https://github.com/Grecil/Corrective-RAG
Implementation of Corrective RAG using LangChain and LangGraph.
https://github.com/Grecil/Corrective-RAG
crag duckduckgo embeddings faiss gemini-api langchain langgraph llm rag streamlit
Last synced: about 2 months ago
JSON representation
Implementation of Corrective RAG using LangChain and LangGraph.
- Host: GitHub
- URL: https://github.com/Grecil/Corrective-RAG
- Owner: Grecil
- Created: 2024-06-18T06:33:52.000Z (10 months ago)
- Default Branch: master
- Last Pushed: 2024-08-06T14:31:16.000Z (9 months ago)
- Last Synced: 2024-08-07T15:46:11.374Z (9 months ago)
- Topics: crag, duckduckgo, embeddings, faiss, gemini-api, langchain, langgraph, llm, rag, streamlit
- Language: Python
- Homepage: https://corrective-rag.streamlit.app
- Size: 39.1 KB
- Stars: 8
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Corrective-RAG
An Implementation of this paper - https://arxiv.org/pdf/2401.15884 using LangChain and LangGraph
### Requirements
- Large Language Model (Change it in models/LLM. By default it uses gemini-1.5-flash by Google. You can use any model supported by langchain.)
- Embeddings Model (Change it in models/EM. By default it uses text-embedding-004 by Google. You can use any model supported by langchain.)
- Python 3.10 (use other versions at your own risk) (skip if using docker)
- Python libraries mentioned in requirements.txt (skip if using docker)
### Setup
- Copy the repository
- Change LLM and EM in models.
- Run the app
- Locally
```
streamlit run streamlit_app.py
```
- Docker
```
docker build -t corrective-rag .
docker run -p 8501:8501 corrective-rag
```
#### Check the app out here - https://corrective-rag.streamlit.app
### To-do (contributions are welcome)
- [ ] Use Hybrid Search
- [ ] Change VectorDB to Pinecone
- [ ] Allow Users to Chat
- [ ] Maintain Chat History for each user
- [ ] Improve Theming
- [ ] DOCX, XLSX, PPTX, CSV, TXT support.