130 Commits

Author SHA1 Message Date
dashi6174
9a01d1b876
The default max tokens of 215 is too small, answers are often cut off.I will modify it to 512 to address this issue. (#845)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2024-05-20 17:25:19 +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
6683179d6a
fix bug about removing KB. (#839)
### What problem does this PR solve?

#838 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-20 09:23:57 +08:00
KevinHuSh
673a28e492
fix bug of chat without stream (#830)
### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-17 20:03:00 +08:00
KevinHuSh
b3c923da6b
add doc ids in API: completion (#827)
### What problem does this PR solve?
#808 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-05-17 17:51:54 +08:00
KevinHuSh
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
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
GYH
081f922ee6
0517 list chunks (#821)
### What problem does this PR solve?

#717 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-05-17 15:58:05 +08:00
KevinHuSh
a2a6a35e94
fix doc number miss-match issue (#822)
### What problem does this PR solve?

#620 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-17 15:35:09 +08:00
KevinHuSh
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
KevinHuSh
c3bc72dfd9
fix too large thumbnail issue (#817)
### What problem does this PR solve?

#709

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-17 14:04:21 +08:00
LiYongHui
2dd705fe68
feat: add feishu oauth (#815)
### What problem does this PR solve?

The back-end code adds Feishu oauth

### Type of change

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

Co-authored-by: yonghui li <yonghui.li@bondex.com.cn>
2024-05-17 13:47:05 +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
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
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
d6772f5dd7
add version (#807)
### What problem does this PR solve?
#709 
### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-05-16 16:17:48 +08:00
KevinHuSh
7b144cc086
fix: can't capitalize file or folder name (#798)
### What problem does this PR solve?


#792 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-16 09:10:29 +08:00
KevinHuSh
1c4e92ed35
Knowledge base search is case sensitive (#797)
### What problem does this PR solve?
#793 
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-16 09:00:12 +08:00
dashi6174
6ff63ee2ba
Support for code files parse (#789)
### 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)
2024-05-15 16:34:28 +08:00
KevinHuSh
d8c080ee52
fix bugs in searching file using keywords (#780)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-15 12:51:57 +08:00
GYH
626ace8639
Updated document upload method (#777)
### What problem does this PR solve?

api_app.py
/document/upload 
add two non mandatory parameters
parser_id:
[naive,qaresume,manual,table,paper,book,laws,presentation,picture,one]
run: 1

### Type of change
- [x] New Feature (non-breaking change which adds functionality)
2024-05-15 12:22:11 +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
KevinHuSh
aa03dfa453
fix bug of get file (#746)
### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-13 14:02:38 +08:00
Sawyer
69b7c61498
fix: typo in user_app.py (#740)
### 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 
- [x] Other (please describe): Fix typo
2024-05-13 09:25:45 +08:00
KevinHuSh
04a9e95161
let file in knowledgebases visible in file manager (#714)
### What problem does this PR solve?

Let file in knowledgebases visible in file manager.
#162 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-05-11 16:04:28 +08:00
KevinHuSh
7ddb2f19be
make sure to raise exception if redis is not there (#674)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2024-05-08 15:20:45 +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
KevinHuSh
8d6d7f6887
fix task losting isssue (#665)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-07 20:46:45 +08:00
KevinHuSh
a5aed2412f
fix bugs (#662)
### What problem does this PR solve?

Fix import error for task_service.py

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-07 16:41:56 +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
c6b6c748ae
fix file encoding detection bug (#653)
### What problem does this PR solve?

#651 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-07 10:01:24 +08:00
Moonlit
ca5acc151a
Refactor: Use TaskStatus enum for task status handling (#646)
### What problem does this PR solve?

This commit changes the status 'not started' from being hard-coded to
being maintained by the TaskStatus enum. This enhancement ensures
consistency across the codebase and improves maintainability.

### Type of change

- [x] Refactoring
2024-05-06 18:39:17 +08:00
KevinHuSh
5f03a4de11
remove redis (#629)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2024-04-30 19:00:41 +08:00
KevinHuSh
cab274f560
remove PyMuPDF (#618)
### What problem does this PR solve?
#613 

### Type of change


- [x] Other (please describe):
2024-04-30 12:38:09 +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
6874c6f3a7
refine document upload (#602)
### What problem does this PR solve?

#567 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-04-29 15:45:08 +08:00
KevinHuSh
8c07992b6c
refine code (#595)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2024-04-28 19:13:33 +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
038822f3bd
make cites in conversation API configurable (#576)
### What problem does this PR solve?

#566 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-04-28 11:56:17 +08:00
KevinHuSh
944776f207
fix bug about fetching file from minio (#574)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-04-28 09:57:40 +08:00
KevinHuSh
ab06f502d7
fix bug of file management (#565)
### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-04-26 19:59:21 +08:00
KevinHuSh
84b39c60f6
fix rename bug (#562)
### What problem does this PR solve?

fix rename file bugs
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-04-26 18:55:21 +08:00
KevinHuSh
f69ff39fa0
add file management feature (#560)
### What problem does this PR solve?

### Type of change

- [x] Documentation Update
2024-04-26 17:21:53 +08:00
KevinHuSh
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
chrysanthemum-boy
26003b5076
Add upload file by knowledge base name API. (#539)
### What problem does this PR solve?
Add upload file by knowledge base name API.

### Type of change

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

---------

Co-authored-by: chrysanthemum-boy <fannc@qq.com>
2024-04-25 15:10:19 +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
chrysanthemum-boy
72384b191d
Add .doc file parser. (#497)
### What problem does this PR solve?
Add `.doc` file parser, using tika.
```
pip install tika
```
```
from tika import parser
from io import BytesIO

def extract_text_from_doc_bytes(doc_bytes):
    file_like_object = BytesIO(doc_bytes)
    parsed = parser.from_buffer(file_like_object)
    return parsed["content"]
```
### Type of change

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

---------

Co-authored-by: chrysanthemum-boy <fannc@qq.com>
2024-04-23 15:31:43 +08:00
KevinHuSh
b8e58fe27a
add redis to accelerate access of minio (#482)
### What problem does this PR solve?

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-04-22 14:11:09 +08:00