https://github.com/runtime-error786/self-rag
https://github.com/runtime-error786/self-rag
huggingface-transformers langchain langgraph llama3
Last synced: 26 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/runtime-error786/self-rag
- Owner: runtime-error786
- Created: 2024-09-14T06:22:39.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-09-15T07:32:07.000Z (over 1 year ago)
- Last Synced: 2025-01-20T23:26:04.794Z (about 1 year ago)
- Topics: huggingface-transformers, langchain, langgraph, llama3
- Language: Jupyter Notebook
- Homepage:
- Size: 896 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Overview
This project implements a Retrieval-Augmented Generation (RAG) chain using a local LLM (Llama3) and the LangChain framework. It focuses on enhancing question answering by improving document retrieval, filtering relevant document, re-generating questions, and scoring the generated responses. This setup allows for more accurate and contextually relevant responses based on retrieved documents.
## Features
Document Retrieval: Retrieve documents from URLs and filter them based on relevance to the query.
RAG Generation: Use the retrieved documents for contextual generation with Llama3.
Question Transformation: Optimize user questions for better retrieval results.
Grading Mechanism: Grade the relevance of documents and the grounding of generated answers.
Hallucination Detection: Identify whether the generated content is grounded in the retrieved documents.
Useful Answer Assessment: Grade generated answers to determine if they address the user’s question.
