RAG Application with Optimizations on HNSW Index, Quantization, Hybrid Search and Semantic Caching 🗽

This repository contains an application application using Qdrant as Vector Database, Hybrid Seach with SPLADE embeddings, semantic caching and some optimization insights related to the configuration of the HNSW Index and quantization

For detailed project descriptions, refer to these Medium blogs:

• Part 1

• Part 2

Tech Stack

Feel free to ⭐ and clone this repo 😉