55 Commits

Author SHA1 Message Date
yungongzi
c0d71adaa2
Bug fix for volcengine (#909)
### What problem does this PR solve?
Bug fixes for the VolcEngine

- Bug fix for front-end configuration code of VolcEngine

- Bug fix for tokens counting logic of VolcEngine


### Type of change

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

---------

Co-authored-by: 海贼宅 <stu_xyx@163.com>
2024-05-24 11:34:39 +08:00
KevinHuSh
6f99bbbb08
add raptor (#899)
### What problem does this PR solve?

#882 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-05-23 14:31:16 +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
dashi6174
21453ffff0
fixed: The choices may be empty. (#876)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-22 15:29:07 +08:00
KevinHuSh
a7bd427116
add locally deployed llm (#841)
### What problem does this PR solve?


### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-05-20 12:40:59 +08:00
KevinHuSh
2b36283712
fix english query bug (#840)
### What problem does this PR solve?

#834 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-20 12:23:51 +08:00
KevinHuSh
f6a599461f
fix zhipuAI stream issue (#825)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-17 17:07:33 +08:00
KevinHuSh
d1614107e2
fix stream chat for ollama (#816)
### What problem does this PR solve?

#709

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-17 12:07:00 +08:00
KevinHuSh
95f809187e
add stream chat (#811)
### What problem does this PR solve?

#709 
### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-05-16 20:14:53 +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
KevinHuSh
4153a36683
truncate text to fitin embedding model (#692)
### What problem does this PR solve?


### Type of change

- [x] Refactoring
2024-05-09 11:35:08 +08:00
KevinHuSh
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
Fakai Zhao
de839fc3f0
optimize srv broker and executor logic (#630)
### What problem does this PR solve?

Optimize task broker and executor for reduce memory usage and deployment
complexity.

### Type of change
- [x] Performance Improvement
- [x] Refactoring

### Change Log
- Enhance redis utils for message queue(use stream)
- Modify task broker logic via message queue (1.get parse event from
message queue 2.use ThreadPoolExecutor async executor )
- Modify the table column name of document and task (process_duation ->
process_duration maybe just a spelling mistake)
- Reformat some code style(just what i see)
- Add requirement_dev.txt for developer
- Add redis container on docker compose

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2024-05-07 11:43:33 +08:00
KevinHuSh
674b3aeafd
fix disable and enable llm setting in dialog (#616)
### What problem does this PR solve?
#614 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-04-30 11:04:14 +08:00
KevinHuSh
2af74cc494
refine docker layers (#606)
### What problem does this PR solve?


### Type of change

- [x] Performance Improvement
2024-04-29 17:57:40 +08:00
KevinHuSh
9d60a84958
refactor code (#583)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2024-04-28 13:19:54 +08:00
KevinHuSh
66f8d35632
Refactor (#537)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2024-04-25 14:14:28 +08:00
KevinHuSh
3610e1e5b4
fix ollama issuet push (#486)
### What problem does this PR solve?

#477 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-04-22 15:13:01 +08:00
KevinHuSh
453c29170f
make sure the models will not be load twice (#422)
### What problem does this PR solve?

#381 
### Type of change

- [x] Refactoring
2024-04-18 09:37:23 +08:00
KevinHuSh
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
Anush
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
KevinHuSh
c39b751600
conversation API backend update (#360)
### What problem does this PR solve?


Issue link:#345

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-04-15 14:43:44 +08:00
KevinHuSh
8ffc09cb5c
Support Xinference (#321)
### What problem does this PR solve?

Issue link:#299

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-04-11 18:25:37 +08:00
KevinHuSh
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
KevinHuSh
f6c7204002
refine log format (#312)
### What problem does this PR solve?

Issue link:#264
### Type of change


- [x] Documentation Update
- [x] Refactoring
2024-04-11 10:13:43 +08:00
KevinHuSh
653c759d8d
resolve issure to call ZH?IPUAI (#277)
### What problem does this PR solve?

Issue link:#265

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-04-09 16:16:10 +08:00
KevinHuSh
6748872b0b
remove presence_penalty for chatglm (#268)
### What problem does this PR solve?

Issue link:#265

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-04-09 09:24:08 +08:00
KevinHuSh
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
KevinHuSh
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
KevinHuSh
121c7a5681
refine error response, add set api-key MD (#178) 2024-03-31 19:09:42 +08:00
KevinHuSh
e876f58b4c
refine readme (#170) 2024-03-29 14:38:15 +08:00
KevinHuSh
38e5737067
add base url for OpenAI (#166) 2024-03-28 19:15:16 +08:00
KevinHuSh
a5384446e3
let's load model from local (#163) 2024-03-28 16:10:47 +08:00
KevinHuSh
bf2e3d7fc1
refine OpenAi Api (#159) 2024-03-27 17:55:45 +08:00
KevinHuSh
fd7fcb5baf
apply pep8 formalize (#155) 2024-03-27 11:33:46 +08:00
KevinHuSh
979b3a5b4b
support snapshot download from local (#153)
* support snapshot download from local

* let snapshot download from local
2024-03-27 09:53:42 +08:00
KevinHuSh
da21320b88
fix plainPdf bugs (#152) 2024-03-26 15:11:07 +08:00
KevinHuSh
5875c8ba08
Add 'One' chunk method (#137) 2024-03-20 18:57:22 +08:00
KevinHuSh
2447f95629
add Moonshot, debug my_llm (#126) 2024-03-15 18:59:00 +08:00
KevinHuSh
675a9f8d9a
add dockerfile for cuda envirement. Refine table search strategy, (#123) 2024-03-14 19:45:29 +08:00
KevinHuSh
f1f09df901
add local llm implementation (#119) 2024-03-12 11:57:08 +08:00
KevinHuSh
2d7c9080f4
deal with stop reason being length problem (#109) 2024-03-07 16:12:01 +08:00
KevinHuSh
8a57f2afd5
change callback strategy, add timezone to docker (#96) 2024-03-05 12:08:41 +08:00
KevinHuSh
4568a4b2cb
refine admin initialization (#75) 2024-02-27 14:57:34 +08:00
KevinHuSh
7fd1eca582
init README of deepdoc, add picture processer. (#71)
* init README of deepdoc, add picture processer.

* add resume parsing
2024-02-23 18:28:12 +08:00
KevinHuSh
a8294f2168 Refine resume parts and fix bugs in retrival using sql (#66) 2024-02-19 19:22:17 +08:00
KevinHuSh
5e0a689c43 refactor retieval_test, add SQl retrieval methods (#61) 2024-02-08 17:01:01 +08:00
KevinHuSh
e32ef75e99 Test chat API and refine ppt chunker (#42) 2024-01-23 19:45:36 +08:00
KevinHuSh
34b2ab3b2f Test APIs and fix bugs (#41) 2024-01-22 19:51:38 +08:00
KevinHuSh
484e5abc1f llm configuation refine and trievalTest API refine (#40) 2024-01-19 19:51:57 +08:00