https://github.com/runtime-error786/adaptive-self-rag
https://github.com/runtime-error786/adaptive-self-rag
agents huggingface-transformers langgraph llama3
Last synced: 5 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/runtime-error786/adaptive-self-rag
- Owner: runtime-error786
- Created: 2024-09-12T14:20:04.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-09-15T07:32:34.000Z (over 1 year ago)
- Last Synced: 2025-07-07T06:09:12.968Z (7 months ago)
- Topics: agents, huggingface-transformers, langgraph, llama3
- Language: Jupyter Notebook
- Homepage:
- Size: 918 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Overview
This project integrates a retrieval-augmented generation (RAG) system using LangChain and a local LLM (Llama) model. The goal is to retrieve relevant documents based on a user's query, generate answers from these document, and perform various evaluation steps such as checking document relevance, hallucination grading, and more.
## Key Features
Document Retrieval: Retrieves relevant documents from a Chroma vectorstore or web search based on a user's query.
Document Relevance Grading: Filters retrieved documents to ensure they are relevant to the user's question.
Query Rewriting: Improves the user's question for better document retrieval performance.
Answer Generation: Uses RAG to generate answers based on the retrieved documents.
Web Search: Routes questions outside the vectorstore's scope to a web search tool.
