Zafer-Liu/Data-Analysis-Agent

What it solves

It enables non-technical users to perform complex business data analysis using natural language instead of writing SQL queries or manually building charts. It bridges the gap between raw data sources (files or databases) and actionable business insights by automating the technical pipeline of data retrieval and visualization.

How it works

Users connect a data source and ask questions in plain language. The agent then executes a multi-step process:

1. Intent Understanding: Interprets the user's request.
2. Schema Analysis: Identifies the structure of the connected data.
3. SQL Generation: Automatically writes and executes the necessary SQL query.
4. Visualization: Recommends and generates the most appropriate chart from a library of 43 types across 6 categories.
5. Insight Generation: Provides a business summary of the findings.

This process is delivered via Server-Sent Events (SSE) for real-time transparency. The system is compatible with various LLMs (DeepSeek, OpenAI, AtlasCloud) and supports extensions via MCP (Model Context Protocol) and a custom business knowledge base.

Who it’s for

• Business analysts and managers who need quick data insights without SQL knowledge.
• Users who want to automate the generation of business reports (Excel, Word, PPT).
• Teams using Feishu (Lark) who want to integrate data analysis directly into group chats via a bot.

Highlights

• Multi-Source Connectivity: Supports Excel, CSV, SQLite, MySQL, PostgreSQL, and SQL Server.
• Extensive Visualization: Automatically selects from 43 different chart types (e.g., Sankey, Treemap, Violin plots).
• Advanced Analytics: Includes built-in tools for K-Means clustering, decision tree modeling, and outlier handling (trimming/winsorizing).
• Export Capabilities: Generates formatted Excel tables, .docx reports, and PPT presentations.
• Feishu Integration: Can read Feishu multi-dimensional tables and return analysis results directly to chat groups.