A framework for benchmarking embedding models in hybrid search scenarios (BM25 + vector search) using Weaviate.

Simple RAG system powered by Milvus.

Enterprise Legal AI for India — RAG-powered research, contract analysis & document drafting built for 1.67M advocates. No hallucinations. Indian corpus. Indian law.

EduPilot is an intelligent course assistant built for Indiana University students. It answers questions across four graduate courses — AML, ADT, STAT, and LLM — using a seven-stage multi-agent RAG pipeline that retrieves directly from course lecture slides and materials, cites every claim and verifies its own answers, and refuses to hallucinate.

🔍 Benchmark embedding models in hybrid search with Weaviate. Evaluate MRR@K, Hit@K, latency, and memory using your data or MTEB datasets.

A 3-stage Information Retrieval engine leveraging Elasticsearch, BERT embeddings, and RRF to implement a robust Hybrid Search strategy for EU Research Projects.

A production-ready Retrieval-Augmented Generation (RAG) system for semantic search over product reviews.

Hybrid BM25-powered search & DB management toolkit for PostgreSQL/pgvector with LangChain integration

A multi-turn agentic dialogue system built on hybrid dense-sparse retrieval, hierarchical agent coordination, and rubric-based evaluation. Designed for real-world deployment with FastAPI serving, streaming responses, and full observability

Hybrid semantic + BM25 search system for natural language recruiter queries. Matches candidates to jobs using sentence-transformers, ChromaDB, and rank_bm25.

A simple hybrid search Flask application that integrates traditional full-text (lexical/BM25) search with semantic (neural sparse embeddings) search. It also provides autocomplete functionality.