Scalable agent registry for AI agents using A2A protocol AgentCard with semantic search. AWS serverless (Lambda, S3 Vectors, Bedrock). Python SDK & React Web UI.

MedSage is a multimodal healthcare assistant that combines LLMs, vector search, and real-time reasoning to deliver fast, reliable medical insights. It supports symptom analysis, medical document Q&A, universal file RAG, multilingual interactions, and emergency SOS with live location.

Terminal-based semantic code search. Local, no API keys, live re-indexing

Pure-Python, zero-dependency RAG memory engine for conversational AI. Retrieves semantically relevant messages from conversation history using two-phase retrieval, TF-IDF + concept-overlap scoring, narrative element extraction, and bidirectional typo correction. No embeddings or vector DB required.

A functionally operational, mathematically unhinged system for achieving 10× effective memory amplification on Apple Silicon using quantized fractal compression, complex-plane KV decomposition, and Euler-aligned swap geometry.

Hybrid RAG with three retrievers—Lexical (BM25), Semantic (embeddings), and Hybrid (Reciprocal Rank Fusion) — parallel retrieval, Llama 3 generation, and side-by-side evaluation with reproducible notebooks.

DocMind is a lightweight Retrieval-Augmented Generation (RAG) application. It ingests virtually any document type, converts it into clean Markdown, indexes it into a fully-local semantic search engine, and lets you query it with natural language.

An end-to-end RAG system that grounds LLMs in factual reality, using semantic search on real-time news to provide verifiable, context-aware answers.

DigiBrain is a second brain web platform that stores links (tweets, YouTube videos, documents, etc.) enriched with metadata such as title, description, and tags. The system integrates an AI assistant that retrieves contextually relevant content using embeddings and a vector database.

An end-to-end NLP application built with KeyBERT, Streamlit, and Google Colab to extract semantic keywords from PDF documents using BERT embeddings.

SementicCore: A transformer-based text embedding model trained with contrastive learning (SimCSE approach) for generating high-quality sentence embeddings.

RAG-powered AI engine that indexes any GitHub repo into a FAISS vector database and lets you query the codebase using natural language. Built with FastAPI, Gemini, and FAISS.

An AI-powered Document Q&A system built with FastAPI, React, and Groq. Features Hybrid Search (pgvector + FTS), Semantic & Parent-Child Chunking, Cross-Encoder Reranking, and Llama-3.3 for highly accurate, cited answers.

A high-performance NLP tool built with Streamlit and YAKE! to extract comprehensive semantic keywords from PDF documents with real-time CSV export functionality.

Building production-grade Retrieval-Augmented Generation (RAG) systems. Explore advanced chunking strategies, hybrid search with Weaviate, LLM task orchestration, and fine-grained generation control.

AI-powered customer interview analysis tool — semantic search, insight extraction, and research synthesis built for the Great Question stack.

An AI-powered document assistant that lets you "chat" with your PDFs using Retrieval-Augmented Generation (RAG) and local LLMs

A hands-on exploration of Retrieval-Augmented Generation's core components: semantic search, retriever evaluation, and context-augmented LLM prompting.

An AI-powered Fashion Assistant built using Retrieval-Augmented Generation (RAG). Combines semantic search, reranking, and LLM-based reasoning to deliver intelligent fashion recommendations, product discovery, and 24/7 customer support.

📖 A Retrieval-Augmented Generation (RAG) MCP server for markdown documentation with semantic search capabilities