DocQuery: RAG-Based Intelligent Document Retrieval Assistant (CS50x Final Project)
-
Updated
Sep 21, 2026 - Python
DocQuery: RAG-Based Intelligent Document Retrieval Assistant (CS50x Final Project)
RAG agentique sur des documents de concession télécom publique (DSP/RIP), pensé eval-first et contrôlé en CI.
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.
Local-first project demonstrating deterministic, memory-driven AI with evidence-only responses.
A Retrieval-Augmented Generation (RAG) pipeline for help.mail.ru that features recursive web scraping, text chunking, FAISS-based semantic search, multiple embedding models (deepvk, MiniLM, LaBSE), uniformity & alignment evaluation, and TSNE visualization.
An AI-powered clinical assistant using Retrieval-Augmented Generation (RAG) on the MIMIC-IV DiReCT dataset. It retrieves relevant patient cases and generates diagnostic reasoning using LLMs. Built with Streamlit, Transformers, FAISS, and SentenceTransformers.
Local-first knowledge assistant: multi-format ingestion, concept graph, and provenance-honest retrieval (FastAPI + Next.js + Postgres + Qdrant)
To associate your repository with the retrievalaugmentedgeneration topic, visit your repo's landing page and select "manage topics."