Commit Graph

3044 Commits

Author SHA1 Message Date
5d6bf2224a Fix: Opensearch chunk management (#7802)
### What problem does this PR solve?

This PR solve the problems metioned in the
pr(https://github.com/infiniflow/ragflow/pull/7140) which is also
submitted by me

### 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):


### Introduction
I fixed the problems when using OpenSearch as the DOC_ENGINE, the
failures of pytest and the wrong API's return.
Mainly about delete chunk, list chunks, update chunk, retrieval chunk.
The pytest comand "cd sdk/python && uv sync --python 3.10 --group test
--frozen && source .venv/bin/activate && cd test/test_http_api &&
DOC_ENGINE=opensearch pytest test_chunk_management_within_dataset -s
--tb=short " is finally successful.

###Others
As some changes between Elasticsearch And Opensearch differ, some pytest
results about OpenSearch are correct and resonable. However, some pytest
params (skipif params) are incompatible. So I changed some pytest params
about skipif.

As a search engine programmer, I will still focus on the usage of vector
databases (especially OpenSearch) for the RAG stuff.
Thanks for your review
2025-05-26 16:57:58 +08:00
c09bd9fe4a Feat: Convert the data of the messge operator to a string array #3221 (#7853)
### What problem does this PR solve?

Feat: Convert the data of the messge operator to a string array #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-26 16:56:50 +08:00
c7db0eaca6 Optimize Tag Removal Method (#7847)
### 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):
2025-05-26 16:56:33 +08:00
78fa37f8ae Feat: Upgrade react-hook-form to the latest version to solve the problem that appending a useFieldArray entry cannot trigger the watch callback function #3221 (#7849)
### What problem does this PR solve?

Feat: Upgrade react-hook-form to the latest version to solve the problem
that appending a useFieldArray entry cannot trigger the watch callback
function #3221

[issue: watch is not called when appending first item to Field Array
#12370](https://github.com/react-hook-form/react-hook-form/issues/12370)

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-26 12:21:19 +08:00
be83074131 Fix: restore task limiter. (#7844)
### What problem does this PR solve?

Close #7828

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-05-26 10:59:01 +08:00
1f756947da Docs: Added code component reference (#7821)
### What problem does this PR solve?

### Type of change

- [x] Documentation Update
2025-05-26 10:39:51 +08:00
ae171956e8 Fix:Setting the message_history_window_size to 0 does not take effect (#7842)
### What problem does this PR solve?

Close #7830
The caller method should already have code to handle this.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-05-26 10:28:46 +08:00
1f32e6e4f4 Fix: list out of boundary (#7843)
### What problem does this PR solve?

Close #7837
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-05-26 10:28:36 +08:00
2f4d803db1 Delete Corresponding Minio Bucket When Deleting a Knowledge Base (#7841)
### What problem does this PR solve?

Delete Corresponding Minio Bucket When Deleting a Knowledge Base
[issue #4113 ](https://github.com/infiniflow/ragflow/issues/4113)

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
2025-05-26 10:02:51 +08:00
552023ee4b Fix: catch non-begin component output (#7827)
### What problem does this PR solve?

Catch non-begin component output

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
v0.19.x
2025-05-23 20:29:23 +08:00
6c9b8ec860 Refa: update gemini2.5 (#7822)
### What problem does this PR solve?

Update gemini2.5

### Type of change

- [x] Refactoring
2025-05-23 20:29:10 +08:00
f9e6ad86b7 Fix: Fixed the issue that the script text of the code operator is not displayed after refreshing the page after saving the script text of the code operator #4977 (#7825)
### What problem does this PR solve?

Fix: Fixed the issue that the script text of the code operator is not
displayed after refreshing the page after saving the script text of the
code operator #4977

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-05-23 18:57:45 +08:00
e604634d2a Feat: Refactor the MessageForm with shadcn #3221 (#7820)
### What problem does this PR solve?

Feat: Refactor the MessageForm with shadcn #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-23 18:45:13 +08:00
590b9dabab Docs: update for v0.19.0 (#7823)
### What problem does this PR solve?

update for v0.19.0

### Type of change

- [x] Documentation Update
2025-05-23 18:25:47 +08:00
c283ea57fd Docs: Added v0.19.0 release notes (#7818)
### What problem does this PR solve?

### Type of change

- [x] Documentation Update
2025-05-23 18:25:33 +08:00
50ff16e7a4 Feat: add claude4 models (#7809)
### What problem does this PR solve?

