shadcn-ui. #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-03-04 15:47:05 +08:00