document-assistant

RAG based Document Assistant for Search

🤖 Agentic RAG - An intelligent document assistant with semantic chunking, hybrid search (vector + BM25), multi-format support (PDF, Word, CSV, Excel), and multi-channel bots (Telegram, WhatsApp). Built with FastAPI, React, PostgreSQL/pgvector, and LangChain.

An intelligent academic document assistant for scholarly research and analysis.

A private AI assistant for your company's documents - runs entirely on your own hardware. Source-available so your IT can audit the privacy claim.

Offline RAG-Based Document Assistant

This repository contains materials for studying and implementing Agentic AI from ReadyTensor.

A lightweight Document Q&A chatbot using RAG. Built from scratch with FastAPI, pgvector, and local (Ollama) or remote (OpenAI) LLMs.

Indexes documentation and answers questions using retrieval-augmented generation with OpenAI, Claude, Gemini, Groq, or Ollama through a CLI or web interface.

Fully local RAG-powered document and code assistant built with LlamaIndex - hybrid ChromaDB + BM25 retrieval, query routing and expansion, and an on-device DeepSeek LLM via Streamlit UI and CLI, with no cloud APIs required.

An intelligent document assistant powered by DeepSeek LLM that enables natural conversations with documents. Features semantic search, source citations, and conversation history. Built with FastAPI, React, and LangChain for robust document processing and chat capabilities.

Small AI document assistant prototype using Python, Streamlit, prompt design, and basic document retrieval.