Popular repositories Loading

1. speculative-rag speculative-rag Public

   A production-ready Retrieval-Augmented Generation (RAG) system with Speculative Decoding powered by Groq API. Get faster, more accurate responses without downloading massive language models!

   Python 2

2. rag-chatbot-groq rag-chatbot-groq Public

   A Retrieval-Augmented Generation (RAG) based chatbot that reads and understands PDF documents. It uses the Groq API for lightning-fast LLM inference and Chroma as the vector database for context re…

   Python

3. jwt-tokens jwt-tokens Public

   This document provides a comprehensive explanation of JWT (JSON Web Token) authentication, breaking down how tokens work, the structure of JWTs, and detailed walkthroughs of each component in a Fas…

   Python

4. spectral-rag spectral-rag Public

   This repo shows new Retrieval-Augmented Generation technique that improves retrieval quality by using spectral graph theory.

   Python

5. memory-management-system memory-management-system Public

   A streamlined Memory Management System for conversational AI. It analyzes user history, generates concise context notes, rewrites queries for clarity, and classifies user intent with confidence sco…

   Python

6. rag-latency-optimization rag-latency-optimization Public

   A high-performance Speculative RAG pipeline designed to reduce latency by combining fast draft generation and accurate verification using Groq Llama models, local HuggingFace embeddings, ChromaDB v…

   Python