81 Commits

Author SHA1 Message Date
Zhichang Yu
d19f059f34
Detect invalid response from api.siliconflow.cn (#3792)
### What problem does this PR solve?

Detect invalid response from api.siliconflow.cn. Close #2643

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-12-02 12:55:05 +08:00
devMls
59a5813f1b
add jina new models in jina connector (#3770)
### What problem does this PR solve?

add new models in jinna connector, to allow use models that support
multilingual models

### Type of change

- [X] Other (please describe): new connectors no breaking change
2024-12-02 10:06:39 +08:00
Kevin Hu
57208d8e53
Fix batch size issue. (#3675)
### What problem does this PR solve?

#3657

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-11-27 18:06:43 +08:00
liuhua
8b35776916
Fix a bug in VolcEngine (#3658)
### What problem does this PR solve?

Fix a bug in VolcEngine  #3553

### Type of change

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

Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
2024-11-27 09:30:49 +08:00
Kevin Hu
e5af18d5ea
Update docs for v0.14.0 (#3625)
### What problem does this PR solve?


### Type of change

- [x] Documentation Update
2024-11-25 11:37:56 +08:00
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
Zhichang Yu
4413683898
Introduced beartype (#3460)
### What problem does this PR solve?

Introduced [beartype](https://github.com/beartype/beartype) for runtime
type-checking.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-11-18 17:38:17 +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
roc king
fa54cd5f5c
exstract model dir from model‘s full name (#3368)
### What problem does this PR solve?

When model’s group name contains 0-9,we can't find downloaded
model,because we do not correctly exstract model dir's name from model‘s
full name

### Type of change

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

Co-authored-by: 王志鹏 <zhipeng3.wang@midea.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2024-11-13 14:10:16 +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
ksztone-huanggonghao
0dff64f6ad
fix: TypeError: only length-1 arrays can be converted to Python scalars (#3211)
### What problem does this PR solve?
fix "TypeError: only length-1 arrays can be converted to Python scalars"
while using cohere embedding model.

### Type of change

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


![image](https://github.com/user-attachments/assets/2c21a69f-cd76-4d25-b320-058964812db8)
2024-11-06 11:15:00 +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
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
Kevin Hu
7f44cf543a
move import positions (#2753)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2024-10-09 10:34:58 +08:00
Omar Leonardo Sanchez Granados
34761fa4ca
Fix/bedrock issues (#2718)
### What problem does this PR solve?

Adding a Bedrock API key for Claude Sonnet was broken. I find the issue
came up when trying to test the LLM configuration, the system is a
required parameter in boto3.

As well, there were problems in Bedrock implementation for embeddings
when trying to encode queries.

### Type of change

- [X] Bug Fix (non-breaking change which fixes an issue)
2024-10-05 16:44:50 +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
dda1367ab2
make it lighten (#2577)
### What problem does this PR solve?

#2295

### Type of change

- [x] Refactoring
2024-09-25 13:38:40 +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
4a6a2a0f1b
refine xinference (#2521)
### What problem does this PR solve?

#1588

### Type of change

- [x] Refactoring
2024-09-20 18:37:01 +08:00
Kevin Hu
3044cb85fd
fix batch size error for qianwen embedding (#2431)
### What problem does this PR solve?

#2402

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-09-14 14:40:57 +08:00
Kevin Hu
4730145696
debug backend API for TAB 'search' (#2389)
### What problem does this PR solve?
#2247

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-09-12 17:51:20 +08:00
黄腾
35b7d17d97
fix SILICONFLOW embedding error (#2363)
### What problem does this PR solve?

#2335  fix SILICONFLOW embedding error

### Type of change

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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-09-11 12:17:44 +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
99993e5026
add support for Voyage AI (#2159)
### What problem does this PR solve?

#1853  #2138 add support for Voyage AI

### 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>
2024-08-29 16:14:49 +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
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
黄腾
b4ef50bdb5
fix OpenAI Embedding length error (#1972)
### What problem does this PR solve?
 
