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: 36 minutes 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 (10 months ago)
• Default Branch: main
• Last Pushed: 2024-11-15T09:51:10.000Z (27 days ago)
• Last Synced: 2024-11-15T10:39:31.137Z (27 days ago)
• Topics: chatbot, cot, graphrag, knowledge-graph, mysql, rag, serverless, vector-database
• Language: TypeScript
• Homepage: https://tidb.ai
• Size: 4.2 MB
• Stars: 203
• Watchers: 15
• Forks: 27
• Open Issues: 46
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE.txt

Awesome Lists containing this project

• StarryDivineSky - pingcap/autoflow
• 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)
• awesome-shadcn-ui - autoflow - pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. (Templates)

README

        




AutoFlow

  

    

  



[![Backend Docker Image Version](https://img.shields.io/docker/v/tidbai/backend?sort=semver&arch=amd64&label=tidbai%2Fbackend&color=blue&logo=fastapi)](https://hub.docker.com/r/tidbai/backend)

[![Frontend Docker Image Version](https://img.shields.io/docker/v/tidbai/frontend?sort=semver&arch=amd64&label=tidbai%2Ffrontend&&color=blue&logo=next.js)](https://hub.docker.com/r/tidbai/frontend)

[![E2E Status](https://img.shields.io/github/check-runs/pingcap/tidb.ai/main?nameFilter=E2E%20Test&label=e2e)](https://tidb-ai-playwright.vercel.app/)

## Introduction



An open source GraphRAG (Knowledge Graph) 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**: [TiDB.AI](https://tidb.ai)

- **Documentation**: [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.

![Image](https://github.com/user-attachments/assets/50a4e5ce-8b93-446a-8ce7-11ed7844bd1e)

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.

![Image](https://github.com/user-attachments/assets/f0dc82db-c14d-4863-a242-c7da3a719568)

## 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

- [shadcn/ui](https://ui.shadcn.com/) - Design

## Contact Us

You can reach out to us on [@TiDB_Developer](https://twitter.com/TiDB_Developer) on Twitter.

## Contributing

We welcome contributions from the community. If you are interested in contributing to the project, please read the [Contributing Guidelines](/CONTRIBUTING.md).



  

    

    

  



## License

TiDB.AI is open-source under the Apache License, Version 2.0. You can [find it here](/LICENSE.txt).