fix: Bulk disable the chunk, the UI still shows they are enabled #1236 (#1534)
### What problem does this PR solve?
fix: Bulk disable the chunk, the UI still shows they are enabled #1236
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
'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>
fix the tokens error that occurred when adding the xinference model (#1527)
### What problem does this PR solve?
fix the tokens error that occurred when adding the xinference model
#1522
root@pc-gpu-86-41:~# curl -X 'POST' 'http://127.0.0.1:9997/v1/rerank' -H
'accept: application/json' -H 'Content-Type: application/json' -d '{
"model": "bge-reranker-v2-m3",
"query": "A man is eating pasta.",
"return_documents":"true",
"return_len":"true",
"documents": [
"A man is eating food.",
"A man is eating a piece of bread.",
"The girl is carrying a baby.",
"A man is riding a horse.",
"A woman is playing violin."
]
}'
{"id":"610a8724-3e96-11ef-81ce-08bfb886c012","results":[{"index":0,"relevance_score":0.999574601650238,"document":{"text":"A
man is eating
food."}},{"index":1,"relevance_score":0.07814773917198181,"document":{"text":"A
man is eating a piece of
bread."}},{"index":3,"relevance_score":0.000017700713215162978,"document":{"text":"A
man is riding a
horse."}},{"index":2,"relevance_score":0.0000163753629749408,"document":{"text":"The
girl is carrying a
baby."}},{"index":4,"relevance_score":0.00001631895975151565,"document":{"text":"A
woman is playing
violin."}}],"meta":{"api_version":null,"billed_units":null,"tokens":{"input_tokens":38,"output_tokens":38},"warnings":null}}
### Type of change
- [ ] 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):
fix: Hundreds of chunks list can't choose page #1238 (#1532)
### What problem does this PR solve?
fix: Hundreds of chunks list can't choose page #1238
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
fix: fixed the issue of error when opening the canvas #918 (#1520)
### What problem does this PR solve?
fix: fixed the issue of error when opening the canvas #918
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### 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] Documentation Update
fix: Add Model Providers:Azure-OpenAI error #1402 (#1512)
### What problem does this PR solve?
fix: Add Model Providers:Azure-OpenAI error #1402
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
fix: fixed the issue that the llm field in the KeywordExtract form had no default value (#1510)
### What problem does this PR solve?
fix: fixed the issue that the llm field in the KeywordExtract form had
no default value
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
feat: remove dagre and elkjs #918
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Fix: Implement DOMPurify to sanitize HTML content before rendering (#1498)
### What problem does this PR solve?
This PR resolves issue #1491 related to HTML Injection and Cross-Site
Scripting (XSS). The issue was caused by the unsafe usage of
`dangerouslySetInnerHTML` without proper sanitization of user input.
### Changes
- Added DOMPurify dependency.
- Updated the following components to use DOMPurify:
-
`web/src/pages/add-knowledge/components/knowledge-chunk/components/chunk-card/index.tsx`
- `web/src/pages/chat/markdown-content/index.tsx`
-
`web/src/pages/add-knowledge/components/knowledge-setting/category-panel.tsx`
### Type of change
- [x] Other (please describe): Security Fix
fix: fixed the issue where parameters of DuckDuckGo could not be saved to the backend after being dragged to the canvas #918 (#1503)
### What problem does this PR solve?
fix: fixed the issue where parameters of DuckDuckGo could not be saved
to the backend after being dragged to the canvas #918
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
fix: fixed the issue where the greeting message could not be displayed when opening the debug window #918 (#1499)
### What problem does this PR solve?
fix: fixed the issue where the greeting message could not be displayed
when opening the debug window #918
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
feat: add llm Select to KeywordExtractForm #918 (#1492)
### What problem does this PR solve?
feat: add llm Select to KeywordExtractForm #918
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
fix: add message_history_window_size to GenerateForm #1472 (#1487)
### What problem does this PR solve?
fix: add message_history_window_size to GenerateForm #1472
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
feat: translate text from DuckDuckGo #918
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
feat: modify DuckDuckGo's style #918
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
#1036
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
feat: add KeywordExtractForm and BaiduForm and DuckDuckGoForm #918 (#1477)
### What problem does this PR solve?
feat: add KeywordExtractForm and BaiduForm and DuckDuckGoForm #918
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
#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>
### What problem does this PR solve?
support xinference rerank model
#1455
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
feat: validate the name field of the categorize operator for duplicate names and nulls #918 (#1471)
### What problem does this PR solve?
feat: validate the name field of the categorize operator for duplicate
names and nulls #918
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Make the document start parsing.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
fix: monitor changes in the data.form field of the categorize and relevant operators and then synchronize them to the edge #918 (#1469)
### What problem does this PR solve?
feat: monitor changes in the table of relevant operators and synchronize
them to the edge #918
feat: fixed the issue of repeated requests when opening the graph page
#918
feat: cache node anchor coordinate information #918
feat: monitor changes in the data.form field of the categorize and
relevant operators and then synchronize them to the edge #918
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
After checking the language of the pdf, the line will hardcode the
language into Chinese
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### 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>
API doc: Correct Base URL and Dataset URL. (#1444)
The correct URL is http://<host_address>/v1/api , not
http://<host_address>/api/v1 .
### What problem does this PR solve?
### Type of change
- [x] Documentation Update
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
feat: display the debugging results of each operator in a pop-up window #918 (#1445)
### What problem does this PR solve?
feat: display the debugging results of each operator in a pop-up window
#918
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
feat: translate name of operator #918
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Kevin Hu
balibabu
黄腾
zhuhao
H
writinwaters
cecilia-uu
Dani Servian
paresh2806
Yuhao Tsui
Yuhao Tsui