Commit Graph

70 Commits

Author SHA1 Message Date
2d4a60cae6 Fix: Reduce excessive IO operations by loading LLM factory configurations (#6047)
…ions

### What problem does this PR solve?

This PR fixes an issue where the application was repeatedly reading the
llm_factories.json file from disk in multiple places, which could lead
to "Too many open files" errors under high load conditions. The fix
centralizes the file reading operation in the settings.py module and
stores the data in a global variable that can be accessed by other
modules.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [x] Performance Improvement
- [ ] Other (please describe):
2025-03-14 09:54:38 +08:00
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
dd0ebbea35 Light GraphRAG (#4585)
### What problem does this PR solve?

#4543

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-01-22 19:43:14 +08:00
c5da3cdd97 Tagging (#4426)
### What problem does this PR solve?

#4367

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-01-09 17:07:21 +08:00
0d68a6cd1b Fix errors detected by Ruff (#3918)
### What problem does this PR solve?

Fix errors detected by Ruff

### Type of change

- [x] Refactoring
2024-12-08 14:21:12 +08:00
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
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
e44e3a67b0 adapt to lower case cohere (#3392)
### What problem does this PR solve?

#3384

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-11-14 10:18:25 +08:00
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
5e7c1fb23a reduce rerank batch size (#2801)
### What problem does this PR solve?

### Type of change


- [x] Performance Improvement
2024-10-11 11:29:19 +08:00
e6da0c7c7b deprecate init a super user (#2589)
### What problem does this PR solve?
#2295

### Type of change

- [x] Refactoring
2024-09-25 18:30:27 +08:00
2484e26cb5 fix superuser password not base64 encoded (#2475)
### What problem does this PR solve?

Fixes the _superuser_ `admin@ragflow.io` not being accessible due to how
entered passwords are used. Unless this is expected behavior?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-09-18 14:30:45 +08:00
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
54fc6dcf01 refine llm init (#1938)
### What problem does this PR solve?


### Type of change

- [x] Performance Improvement
2024-08-14 13:28:55 +08:00
a313b77cdd rm qwen-v1-max (#1894)
### What problem does this PR solve?

#1748

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-08-09 18:41:44 +08:00
ede733e130 add support for eml file parser (#1768)
### What problem does this PR solve?

add support for eml file parser
#1363

### 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>
2024-08-06 16:42:14 +08:00
152072f900 Add graphrag (#1793)
### What problem does this PR solve?

#1594

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-08-02 18:51:14 +08:00
H
ac7a0d4fbf Add ParsertType Audio (#1637)
### What problem does this PR solve?

#1514 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-07-22 19:17:30 +08:00
a5306e6345 fix minimax init error (#1537)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-07-16 16:55:31 +08:00
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
607de74ace fix minimax bug (#1528)
### What problem does this PR solve?

#1353 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-07-16 10:55:33 +08:00
ddeac9ab3d added SVG for Groq model model providers (#1470)
#1432  #1447 
This PR adds support for the GROQ LLM (Large Language Model).

Groq is an AI solutions company delivering ultra-low latency inference
with the first-ever LPU™ Inference Engine. The Groq API enables
developers to integrate state-of-the-art LLMs, such as Llama-2 and
llama3-70b-8192, into low latency applications with the request limits
specified below. Learn more at [groq.com](https://groq.com/).
Supported Models


| ID | Requests per Minute | Requests per Day | Tokens per Minute |

|----------------------|---------------------|------------------|-------------------|
| gemma-7b-it | 30 | 14,400 | 15,000 |
| gemma2-9b-it | 30 | 14,400 | 15,000 |
| llama3-70b-8192 | 30 | 14,400 | 6,000 |
| llama3-8b-8192 | 30 | 14,400 | 30,000 |
| mixtral-8x7b-32768 | 30 | 14,400 | 5,000 |

---------

Co-authored-by: paresh0628 <paresh.tuvoc@gmail.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2024-07-12 09:25:44 +08:00
009e18f094 feat: support xinference rerank model (#1466)
### What problem does this PR solve?

support xinference rerank model
#1455 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-07-11 18:37:41 +08:00
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
258c9ea644 add keyword extraction in graph (#1373)
### What problem does this PR solve?
#918 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-07-04 15:57:25 +08:00
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
7c9ea5cad9 add interpreter to graph (#1347)
### What problem does this PR solve?

#918 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-07-03 12:15:15 +08:00
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
1de31ca9f6 refine file select code (#1021)
### What problem does this PR solve?

#1015 

### Type of change

- [x] Refactoring
2024-05-31 19:44:33 +08:00
c58a1c48eb Fix: bug #991 (#1013)
### What problem does this PR solve?

issue #991

### Type of change

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

---------

Co-authored-by: KevinHuSh <kevinhu.sh@gmail.com>
2024-05-31 18:03:47 +08:00
260c68f60c Adding the Minimax model (#1009)
### What problem does this PR solve?

Added support for MiniMax LLM

### Type of change

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

---------

Co-authored-by: cecilia-uu <konghui1996@163.com>
2024-05-31 16:38:53 +08:00
f077b57f8b set ollama keep_alive (#985)
### What problem does this PR solve?

#980 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-30 11:27:58 +08:00
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
9ffd7ae321 Added support for Baichuan LLM (#934)
### What problem does this PR solve?

- Added support for Baichuan LLM

### Type of change

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

Co-authored-by: 海贼宅 <stu_xyx@163.com>
2024-05-28 09:09:37 +08:00
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
a1586e0af9 correct mismatched kb doc number (#826)
### What problem does this PR solve?

#620

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-17 17:27:39 +08:00
9e5d501e83 fix data init error (#820)
### What problem does this PR solve?

#810 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-17 14:33:19 +08:00
e73ce39b66 Add 2 embeding models from OpenAI (#812)
### What problem does this PR solve?

#810 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-05-17 08:51:29 +08:00
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
eb27a4309e add support for deepseek (#668)
### What problem does this PR solve?

#666 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-05-08 10:30:02 +08:00
b75d75e995 fix youdao bug (#551)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-04-26 09:58:22 +08:00
66f8d35632 Refactor (#537)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2024-04-25 14:14:28 +08:00
890561703b Add bce-embedding and fastembed (#383)
### What problem does this PR solve?


Issue link:#326

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-04-16 16:42:19 +08:00
826ad6a33a feat: FastEmbed embedding support (#291)
### Description

Following up on https://github.com/infiniflow/ragflow/pull/275, this PR
adds support for FastEmbed model configurations.

The options are not exhaustive. You can find the full list
[here](https://qdrant.github.io/fastembed/examples/Supported_Models/).

P.S. I ran into OOM issues when building the image.

### Type of change

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

---------

Co-authored-by: KevinHuSh <kevinhu.sh@gmail.com>
2024-04-15 15:58:06 +08:00
4608cccd05 add new model gpt-3-turbo (#352)
### What problem does this PR solve?


Issue link:#351

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-04-15 08:58:42 +08:00
91068edf16 Support Xinference (#320)
### What problem does this PR solve?

Issue link:#299

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-04-11 18:22:25 +08:00
3708b97db9 Support Ollama (#261)
### What problem does this PR solve?

Issue link:#221

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-04-08 19:20:57 +08:00
591202721d fix bug about field misspell (#243)
### 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._

Issue link:#[[Link the issue
here](https://github.com/infiniflow/ragflow/issues/242)]

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-04-07 14:18:01 +08:00
23b448cf96 fix docker compose issue (#238)
### 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._

Issue link:#[[Link the issue
here](https://github.com/infiniflow/ragflow/issues/226)]

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-04-07 09:04:32 +08:00