71 Commits

Author SHA1 Message Date
liuhua
d42362deb6
Add api for sessions and add max_tokens for tenant_llm (#3472)
### What problem does this PR solve?

Add api for sessions and add max_tokens for tenant_llm

### Type of change

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

---------

Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
2024-11-19 14:51:33 +08:00
shizzgar
4b3eeaa6ef
Added LocalAI support for rerank models (#3446)
### What problem does this PR solve?

Hi there!
LocalAI added support of rerank models
https://localai.io/features/reranker/

I've implemented LocalAIRerank class (typically copied it from
OpenAI_APIRerank class).
Also, LocalAI model response with 500 error code if len of "documents"
is less than 2 in similarity check.
So I've added the second "document" on RERANK model connection check in
`api/apps/llm_app.py`.

### Type of change

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

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2024-11-18 12:05:52 +08:00
Jin Hai
1e90a1bf36
Move settings initialization after module init phase (#3438)
### What problem does this PR solve?

1. Module init won't connect database any more.
2. Config in settings need to be used with settings.CONFIG_NAME

### Type of change

- [x] Refactoring

Signed-off-by: jinhai <haijin.chn@gmail.com>
2024-11-15 17:30:56 +08:00
Zhichang Yu
30f6421760
Use consistent log file names, introduced initLogger (#3403)
### What problem does this PR solve?

Use consistent log file names, introduced initLogger

### 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):
2024-11-14 17:13:48 +08:00
Zhichang Yu
a2a5631da4
Rework logging (#3358)
Unified all log files into one.

### What problem does this PR solve?

Unified all log files into one.

### Type of change

- [x] Refactoring
2024-11-12 17:35:13 +08:00
Zhichang Yu
185c6a0c71
Unified API response json schema (#3170)
### What problem does this PR solve?

Unified API response json schema

### Type of change

- [x] Refactoring
2024-11-05 11:02:31 +08:00
0000sir
4991107822
Fix keys of Xinference deployed models, especially has the same model name with public hosted models. (#2832)
### What problem does this PR solve?

Fix keys of Xinference deployed models, especially has the same model
name with public hosted models.

### Type of change

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

---------

Co-authored-by: 0000sir <0000sir@gmail.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2024-10-16 10:21:08 +08:00
Kevin Hu
190eea7097
trival (#2808)
### What problem does this PR solve?



### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-10-11 15:33:38 +08:00
Kevin Hu
2d1c83da59
fix LIGHTEN issue (#2806)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-10-11 15:01:27 +08:00
JobSmithManipulation
18f80743eb
support api-version and change default-model in adding azure-openai and openai (#2799)
### What problem does this PR solve?
#2701 #2712 #2749

### Type of change
-[x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2024-10-11 11:26:42 +08:00
JobSmithManipulation
96f56a3c43
add huggingface model (#2624)
### What problem does this PR solve?

#2469

### Type of change

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

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2024-09-27 19:15:38 +08:00
Kevin Hu
7bb28ca2bd
add lighten control (#2567)
### What problem does this PR solve?

#2295

### Type of change

- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
2024-09-24 19:22:01 +08:00
Kevin Hu
d40041cc82
refine multi-turn chat in agent (#2560)
### What problem does this PR solve?

#2484

### Type of change

- [x] Performance Improvement
- [ ] Other (please describe):
2024-09-24 16:20:19 +08:00
Kevin Hu
7b3099b1a1
add an API of delete llm supplier (#2556)
### What problem does this PR solve?

#1853

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-09-24 15:24:15 +08:00
liuhua
d9c2a128a5
SparkTTS (#2535)
### What problem does this PR solve?

SparkTTS

### Type of change

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

---------

Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
2024-09-24 12:15:12 +08:00
Kevin Hu
a44f1f735d
fix self deployed llm lost (#2510)
### What problem does this PR solve?

