Site Rag
github.com
Streamlined RAG implementation for website content extraction and querying.
Description
Site Rag is an open-source tool that simplifies the process of implementing Retrieval Augmented Generation (RAG) for website content. It automates the extraction of text from web pages, creates embeddings, and allows users to query the extracted information using natural language. This tool is designed to make RAG more accessible and easier to implement for developers working with web content
Features
Automated web scraping and text extraction
Embedding generation for extracted content
Natural language querying of website information
Integration with popular language models
Customizable scraping and embedding options
Easy-to-use command-line interface
Use cases
Content summarization for websites
Question-answering systems based on web content
Information retrieval from multiple web sources
Automated research and data gathering
Creating chatbots with website-specific knowledge
Specs
| Type | Agent |
| Section | AI agents |
| Pricing | free |
| Platform | API only |
| Systems | api, web |
| Site language | en |
| GitHub | bracesproul/site-rag |
| Rating | 0.00 (0 reviews) |
| Views | 643 |
| Launched | 2025-02-05 |
