autoflow
(opens in a new tab)
Introduction
An open source GraphRAG (Knowledge Graph) built on top of TiDB Vector (opens in a new tab) and LlamaIndex (opens in a new tab) and DSPy (opens in a new tab).
- Live Demo: TiDB.AI (opens in a new tab)
- Documentation: Docs (opens in a new tab)
Features
-
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.
You can even edit the Knowledge Graph to add more information or correct any inaccuracies. This feature is particularly useful for enhancing the search experience and ensuring that the information provided is accurate and up-to-date.
-
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 (opens in a new tab) (with: 4 CPU cores and 8GB RAM)
Tech Stack
- TiDB (opens in a new tab) – Database to store chat history, vector, json, and analytic
- LlamaIndex (opens in a new tab) - RAG framework
- DSPy (opens in a new tab) - The framework for programming—not prompting—foundation models
- Next.js (opens in a new tab) – Framework
- shadcn/ui (opens in a new tab) - Design
Contact Us
You can reach out to us on @TiDB_Developer (opens in a new tab) on Twitter.
Contributing
We welcome contributions from the community. If you are interested in contributing to the project, please read the Contributing Guidelines.
License
TiDB.AI is open-source under the Apache License, Version 2.0. You can find it here.