#1958   fix OpenAI Embedding length error

### Type of change

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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-08-16 09:49:27 +08:00
黄腾
e013ac52af
add support for SILICONFLOW (#1926)
### What problem does this PR solve?

#1853 add support for SILICONFLOW

### Type of change


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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-08-13 16:09:10 +08:00
黄腾
e9e39d57ce
add support for Upstage (#1902)
### What problem does this PR solve?

#1853  add support for Upstage

### Type of change


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

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-08-12 11:06:25 +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
9a6dc89156
add support for PerfXCloud (#1883)
### What problem does this PR solve?

#1853  add support for PerfXCloud

### Type of change


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

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-08-12 10:11:50 +08:00
黄腾
e34817c2a9
add support for cohere (#1849)
### 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: Zhedong Cen <cenzhedong2@126.com>
2024-08-07 18:40:51 +08:00
黄腾
60428c4ad2
fix LocalAI add bug (#1851)
### What problem does this PR solve?

#1848 

### Type of change

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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-08-07 18:10:42 +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
江不江
bc50f68127
fix embedding_model (#1698)
### What problem does this PR solve?
fix embedding_model #1692
### Type of change

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

Signed-off-by: seaver <zhudan187@qq.com>
2024-07-25 11:43:43 +08:00
黄腾
e67bfca552
refactor some llm api using openai api format (#1692)
### What problem does this PR solve?

refactor some llm api using openai api format

### Type of change

- [x] Refactoring

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-07-25 10:23:35 +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
b4a281eca1
add support for NVIDIA llm (#1645)
### What problem does this PR solve?

add support for NVIDIA llm
### Type of change

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

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-07-23 10:43:09 +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
Kevin Hu
be6d5b76c3
fix embeding model for Azure (#1601)
### What problem does this PR solve?

#1599

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-07-19 09:22:59 +08:00
黄腾
3e9f444e6b
add support for Gemini (#1465)
### What problem does this PR solve?

#1036

### Type of change

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

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
2024-07-11 15:41:00 +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
LiYongHui
a6765e9ca4
Integrates LLM Azure OpenAI (#1318)
### What problem does this PR solve?

feat: Integrates LLM Azure OpenAI #716 

### Type of change

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

### Other
It's just the back-end code, the front-end needs to provide the Azure
OpenAI model addition form.
   
#### Required parameters

- base_url
- api_key

---------

Co-authored-by: yonghui li <yonghui.li@bondex.com.cn>
2024-07-04 09:57:16 +08:00
zhuhao
47926a95ae
Fix ragflow may encounter an OOM (Out Of Memory) when there are a lot of conversations (#1292)
### What problem does this PR solve?

Fix ragflow may encounter an OOM (Out Of Memory) when there are a lot of
conversations.
#1288

### Type of change

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

Co-authored-by: zhuhao <zhuhao@linklogis.com>
2024-06-27 14:48:49 +08:00
KevinHuSh
7dc39cbfa6
add support for mistral (#1153)
### What problem does this PR solve?

#433 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-06-14 11:32:58 +08:00
KevinHuSh
2023fdc13e
fix file preview in file management (#1151)
### What problem does this PR solve?

fix file preview in file management

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-06-14 10:33:59 +08:00
KevinHuSh
abcd3d2469
refactor (#1124)
### What problem does this PR solve?


### Type of change

- [x] Refactoring
2024-06-12 11:02:15 +08:00
Michael Feil
68a698655a
infinity: Update embedding_model.py (#1109)
### What problem does this PR solve?

I implemented infinity, a fast vector embeddings engine. 

### Type of change


- [x] Performance Improvement
- [X] Other (please describe):
2024-06-11 08:23:58 +08:00
KevinHuSh
923c3b8cac
fix bug in api (#1088)
### What problem does this PR solve?

#1075 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-06-07 09:56:14 +08:00