Build Semantic Search with S-BERT and Fine-tune your model in unsupervised way

An easy-to-use vector database.

Agentic RAG with LangGraph 🔥

A .NET-based AI project leveraging Retrieval-Augmented Generation (RAG) and OpenAI to provide efficient, intelligent search capabilities for team documentation.

LLM-assistant that searches PubMed, retrieves abstracts or full-texts, and generates answers using OpenAI ChatGPT. Features a custom RAG pipeline, semantic search, and knowledge graph generation.

Sematic Cache is a semantic caching library that uses LanceDB for vector storage. It allowing caching of natural language queries based on semantic similarity rather than exact string matching.

Search IATI descriptions using different methods

Docker image of PostgreSQL with vector database extension **pgvector** on Alpine Linux.

Conversational AI code assistant powered by Mistral & RAG. Explore codebases through natural language—ask questions, find functions, understand logic, and generate documentation. Uses vector embeddings for semantic search. Runs locally with Ollama for complete privacy. Zero API costs, your code never leaves your machine.

Developed a semantic search engine as part of the CS-328 Introduction to DataScience course, using word embeddings to retrieve semantically relevant documents. Explored approximate nearest neighbor (ANN) and hashing-based methods to strike a balance between retrieval accuracy and computational efficiency.

Trivia game using Sematic web and Prolog, Little javascript with cool animations.

Backend for a RAG-powered news chatbot providing real-time AI responses, semantic search, and news retrieval using Node.js, Socket.IO, PostgreSQL, Redis, and Qdrant.