pingcap/autoflow
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai
Combines LlamaIndex and DSPy frameworks for structured RAG with knowledge graph construction, storing vectors and chat history in TiDB's multi-modal database. Features a Perplexity-style conversational search interface with built-in sitemap-based web crawlers, plus embeddable JavaScript widgets for integrating AI search into external websites.
2,745 stars.
Stars
2,745
Forks
177
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Jan 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/pingcap/autoflow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
AstraBert/e-library-agent
A virtual agent for your virtual books📚
luuisotorres/AML-MultiAgent-RAG
A Multi-Agent RAG platform using Vector DBs and AI models to accurately answer AML/CFT...
vennelchenfoo/slack-it-rag-agent
AI-powered IT support agent for Slack using RAG architecture with n8n, OpenAI, and Supabase
inngest/weaviate-agentic-workflow
A Dinner generator agentic workflow built with Inngest and Weaviate
Fizmath/Agentic_RAG_APP
Agentic RAG APP with FastAPI, Ollama and Vue.js UI