README.md

metadata

title: Langgraph Ui
emoji: 🚀
colorFrom: yellow
colorTo: yellow
sdk: gradio
sdk_version: 5.49.1
app_file: app.py
pinned: false

LangGraph UI

A Gradio-based chat interface for LangGraph supervisor workflow with nested agent visualization and ML pipeline automation.

Features

• 📊 Data extraction from RDB tables using SQL
• 🔤 Language model pretraining with tokenization
• 🎯 Classification model finetuning
• 📈 Comprehensive model evaluation (Precision, Recall, F1-score, Accuracy)
• 🤝 4 specialized agents coordinated by supervisor
• 🇰🇷 Korean language support

Setup

Local Development

1. Install dependencies:

uv sync

2. Set up environment variables: Create a .env file in the root directory (or copy from .env.example):

# Required
OPENAI_API_KEY=your-openai-api-key-here

# Optional: LangSmith Observability
LANGCHAIN_TRACING_V2=true
LANGCHAIN_API_KEY=your-langsmith-api-key-here
LANGCHAIN_PROJECT=langgraph-ui

To get a LangSmith API key:

• Sign up at LangSmith
• Create an API key in your settings
• LangSmith provides observability for all agent executions, traces, and performance metrics

3. Run the application:

uv run python app.py

The application will start on http://localhost:7860

HuggingFace Spaces Deployment

To deploy on HuggingFace Spaces, set these secrets:

1. Go to your Space settings
2. Navigate to "Repository secrets"
3. Add required secret:
   • Name: OPENAI_API_KEY
   • Value: your OpenAI API key
4. (Optional) Add LangSmith secrets for observability:
   • LANGCHAIN_TRACING_V2=true
   • LANGCHAIN_API_KEY=your-langsmith-api-key
   • LANGCHAIN_PROJECT=langgraph-ui

Project Structure

• app.py - Main Gradio application
• ml_pipeline_workflow.py - ML pipeline supervisor workflow with 4 specialized agents
• pyproject.toml - Project dependencies managed by uv
• .env - Environment variables (not tracked in git)
• .env.example - Environment variables template

Technologies

• Gradio - Web UI framework
• LangGraph - Agent orchestration
• LangChain - LLM framework
• OpenAI - LLM provider
• LangSmith - Observability and monitoring (optional)
• uv - Python package manager

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference