中文 | English
Enterprise-grade Intelligent Data Analyst powered by Spring AI Alibaba
Text-to-SQL | Python Deep Analysis | Intelligent Reports | MCP Server | RAG Enhancement
Introduction • Core Features • Quick Start • Documentation • Community
DataAgent is an enterprise-grade intelligent data analysis Agent built on Spring AI Alibaba Graph. It goes beyond traditional Text-to-SQL tools, evolving into an AI-powered data analyst capable of executing Python deep analysis and generating multi-dimensional chart reports.
The system adopts a highly extensible architecture design, fully compatible with OpenAI API specifications for chat models and embedding models, and supports flexible integration with any vector database. Whether for private deployment or integration with mainstream LLM services (such as Qwen, Deepseek), it can be easily adapted to provide flexible and controllable data insight services for enterprises.
Additionally, this project natively supports MCP (Model Context Protocol), enabling seamless integration as an MCP server into MCP-compatible ecosystem tools such as Claude Desktop.
| Feature | Description |
|---|---|
| Intelligent Data Analysis | StateGraph-based Text-to-SQL conversion, supporting complex multi-table queries and multi-turn conversation intent understanding. |
| Python Deep Analysis | Executes generated code in task-scoped Spring AI Alibaba Sandbox containers with PEP 723 dynamic dependencies, resource limits, retries, and automatic cleanup. |
| Intelligent Report Generation | Analysis results are automatically summarized into HTML/Markdown reports with ECharts visualizations, WYSIWYG. |
| Human Feedback Mechanism | Innovative Human-in-the-loop mechanism, supporting user intervention and adjustments during the plan generation phase. |
| RAG Retrieval Enhancement | Integrated vector database, supporting semantic retrieval of business metadata and terminology libraries to improve SQL generation accuracy. |
| Multi-Model Orchestration | Built-in model registry, supporting runtime dynamic switching between different LLM and Embedding models. |
| MCP Server | Compliant with MCP protocol, supporting external provision of NL2SQL and agent management capabilities as a Tool Server. |
| API Key Management | Comprehensive API Key lifecycle management with fine-grained permission control. |
For detailed installation and configuration guidance, see the Quick Start Guide.
- JDK 17+
- MySQL 5.7+
- Node.js 22+
- pnpm 11+
- Docker (required when a workflow executes Python steps)
# 1. Import database
mysql -u root -p < data-agent-management/src/main/resources/sql/schema.sql
# 2. Start backend
./mvnw -pl data-agent-management spring-boot:run
# 3. Start the frontend in another terminal
cd data-agent-frontend-nuxt
pnpm install && pnpm devOpen your browser and visit http://localhost:3000 to start creating your first data agent!
| Document | Contents |
|---|---|
| Quick Start | Environment requirements, database import, basic configuration, getting started |
| Architecture Design | System layered architecture, StateGraph and workflow design, core module sequence diagrams |
| Developer Guide | Development environment setup, detailed configuration manual, coding standards, extension development (vector DB/models) |
| Advanced Features | API Key invocation, MCP server configuration, custom hybrid retrieval strategies, SAA Python sandbox, and dynamic dependencies |
| Knowledge Configuration Best Practices | Explanation and usage of semantic models, business knowledge, and agent knowledge |
- DingTalk Group:
154405001431("DataAgent User Group 1") Some users may not be able to join due to account security issues. If possible, please try with a different account. - Contribution Guide: Community contributions are welcome! Please refer to the Developer Guide to learn how to submit PRs.
- Contribution Rules: For contribution workflow details, see the English guide or the Chinese guide.
This project is licensed under the Apache License 2.0.