https://github.com/pingcap/autoflow
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai
https://github.com/pingcap/autoflow
chatbot cot graphrag knowledge-graph mysql rag serverless vector-database
Last synced: 3 days ago
JSON representation
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai
- Host: GitHub
- URL: https://github.com/pingcap/autoflow
- Owner: pingcap
- License: apache-2.0
- Created: 2024-02-05T06:53:14.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-31T10:08:21.000Z (14 days ago)
- Last Synced: 2025-04-11T20:59:06.742Z (3 days ago)
- Topics: chatbot, cot, graphrag, knowledge-graph, mysql, rag, serverless, vector-database
- Language: TypeScript
- Homepage: https://tidb.ai
- Size: 5.41 MB
- Stars: 2,508
- Watchers: 25
- Forks: 146
- Open Issues: 76
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE.txt
Awesome Lists containing this project
- StarryDivineSky - pingcap/autoflow
- awesome-hacking-lists - pingcap/autoflow - pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai (TypeScript)
- awesome-shadcn-ui - autoflow - An open source GraphRAG (Knowledge Graph) built on top of TiDB Vector and LlamaIndex and DSPy. [Demo site](https://tidb.ai) (Boilerplates / Templates / Portfolios)
- definitive-opensource - AutoFlow
README
AutoFlow
[](https://hub.docker.com/r/tidbai/backend)
[](https://hub.docker.com/r/tidbai/frontend)
[](https://tidb-ai-playwright.vercel.app/)
> [!WARNING]
> Autoflow is still in the early stages of development. And we are actively working on it, the next move is to make it to a python package and make it more user-friendly e.g. `pip install autoflow-ai`. If you have any questions or suggestions, please feel free to contact us on [Discussion](https://github.com/pingcap/autoflow/discussions).
## Introduction
AutoFlow is an open source graph rag (graphrag: knowledge graph rag) based knowledge base tool built on top of [TiDB Vector](https://www.pingcap.com/ai?utm_source=tidb.ai&utm_medium=community) and [LlamaIndex](https://github.com/run-llama/llama_index) and [DSPy](https://github.com/stanfordnlp/dspy).
- **Live Demo**: [https://tidb.ai](https://tidb.ai?utm_source=tidb.ai&utm_medium=community)
- **Deployment Docs**: [Deployment Docs](https://tidb.ai/docs/?utm_source=github&utm_medium=tidb.ai)
## Features
1. **Perplexity-style Conversational Search page**: Our platform features an advanced built-in website crawler, designed to elevate your browsing experience. This crawler effortlessly navigates official and documentation sites, ensuring comprehensive coverage and streamlined search processes through sitemap URL scraping.
2. **Embeddable JavaScript Snippet**: Integrate our conversational search window effortlessly into your website by copying and embedding a simple JavaScript code snippet. This widget, typically placed at the bottom right corner of your site, facilitates instant responses to product-related queries.
## Deploy
- [Deploy with Docker Compose](https://tidb.ai/docs/deploy-with-docker) (with: 4 CPU cores and 8GB RAM)
## Tech Stack
- [TiDB](https://www.pingcap.com/ai?utm_source=tidb.ai&utm_medium=community) – Database to store chat history, vector, json, and analytic
- [LlamaIndex](https://www.llamaindex.ai/) - RAG framework
- [DSPy](https://github.com/stanfordnlp/dspy) - The framework for programming—not prompting—foundation models
- [Next.js](https://nextjs.org/) – Framework
- [Tailwind CSS](https://tailwindcss.com/) – CSS framework
- [shadcn/ui](https://ui.shadcn.com/) - Design
## Contributing
We welcome contributions from the community. If you are interested in contributing to the project, please read the [Contributing Guidelines](/CONTRIBUTING.md).
## License
AutoFlow is open-source under the Apache License, Version 2.0. You can [find it here](https://github.com/pingcap/autoflow/blob/main/LICENSE.txt).
## Contact
You can reach out to us on [Discord](https://discord.gg/XzSW23Jg9p).