#

retrieval-augmented-generation

Retrieval-augmented generation (RAG) is a technique that improves large language models by retrieving relevant information from external sources and using it to generate more accurate and context-aware responses.

A RAG system combines information retrieval with a language model. It is commonly used in AI assistants, search systems, document question answering, and applications that need access to private or frequently updated information.

Here are 7,554 public repositories matching this topic...

Akramtaha98 / LoRA_Experiment

LoRA/QLoRA/AdaLoRA/DoRA/VeRA fine-tuning for RAG faithfulness Arabic (XQuAD) & Malay (Belebele) QA with mT5, self-critical sequence training, and independent NLI verification.

lora dora vera arabic-nlp mt5 nli peft malay-nlp self-critical-sequence-training huggingface-transformers low-resource-nlp adalora faithfulness qlora retrieval-augmented-generation parameter-efficient-fine-tuning

Updated Sep 8, 2026
Python

linny006 / rag-radar

Live tracker of new RAG implementations, tools, and patterns — updated every 15 minutes

machine-learning awesome-list knowledge-base semantic-search live-data rag vector-search vector-database ai-engineering ai-tools auto-updated ai-development retrieval-augmented llm-tools retrieval-augmented-generation llm-rag rag-tools llm-stack awesome-rag

Updated Sep 8, 2026
Python

shikanon / orag

A Go-native RAG service framework for ingestion, hybrid retrieval, generation, evaluation, and optimization.

golang mcp postgresql openapi hertz rag qdrant retrieval-augmented-generation llm-evaluation eino

Updated Sep 8, 2026
Go

imrohitagrawal / citevyn

Grounded RAG for official AI documentation with citations, strict refusal, evaluation gates, and versioned retrieval.

docker citations observability ai-safety rag fastapi llm pgvector retrieval-augmented-generation llm-evaluation

Updated Sep 8, 2026
Python

1ay1 / agentty

AI pair programming in your terminal — one static binary, sub-ms startup, any model

Updated Sep 8, 2026
C++

onestardao / WFGY

WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.

debugging information-retrieval evaluation knowledge-graph alignment reasoning ai-agents hallucination rag llm retrieval-augmented-generation graphrag

Updated Sep 8, 2026
Jupyter Notebook

infiniflow / ragflow

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

ai ai-agents knowledge-compilation rag context-engine retrieval-augmented-generation llm-apps context-management agentic-search agentic-ai context-engineering agent-harness agentic-retrieval harness-engineering

Updated Sep 8, 2026
Go

dhanoliya-ji / DocMinds

Multi-tenant RAG platform for enterprise documents: ingests 19 file extensions with automatic Tesseract OCR for scans, token-aware page-preserving chunking (tiktoken), local sentence-transformers embeddings in PostgreSQL + pgvector with an HNSW cosine index, and grounded answers with page-level citations via Llama 3.3 on Groq.

ocr nextjs embeddings celery semantic-search rag fastapi vector-database llm pgvector retrieval-augmented-generation

Updated Sep 8, 2026
Python

Raxorr / ragornot

Does RAG actually earn its cost? ragornot runs the same query through four retrieval modes (Flat/BM25, Hierarchical, LLM-only, RAG) against a live AWS Lambda + Bedrock backend and measures latency, quality, cost, and carbon — so you can decide RAG-or-not with data. Static Next.js on GitHub Pages.

benchmark information-retrieval typescript aws-lambda serverless nextjs static-site cloudfront bm25 claude rag llm retrieval-augmented-generation aws-bedrock

Updated Sep 8, 2026
TypeScript

raphasouthall / neurostack

Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection, session harvesting into memories. Local-first.

python markdown open-source mcp knowledge-graph knowledge-base obsidian semantic-search pkm rag local-first retrieval-augmented-generation local-ai ai-memory mcp-server stale-detection

Updated Sep 8, 2026
Python

DanceNitra / agora

An autonomous research organization: agents that do grounded research, test hypotheses with runnable falsifiers, and keep an open track record.

Updated Sep 8, 2026
Python

beenish-majeed / fuzzy-dollop

AI-powered RAG system for querying engineering documentation with grounded answers and source citations.

ai nextjs embeddings semantic-search document-search rag vector-search supabase llm retrieval-augmented-generation

Updated Sep 8, 2026
TypeScript

haystack

deepset-ai / haystack

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

Updated Sep 8, 2026
Python

Mohanaspiringcoder / finrag-rbi-document-qa

A local RAG-based question answering system for RBI documents using ChromaDB, Sentence Transformers, and Llama 3.2 running with Ollama.

fintech rbi rag sentence-transformers llm chromadb retrieval-augmented-generation ollama

Updated Sep 8, 2026
Python

Dongmyung378 / Korean-NLP-RAG

Korean RAG portfolio with BM25-dense retrieval, Cross-Encoder reranking, extractive QA, citations, abstention, and reproducible evaluations.

nlp machine-learning natural-language-processing information-retrieval transformers pytorch question-answering bm25 korean-nlp faiss rag huggingface korquad cross-encoder retrieval-augmented-generation

Updated Sep 8, 2026
Jupyter Notebook

DanceNitra / ramr

RAMR — Retrieval-Augmented Memory Reliability: a contamination-resistant synthetic benchmark for agentic-RAG / memory systems (findings + method)

benchmark retrieval evaluation dataset benchmarks reproducibility synthetic-data rag llm retrieval-augmented-generation llm-evaluation agentic-rag agent-memory contamination-resistant memory-reliability memaudit chain-fragility fake-risk

Updated Sep 8, 2026
Python

SadiqCodex / Website-Grounded-RAG-Agent

A production-ready Website-Grounded RAG Agent that retrieves relevant website content, grounds LLM responses in retrieved context, and generates accurate, source-aware answers using modern RAG and agentic AI techniques.

python natural-language-processing embeddings web-scraping semantic-search ai-agents rag fastapi vector-database llm generative-ai langchain retrieval-augmented-generation agentic-ai

Updated Sep 8, 2026
Python

oracle / ai-optimizer

GenAI/RAG Optimizer and Toolkit for experimentation using Oracle Database AI Vector Search and NL2SQL

embedding-models oracle-database nl2sql vector-database large-language-models generative-ai retrieval-augmented-generation

Updated Sep 8, 2026
Python

causa-rag

laputski / causa-rag

A diagnostic bench for RAG. Scores every question separately, names the pipeline stage that failed, and diffs two runs question by question. Runs entirely on your own machine.

opensearch rag local-first multilingual-search qdrant llmops retrieval-augmented-generation ollama llm-evaluation rag-evaluation

Updated Sep 8, 2026
Python

deokjinlog / docs-rag

검증까지 내장한 한국어 문서 RAG 파이프라인 — Hybrid 검색(BGE-M3+BM25+RRF) · CRAG · Self-RAG · Critic 재생성 · RAGAS 평가

korean-nlp rag fastapi paddleocr crag qdrant llm vllm retrieval-augmented-generation ragas bge-m3 self-rag

Updated Sep 8, 2026
Python

Followers: 679 followers
Website: github.com/topics/rag
Wikipedia: Wikipedia

Related topics

artificial-intelligence embeddings generative-ai llms