Skip to content
#

rag-pipeline

rag logo

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 2,551 public repositories matching this topic...

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.

  • Updated Sep 29, 2026
  • Python

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM applications.

  • Updated Aug 30, 2026
  • Python

Declarative AI pipelines in one YAML file. Tokens, audio chunks, and video frames flow between isolated components. Compose 100+ components for models, agents, speech, vision, and live broadcast. Run local models, cloud APIs, or both. Inspired by docker-compose.

  • Updated Oct 1, 2026
  • Python
kektordb

AI memory system combining vector search with temporal knowledge graph. Built-in cognitive engine for agents. Supports memory decay, contradiction detection, and MCP integration.

  • Updated Sep 23, 2026
  • Go