Running Llama 2 and other Open-Source LLMs on CPU Inference Locally for Document Q&A

This Repositry is an experiment with an agent that searches documents and asks questions repeatedly in response to the main question. It automatically determines the optimal answer from the current documents or recognizes when there is no answer.

🐋 DeepSeek-R1: Retrieval-Augmented Generation for Document Q&A 📄

RAG chatbot designed for domain-specific queries using Ollama, Langchain, phi-3 and Faiss

Sistema RAG (Retrieval Augmented Generation) para asistencia de documentación técnica en español utilizando LangChain, OpenAI Y Streamlit para la interfaz visual

AI agent API (Python/FastAPI) to upload documents (PDF/TXT) and answer questions using RAG with Azure OpenAI and LangChain.

A Document QA chatbot using LangChain, Pinecone for vector storage, and Amazon Bedrock (mistral.mixtral-8x7b-instruct for LLM and titan-embed-text for embeddings). Built with a Streamlit frontend for document uploads and contextual question answering.

An advanced, fully local, and GPU-accelerated RAG pipeline. Features a sophisticated LLM-based preprocessing engine, state-of-the-art Parent Document Retriever with RAG Fusion, and a modular, Hydra-configurable architecture. Built with LangChain, Ollama, and ChromaDB for 100% private, high-performance document Q&A.

Sub-second RAG-based chatbot for medical Q&A over 10+ textbooks with source-cited responses.

⚡️ Local RAG API using FastAPI + LangChain + Ollama | Upload PDFs, DOCX, CSVs, XLSX and ask questions using your own documents — fully offline!

🔒 Local AI Agent - Offline RAG system for secure document Q&A with no external APIs

A document question-answering system that allows users to upload files (PDFs, DOCs, TXTs) and ask questions about their content using RAG (Retrieval-Augmented Generation) with ChromaDB and Gemma.

Successfully developed a Multi-Domain AI Personal Assistant using LangChain, OpenAI, and Streamlit. The application seamlessly integrates multiple specialized capabilities, including document-based question answering (QA), Python code execution, debugging, explanation and optimization, web search, latest news retrieval, and currency conversion.

An intelligent document assistant powered by Open-Source Large Language Models

Create your own Retrieval-Augmented Generation (RAG) chatbot for PDFs. This project uses LangChain, Flask, and an LLM (IBM WatsonX/Hugging Face) to build a conversational AI that understands your documents.

Cross-document QA leveraging LLM and taxonomy

AI assistant backend for document-based question answering using RAG (LangChain, OpenAI, FastAPI, ChromaDB). Features modular architecture, multi-tool agents, conversational memory, semantic search, PDF/Docx/Markdown processing, and production-ready deployment with Docker.