vector-search-embeddings

Production-ready semantic vector search for Django — searches across FK, M2M, and reverse relations by traversing your model graph. Pluggable backends: ChromaDB, FAISS, Qdrant.

Privacy-first AI assistant for legal documents. Ask questions in natural language, get instant answers with exact sources. Scans contracts for risky clauses automatically. Runs 100% on your computer—no cloud required. Supports local AI (Ollama) or cloud APIs (ChatGPT, Claude, etc.). completely Free

AI-powered Indian legal assistant using RAG — 164K chunks, hybrid search, cross-encoder reranking, Gemini 2.5 Flash streaming, 3D Next.js UI.

Model Context Protocol (MCP) memory server giving AI agents a persistent, shared world across sessions, vendors, and models.

A Retrieval-Augmented Generation (RAG) based AI assistant for answering questions using video transcript chunks, featuring contextual understanding, similarity ranking, and JSON-formatted responses.

AI-powered legal contract intelligence platform. A LangGraph multi-agent engine (parsing → 9-clause detection → 3-tier risk → 8-domain compliance → redlines) with grounded, pinpoint-cited Q&A. FastAPI + React 19, PostgreSQL, ChromaDB, 100% free-tier Google Gemini, banking-grade security.

RAG-based chatbot that ingests Healthline URLs to produce concise, source‑grounded summaries & answers. Built to eliminate manual copy‑pasting & streamline insight extraction: paste article links, ask a question, & get reliable, Healthline‑only results fast.

RAG Mini Project — Retrieval‑Augmented Generation chatbot with FastAPI backend (Docker on Hugging Face Spaces) and Streamlit frontend (Render), featuring document ingestion, vector search, and LLM‑powered answers

Serverless Retrieval-Augmented Generation system on AWS using Bedrock Titan embeddings, Aurora PostgreSQL pgvector, Lambda, API Gateway, SageMaker, and Streamlit.

Production-resilient TypeScript engine for PDF text chunking, Gemini vector embeddings, and ChromaDB HNSW semantic search.

RAG PDF chatbot, retrieval-augmented QA over PDFs using FAISS and Ollama Llama 3.2:3b.

Advanced RAG with hybrid search, query classification, answer fusion, and self-correction

My First RAG pipeline using local ollama models

A learning-purpose RAG project that loads multiple document types, builds embeddings, performs semantic search, and generates Gemini-based answers for Vision-Language Navigation research.

A notes app with hybrid recall — BM25 keyword search and semantic embeddings fused into one ranked result. FastAPI, Next.js, SQLite FTS5, Chroma.

A WhatsApp bot with Baileys + Python RAG catalog search + Ollama/Mistral for cha

Projeto de busca semântica de filmes utilizando Qdrant como banco de dados vetorial e Sentence Transformers para geração de embeddings. O objetivo é demonstrar como diferentes estratégias de segmentação de texto (chunking) impactam a qualidade dos resultados em uma busca por similaridade.

Resume Intelligence System using Spring AI and Gemini with RAG-based semantic search and question answering over PDF resumes.

Lean vector embedding provider package for CitOmni with unified contracts across providers and profile-based adapters.