Back to directory

AutoFlow

An open-source conversational knowledge base that answers questions over a graph-based retrieval-augmented-generation pipeline built on TiDB's vector storage.

AutoFlow

AutoFlow is an open-source Graph RAG knowledge base tool, combining a knowledge graph with retrieval-augmented generation and built on TiDB Serverless vector storage, LlamaIndex, and DSPy. It presents a conversational search page backed by a website crawler that follows sitemaps to index documentation and other sites.

The search widget can be embedded into any website as a JavaScript snippet, typically placed in a corner of the page, to answer visitors' product questions instantly. The project is still in early development, deploys with Docker Compose on modest hardware, and the maintainers say the next step is to package it as a Python library.

AutoFlow is written in TypeScript and released under the Apache License 2.0.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.