#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?
#1036
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
### 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>
Support displaying tables in the chunks of pdf file when using QA parser (#1263)
### What problem does this PR solve?
Support displaying tables in the chunks of pdf file when using QA parser
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Support extracting questions and answers from PDF files
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
The fasttext library is missing, and it is used in the operators.py file. (#925)
### 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 which fixes an issue)
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)
### 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>
Fix missing 'ollama' package in requirements.txt (#621)
### What problem does this PR solve?
This commit resolves an issue where the 'ollama' package was
inadvertently omitted from the requirements.txt file. The package has
now been added to ensure all dependencies are correctly installed for
the project.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Fix: missing 'redis' package in requirements.txt (#622)
### What problem does this PR solve?
This commit resolves an issue where the 'redis' package was
inadvertently omitted from the requirements.txt file. The package has
now been added to ensure all dependencies are correctly installed for
the project.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### 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>
### 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>
H
paresh2806
黄腾
Zhedong Cen
KevinHuSh
dashi6174
Fakai Zhao
Moonlit
chrysanthemum-boy
jie yang
Anush