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.
AutoFlow is an open source graph rag (graphrag: knowledge graph rag) based knowledge base tool built on top of TiDB Vector and LlamaIndex and DSPy.
- Live Demo: https://tidb.ai
- Deployment Docs: Deployment Docs
- 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.
- 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 with Docker Compose (with: 4 CPU cores and 8GB RAM)
- TiDB – Database to store chat history, vector, json, and analytic
- LlamaIndex - RAG framework
- DSPy - The framework for programming—not prompting—foundation models
- Next.js – Framework
- Tailwind CSS – CSS framework
- shadcn/ui - Design
We welcome contributions from the community. If you are interested in contributing to the project, please read the Contributing Guidelines.
AutoFlow is open-source under the Apache License, Version 2.0. You can find it here.
You can reach out to us on Discord.
This repository contains a Docker Compose configuration for quickly spinning up a TiDB cluster for development or testing purposes.
The cluster consists of:
- PD (Placement Driver): Manages and schedules TiKV nodes
- TiKV: Distributed key-value storage engine
- TiDB: SQL layer compatible with MySQL protocol
- Prometheus: Monitoring system
- Grafana: Visualization for monitoring data
- Docker and Docker Compose installed
- At least 4GB of RAM available for the cluster
Before starting, create the necessary directories:
mkdir -p data/pd data/tikv data/prometheus data/grafana config- Start the TiDB cluster:
docker-compose up -d- Connect to TiDB:
mysql -h 127.0.0.1 -P 4000 -u root-
Access Grafana dashboard:
- URL: http://localhost:3000
- Username: admin
- Password: admin
-
Access Prometheus:
- TiDB is accessible on port 4000 (MySQL protocol)
- Grafana is accessible on port 3000
- Prometheus is accessible on port 9090
- PD is accessible on port 2379
All data is stored in the ./data directory:
./data/pd: PD data./data/tikv: TiKV data./data/prometheus: Prometheus data./data/grafana: Grafana data
To stop the cluster:
docker-compose downTo completely remove the cluster including all data:
docker-compose down
rm -rf data