RAG Document Q&A

3

RAG-powered document question-answering using FAISS vector search, Sentence Transformers, and Groq LLM for grounded answers from private documents.

GitHub
Category Models
Added Mar 28, 2026
Views 53

About

A RAG-powered MCP server for document question-answering. Indexes PDFs using FAISS vector search and Sentence Transformers, then generates grounded answers via Groq LLaMA inference. Includes a Streamlit chat interface and Claude Desktop integration for querying private document collections with source-grounded, hallucination-free responses.

Is this your product? Claim this listing with an email at your domain to post updates.

Is this your project?

Claim this listing to manage your page, access analytics, and unlock upgrades. Verification takes 60 seconds.

Log In to Claim

Share This Project

Share on X Share on LinkedIn

Embed Badge

Add this badge to your README:

[![Listed on AiList](https://hifriendbot.com/ai-list/badge/rag-document-qa.svg)](https://hifriendbot.com/ai-list/rag-document-qa/)
Listed on AiList

Compare

RAG Document Q&A vs RAG Document Search RAG Document Q&A vs Document Indexer RAG Document Q&A vs Qdrant Vector Database

Similar Projects

RAG Document Search

Performs semantic search over PDF documents using FAISS vector indexing and sentence embeddings.

MCP Servers

Document Indexer

16

Monitors local document folders and maintains a searchable vector index using LanceDB and sentence transformers, enabling natural language queries across personal document collections with automatic file change detection and local LLM-powered summarization.

Models

Qdrant Vector Database

1

Provides a vector database for storing and retrieving code snippets through semantic search using Docker containers and sentence-transformers embeddings

MCP Servers

List Your Project

Join the directory Ai agents read. Free forever.

Submit Your Project