Add claude4 models.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-05-23 18:25:13 +08:00
453287b06b Feat: more robust fallbacks for citations (#7801)
### What problem does this PR solve?

Add more robust fallbacks for citations

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
2025-05-23 18:24:55 +08:00
e166f132b3 Feat: change default models (#7777)
### What problem does this PR solve?

change default models to buildin models
https://github.com/infiniflow/ragflow/issues/7774

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-05-23 18:21:25 +08:00
42f4d4dbc8 Fix: wrong type hint (#7738)
### What problem does this PR solve?

Wrong hint type. #7729.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-05-23 18:21:06 +08:00
7cb8368e0f Feat: sandox enhancement (#7739)
### What problem does this PR solve?

1. Add sandbox options for max memory and timeout.
2. ​Malicious code detection for Python only.​​

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-05-23 18:20:51 +08:00
Sol
0d7cfce6e1 Update rag/nlp/query.py (#7816)
### What problem does this PR solve?
Fix tokenizer resulting in low recall

![37743d3a495f734aa69f1e173fa77457](https://github.com/user-attachments/assets/1394757e-8fcb-4f87-96af-a92716144884)

![4aba633a17f34269a4e17e84fafb34c4](https://github.com/user-attachments/assets/a1828e32-3e17-4394-a633-ba3f09bd506d)

![image](https://github.com/user-attachments/assets/61308f32-2a4f-44d5-a034-d65bbec554ef)



### Type of change

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

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2025-05-23 17:13:37 +08:00
2d7c1368f0 Feat: add code_executor_manager (#7814)
### What problem does this PR solve?

Add code_executor_manager. #4977.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-05-23 16:33:38 +08:00
db4371c745 Fix: Improve First Chunk Size (#7806)
### What problem does this PR solve?

https://github.com/infiniflow/ragflow/issues/7790

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-05-23 14:30:19 +08:00
e6cd799d8a Feat: Translate the begin operator #3221 (#7811)
### What problem does this PR solve?

Feat: Translate the begin operator #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-23 14:18:27 +08:00
ab29b58316 Docs: Added instructions on cross-language search (#7812)
### What problem does this PR solve?



### Type of change


- [x] Documentation Update
2025-05-23 14:18:14 +08:00
3f037c9786 Feat: Reconstruct the QueryTable of BeginForm using shandcn #3221 (#7807)
### What problem does this PR solve?

Feat: Reconstruct the QueryTable of BeginForm using shandcn #3221
### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-23 12:31:05 +08:00
Sol
53b991aa0e Fix backquotes in text2sql causing execution errors (#7793)
### What problem does this PR solve?
Remove the backquotes in the sql generated by LLM to prevent it from
causing execution errors.

![image](https://github.com/user-attachments/assets/40d57ef7-b812-402a-b469-5793e466b83d)


![image](https://github.com/user-attachments/assets/d0a9bc17-ff5a-43cb-90cb-b2b3827b00b0)


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-05-23 09:49:45 +08:00
9e80f39caa Feat: Synchronize BeginForm's query data to the canvas #3221 (#7798)
### What problem does this PR solve?

Feat: Synchronize BeginForm's query data to the canvas #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-23 09:49:14 +08:00
bdc2b74e8f Fix baidu request error (#7799)
### What problem does this PR solve?

### Type of change

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

Co-authored-by: xiaohzho <xiaohzho@cisco.com>
2025-05-23 09:48:55 +08:00
1fd92e6bee Docs: RAGFlow does not suppport batch metadata setting (#7795)
### 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] Documentation Update
2025-05-22 17:02:23 +08:00
02fd381072 Feat: Verify the parameters of the begin operator #3221 (#7794)
### What problem does this PR solve?

Feat: Verify the parameters of the begin operator #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-22 16:58:47 +08:00
b6f3a6a68a Feat: Refactor BeginForm with shadcn #3221 (#7792)
### What problem does this PR solve?

