spring-ai-alibaba/DataAgent

Spring AI Alibaba DataAgent

What it solves

DataAgent transforms traditional Text-to-SQL tools into an enterprise-grade AI data analyst. It solves the problem of complex data retrieval and analysis by allowing users to perform multi-table queries, execute deep Python-based analysis, and generate visual reports using natural language, rather than requiring manual SQL writing or data science expertise.

How it works

Built on Spring AI Alibaba Graph, the system uses a StateGraph-based workflow to convert natural language into SQL. For deeper insights, it utilizes a Python sandbox to execute generated code in task-level containers with dynamic dependency support. It incorporates a Human-in-the-loop mechanism for user intervention during the planning phase and uses RAG (Retrieval-Augmented Generation) with vector databases to retrieve business metadata and terminology to improve SQL accuracy.

Who it’s for

It is designed for enterprises that need an intelligent layer over their databases to provide data insights to non-technical users or to accelerate the workflow of data analysts.

Highlights

  • Python Deep Analysis: Executes generated code in secure containers with support for PEP 723 dynamic dependencies and automatic cleanup.
  • Intelligent Reporting: Automatically summarizes analysis results into HTML/Markdown reports featuring ECharts visualizations.
  • MCP Server Support: Implements the Model Context Protocol, allowing it to integrate as a tool server for ecosystems like Claude Desktop.
  • Flexible Model Integration: Fully compatible with OpenAI API specifications, supporting various LLMs (e.g., Qwen, Deepseek) and customizable vector databases.

Related

  • Project
    AMA-CMFAI/LAMBDA

    A data analysis agent that converts natural-language questions into reproducible analysis workflows, including code execution, visualization, and report generation.

  • Project
    Zafer-Liu/Data-Analysis-Agent

    A conversational AI agent for business data analysis that converts natural language questions into SQL queries, visualizations, and business insights.

  • Project
    dataease/SQLBot

    An intelligent data questioning system based on LLMs and RAG that enables conversational data analysis (ChatBI) by converting natural language into SQL queries.

  • Project
    Tswoen/Paper-Agent

    Paper‑Agent is an open‑source AI research assistant that automates literature review creation. It uses a LangGraph‑driven workflow of specialized agents (search, read, analyse, outline, write) that call LLMs (OpenAI/Anthropic compatible) to retrieve papers from arXiv, OpenAlex, and Semantic Scholar, download PDFs, convert them to markdown, chunk and embed the text in ChromaDB, analyse sub‑topics, generate a structured outline, and write each section of a review. A FastAPI backend streams real‑time progress via SSE, persisting sessions in SQLite + files, while a Vue 3 front‑end lets users configure model providers, monitor token usage, and resume work after refresh. Installation uses the `uv` Python package manager and npm for the UI; configuration is done via `config/model.json`. The project is fully open source and invites contributions via tests and PRs.

  • Project
    iDC-NEU/YiGraph

    YiGraph is an intelligent graph data analysis agent system that uses the AAG framework to convert natural language questions into executable graph algorithm workflows for complex relational data analysis.