#2509 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-09-20 10:41:25 +08:00
Kevin Hu
5968f148bc
refactor add LLM (#2508)
### What problem does this PR solve?

#2487

### Type of change

- [x] Refactoring
2024-09-20 10:20:35 +08:00
yungongzi
4f962d6bff
BugFix: Fixed api_key generation error for VolcEngine (#2502)
BugFix: Fixed api_key generation error for VolcEngine with python's
f-string syntax

### 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)

Co-authored-by: 海贼宅 <stu_xyx@163.com>
2024-09-20 10:03:43 +08:00
Kevin Hu
b5d1d2fec4
refine TTS (#2500)
### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-09-19 19:15:16 +08:00
_Chenbing
af0b4b0828
fix(Add model api): Add VolcEngine to create api_key format error (#2490)
### What problem does this PR solve?


Add VolcEngine to create api_key format error
When constructing the json string, there was an extra "," at the end,
which caused a formatting error. This commit fixed the problem.


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-09-19 15:10:49 +08:00
Kevin Hu
66c54e75f3
add default model types (#2342)
### What problem does this PR solve?


### Type of change

- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
2024-09-10 11:39:44 +08:00
Kevin Hu
f60dfffb4b
add model types to factories API (#2341)
### What problem does this PR solve?

### Type of change

- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
2024-09-10 11:26:01 +08:00
Kevin Hu
0fe19f3fbc
fix QWenSeq2txt bug (#2245)
### What problem does this PR solve?

#2243

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-09-04 18:25:43 +08:00
黄腾
87a998e9e5
fix tts add bug (#2224)
### What problem does this PR solve?

fix tts add bug

### Type of change

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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-09-03 18:40:20 +08:00
黄腾
5decdde182
add support for Google Cloud (#2175)
### What problem does this PR solve?

#1853 add support for Google Cloud

### Type of change


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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-09-02 12:06:41 +08:00
黄腾
12975cf128
Fix some security vulnerabilities. (#2160)
### What problem does this PR solve?

Fix some security vulnerabilities

### Type of change

- [x] Performance Improvement

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-08-29 16:21:32 +08:00
黄腾
2da4e7aa46
add support for Tencent Cloud ASR (#2102)
### What problem does this PR solve?

add support for Tencent Cloud ASR

### Type of change

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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2024-08-27 11:47:11 +08:00
黄腾
6b7c028578
add support for TTS model (#2095)
### What problem does this PR solve?

add support for TTS model
#1853

### Type of change

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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2024-08-26 15:19:43 +08:00
yungongzi
7539d142a9
VolcEngine SDK V3 adaptation (#2082)
1) Configuration interface update
2) Back-end adaptation API update
Note: The official no longer supports the Skylark1/2 series, and all
have been switched to the Doubao series


![image](https://github.com/user-attachments/assets/f6fd8782-0cdf-4c0b-ac8f-9eb130f667a5)

### 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):

Co-authored-by: 海贼宅 <stu_xyx@163.com>
2024-08-26 13:34:29 +08:00
黄腾
733219cc3f
add support for Baidu yiyan (#2049)
### What problem does this PR solve?

add support for Baidu yiyan

### Type of change

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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-08-22 16:45:15 +08:00
黄腾
be431449bd
add support for XunFei Spark (#2017)
### What problem does this PR solve?

#1853  add support for XunFei Spark

### Type of change

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

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-08-20 16:56:42 +08:00
黄腾
6f438e0a49
add support for Tencent Hunyuan (#2015)
### What problem does this PR solve?

#1853 

### Type of change


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

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-08-20 15:27:13 +08:00
黄腾
79426fc41f
add support for Replicate (#1980)
### What problem does this PR solve?

#1853  add support for Replicate

### Type of change


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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-08-19 10:36:57 +08:00
Jin Hai
6b3a40be5c
Format file format from Windows/dos to Unix (#1949)
### What problem does this PR solve?