Feat: Refactor BeginForm with shadcn #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-22 15:33:40 +08:00
ae70512f5d fix:When creating a new assistant, an avatar was uploaded, but when selecting the assistant to start a new chat, the default avatar still appears in the chat window instead of the one uploaded during creation (#7769)
### 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] 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):
2025-05-22 11:50:02 +08:00
d4a123d6dd Fix: resolve regex library warnings (#7782)
### What problem does this PR solve?
This small PR resolves the regex library warnings showing in Python3.11:
```python
DeprecationWarning: 'count' is passed as positional argument
```

### 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):

Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
2025-05-22 10:06:28 +08:00
ce816edb5f Fix: improve task cancel lag (#7765)
### What problem does this PR solve?

https://github.com/infiniflow/ragflow/issues/7761

but it may be difficult to achieve 0 delay (which need to pass the
cancel token to all parts)

Another solution is just 0 delay effect at UI.
And task will stop latter

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-05-22 09:28:08 +08:00
ac2643700b Feat: Add return value widget to CodeForm #3221 (#7776)
### What problem does this PR solve?
Feat: Add return value widget  to CodeForm #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-21 19:35:27 +08:00
558b252c5a Feat: Switching the programming language of the code operator will switch the corresponding language template #3221 (#7770)
### What problem does this PR solve?

Feat: Switching the programming language of the code operator will
switch the corresponding language template #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-21 18:22:06 +08:00
754a5e1cee Feat: Fixed the issue where the page would refresh continuously when opening the sheet on the right side of the canvas #3221 (#7756)
### What problem does this PR solve?

Feat: Fixed the issue where the page would refresh continuously when
opening the sheet on the right side of the canvas #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-21 17:03:16 +08:00
e3e7c7ddaa Feat: delete useless image blobs when task executor meet edge cases (#7727)
### What problem does this PR solve?

delete useless image blobs when the task executor meets edge cases

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-05-21 10:22:30 +08:00
76b278af8e 0519 pdfparser (#7747)
### What problem does this PR solve?


### Type of change


- [x] Documentation Update
2025-05-20 19:41:55 +08:00
1c6320828c Feat: Rename agent #3221 (#7740)
### What problem does this PR solve?

Feat: Rename agent #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-20 19:13:19 +08:00
d72468426e Feat: Render the agent list page by page #3221 (#7736)
### What problem does this PR solve?

Feat: Render the agent list page by page #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-20 16:03:55 +08:00
796f4032b8 Feat: Migrate the code operator to the new agent. #3221 (#7731)
### What problem does this PR solve?

Feat: Migrate the code operator to the new agent. #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-20 15:30:56 +08:00
1ae7b942d9 Feat: The image displayed in the reply message can also be clicked to display the location of the source document where the slice is located #7623 (#7723)
### What problem does this PR solve?

Feat: The image displayed in the reply message can also be clicked to
display the location of the source document where the slice is located
#7623

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-20 10:40:53 +08:00
fed1221302 Refa: HTTP API list datasets / test cases / docs (#7720)
### What problem does this PR solve?

This PR introduces Pydantic-based validation for the list datasets HTTP
API, improving code clarity and robustness. Key changes include:

Pydantic Validation
Error Handling
Test Updates
Documentation Updates

### Type of change

- [x] Documentation Update
- [x] Refactoring
2025-05-20 09:58:26 +08:00
6ed81d6774 Feat: Add OAuth state parameter for CSRF protection (#7709)
### What problem does this PR solve?

Add OAuth `state` parameter for CSRF protection:
- Updated `get_authorization_url()` to accept an optional state
parameter
- Generated a unique state value during OAuth login and stored in
session
- Verified state parameter in callback to ensure request legitimacy

This PR follows OAuth 2.0 security best practices by ensuring that the
authorization request originates from the same user who initiated the
flow.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-05-20 09:40:31 +08:00
115850945e Fix:When you create a new API module named xxxa_api, the access route will become xxx instead of xxxa. For example, when I create a new API module named 'data_api', the access route will become 'dat' instead of 'data (#7325)
### What problem does this PR solve?

Fix:When you create a new API module named xxxa_api, the access route
will become xxx instead of xxxa. For example, when I create a new API
module named 'data_api', the access route will become 'dat' instead of
'data'
Fix:Fixed the issue where the new knowledge base would not be renamed
when there was a knowledge base with the same name

### Type of change

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

---------

Co-authored-by: tangyu <1@1.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2025-05-20 09:39:26 +08:00
8e87436725 Feat: Modify the Python language template code of the code operator #4977 (#7714)
### What problem does this PR solve?

Feat: Modify the Python language template code of the code operator
#4977
### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2025-05-19 19:34:43 +08:00
e8e2a95165 Refa: more fallbacks for bad citation format (#7710)
### What problem does this PR solve?

More fallbacks for bad citation format

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2025-05-19 19:34:05 +08:00
b908c33464 Fix: uncaptured image data with position information (#7683)
### What problem does this PR solve?

Fixed uncaptured figure data with position information. #7466, #7681

### Type of change

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

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2025-05-19 19:33:28 +08:00