README.md

metadata

title: DataForge
emoji: 💬
colorFrom: yellow
colorTo: purple
sdk: gradio
sdk_version: 5.0.1
app_file: app.py
pinned: false
license: mit
short_description: CodeAct Agent to process large data set
tags:
  - agent-demo-track

🎥 Demo Video

Watch DataForge in Action:

🎬 Click here to watch the full demo on YouTube

---

🔍 DataForge - AI Assistant with File Analysis

An intelligent AI assistant that combines conversational chat capabilities with advanced file analysis using CodeAct agents. Built with Gradio, LangChain, and LangGraph.

✨ Features

💬 Chat Assistant

• Interactive AI chatbot powered by OpenAI GPT-4
• Customizable system messages and parameters
• Real-time streaming responses
• Conversation history support

📁 File Analysis

• Upload & Analyze: Support for various file formats (.txt, .log, .csv, .json, .xml, .py, .js, .html, .md)
• Smart Analysis: Automatic file type detection and tailored analysis
• CodeAct Integration: Uses LangGraph CodeAct agents for deep file analysis
• Comprehensive Insights: Provides security analysis, performance insights, error detection, and statistical summaries

🚀 Getting Started

Prerequisites

• Python 3.11+
• OpenAI API Key

Installations

1. Create and activate virtual environment:

uv venv --python 3.11 
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

2. Install dependencies:

uv pip install -r requirements.txt

3. Set up environment variables:

# Create .env file and add your OpenAI API key
OPENAI_API_KEY=your_openai_api_key_here

Running the Application

python app.py

The application will start a Gradio interface accessible at http://localhost:7860

📊 File Analysis Capabilities

Supported File Types

• Log files (.log, .txt): Security analysis, performance bottlenecks, error detection
• Data files (.csv, .json): Data quality assessment, statistical analysis
• Code files (.py, .js, .html): Structure analysis, best practices review
• Configuration files (.xml, .md): Content analysis and recommendations

Analysis Features

• Security Analysis: Detect threats, suspicious activities, and security patterns
• Performance Insights: Identify bottlenecks and performance issues
• Error Analysis: Categorize and analyze errors and warnings
• Statistical Summary: Basic statistics and data distribution
• Pattern Recognition: Identify trends and anomalies
• Actionable Recommendations: Suggested actions based on analysis

🧪 Testing

A sample server log file (sample_server.log) is included for testing the file analysis functionality.

🛠️ Technical Architecture

• Frontend: Gradio for web interface
• Backend: LangChain for AI orchestration
• Analysis Engine: LangGraph CodeAct agents with PyodideSandbox
• File Processing: Custom FileInjectedPyodideSandbox for secure file analysis
• Model: OpenAI GPT-4 for both chat and analysis

📄 License

MIT License