retrieval-augmented-generation

Home Assistant LLM integration for local OpenAI-compatible services (llamacpp, vllm, etc)

Official Implementation for the ACL 2026 paper "SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression"

Akcio is a demonstration project for Retrieval Augmented Generation (RAG). It leverages the power of LLM to generate responses and uses vector databases to fetch relevant documents to enhance the quality and relevance of the output.

Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.

Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP exits.

Official Implementation of "Multi-Head RAG: Solving Multi-Aspect Problems with LLMs"

OriginTrail Decentralized Knowledge Graph network node

RAG with langchain using Amazon Bedrock and Amazon OpenSearch

A collection of RAG systems powered by LLM.

A lightweight, production-ready RAG (Retrieval Augmented Generation) library in Go.

Lightweight chat AI platform featuring custom knowledge, open-source LLMs, prompt-engineering, retrieval analysis. Highly customizable. For Retrieval-Centric & Retrieval-Augmented Generation.

Backend library for conversational AI in biomedicine

Official code for NeurIPS2025 "Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers"

📁 This repository hosts a growing collection of AI blueprint projects that run end-to-end using Jupyter notebooks, MLflow deployments, and Streamlit web apps.🛠️ All projects are built using HP AI Studio with ❤️ If you find this useful, please don’t forget to star the repository ⭐ and support our work 🚀

Visualization for a Retrieval-Augmented Generation (RAG) Assistant 🤖❤️📚

A curated list of battle-tested tools, frameworks, and best practices for building scalable, production-grade Retrieval-Augmented Generation (RAG) systems.

Provenance-first extractive RAG: return verbatim source spans with citations using local ModernBERT or optional LLM-assisted extraction.

[ICLR'26] AutoGEO: a Generative Engine Optimization framework to automatically learn generative engine preferences, and rewrite web contents for more traction.

Turn PDFs into clean, structured Markdown

🔥🔥🔥 Enterprise AI middleware, alternative to unifyapps, n8n, lyzr