Related source file is in Windows/DOS format, they are format to Unix
format.

### Type of change

- [x] Refactoring

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2024-08-15 09:17:36 +08:00
黄腾
94cb66ba80
add support for TogetherAI (#1890)
### What problem does this PR solve?

#1853 add support for TogetherAI

### Type of change

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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2024-08-12 10:15:21 +08:00
黄腾
411c645134
Enhance the robustness of the code (#1879)
### What problem does this PR solve?

Enhance the robustness of the code

### Type of change

- [x] Refactoring

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-08-09 10:18:08 +08:00
Tong Liu
f43db8bc51
fix code injection (#1868)
### What problem does this PR solve?

fix code injection in https://github.com/infiniflow/ragflow/issues/1860,
developers can have a check to see if the fix works as expected.

### Type of change

Vulnerability Fix
2024-08-08 13:44:55 +08:00
Kevin Hu
1d5a9b74ff
fix add slef base url openai error (#1854)
### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-08-07 19:16:46 +08:00
黄腾
b67484e77d
add supprot for OpenAI-API-Compatible llm (#1787)
### What problem does this PR solve?

#1771  add supprot for OpenAI-API-Compatible 

### Type of change

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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-08-06 16:20:21 +08:00
黄腾
753c13d76f
fix add local vision llm error when cannot download test pic (#1732)
### What problem does this PR solve?

#1726   fix add local vision llm  error when cannot download test pic

### Type of change

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

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-07-29 11:52:59 +08:00
黄腾
d96348eb22
add support for LM Studio (#1663)
### What problem does this PR solve?

#1602 

### Type of change

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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-07-24 12:46:43 +08:00
黄腾
3fcdba1683
add support for LocalAI (#1608)
### What problem does this PR solve?

#762 

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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-07-19 15:50:28 +08:00
黄腾
75086f41a9
'load llm infomation from a json file and add support for OpenRouter' (#1533)
### What problem does this PR solve?

#1467 

### Type of change

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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-07-16 15:19:43 +08:00
Kevin Hu
99f7bbaaa2
fix bugs of rerank model with xinference (#1481)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-07-12 12:33:37 +08:00
H
6144a109ab
Add Support for AWS Bedrock (#1408)
### What problem does this PR solve?

#308 

### Type of change

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

---------

Co-authored-by: KevinHuSh <kevinhu.sh@gmail.com>
2024-07-08 09:37:34 +08:00
KevinHuSh
758eb03ccb
fix jina adding issure and term weight refinement (#974)
### What problem does this PR solve?

#724 #162

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
2024-05-29 19:38:57 +08:00
KevinHuSh
614defec21
add rerank model (#969)
### What problem does this PR solve?

feat: add rerank models to the project #724 #162

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-05-29 16:50:02 +08:00
yungongzi
eb51ad73d6
Add support for VolcEngine - the current version supports SDK2 (#885)
- The main idea is to assemble **ak**, **sk**, and **ep_id** into a
dictionary and store it in the database **api_key** field
- I don’t know much about the front-end, so I learned from Ollama, which
may be redundant.

### Configuration method

- model name

- Format requirements: {"VolcEngine model name":"endpoint_id"}
    - For example: {"Skylark-pro-32K":"ep-xxxxxxxxx"}
    
- Volcano ACCESS_KEY
- Format requirements: VOLC_ACCESSKEY of the volcano engine
corresponding to the model

- Volcano SECRET_KEY
- Format requirements: VOLC_SECRETKEY of the volcano engine
corresponding to the model
    
### 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)
2024-05-23 11:15:29 +08:00
KevinHuSh
aa1c915d6e
support gpt-4o (#773)
### What problem does this PR solve?
#771 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-05-15 11:16:08 +08:00
Jin Hai
d7744f5870
Refactor method name (#760)
### What problem does this PR solve?

#757

### Type of change

- [x] Refactoring

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2024-05-14 14:48:15 +08:00