DeepAnalyze
DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师,自动分析大量数据,一键生成专业分析报告!
What is DeepAnalyze?
DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师,自动分析大量数据,一键生成专业分析报告!
Overview of DeepAnalyze
What it is
DeepAnalyze is an agentic large language model for autonomous data science. It is designed to complete data-centric tasks without human intervention, covering the entire data science pipeline from data preparation to report generation. The project is fully open-source, including the model, code, training data, and demo.
Key features
- Supports the entire data science pipeline: data preparation, analysis, modeling, visualization, and report generation.
- Conducts open-ended data research on structured data (Databases, CSV, Excel), semi-structured data (JSON, XML, YAML), and unstructured data (TXT, Markdown).
- Produces analyst-grade research reports automatically.
- Fully open-source: model, code, training data, and demo are all publicly available.
- Provides multiple interfaces: WebUI, WebUI v2, JupyterUI, and Command Line Terminal UI.
- Supports OpenAI-style API endpoints and Docker-based sandboxed code execution.
Use cases
DeepAnalyze can be used for autonomous data analysis, visualization, and reporting in a browser. It is suitable for data discovery, code-execution challenges, and any data-centric tasks where users bring their data and questions to uncover insights.
Getting started
To deploy DeepAnalyze-8B via vllm and launch the WebUI:bashvllm serve DeepAnalyze-8Bcd demo/chat/frontendnpm installcd ..bash start.shFor WebUI v2:bashcd demo/chat_v2/frontendnpm installcd ..cp .env.example .envbash start.shFor CLI:bashvllm serve DeepAnalyze-8Bcd APIpython start_server.pycd demo/clipython api_cli.py
License and pricing
The project is licensed under MIT and is open-source. Pricing is not stated.
Based on the project's public README and repository metadata.