README.md

metadata

title: DailyRA
emoji: 🚀
colorFrom: gray
colorTo: yellow
sdk: docker
pinned: false

日次RA (Daily Risk Assessment)

A Streamlit application for daily risk assessment in construction and industrial settings, with automatic safety rule generation.

🚀 Features

• Daily Risk Assessment Form: Input work details, hazards, and mitigation measures
• Automatic Rule Generation: AI-powered safety rule extraction based on object relationships
• Database Storage: Persistent storage using Supabase PostgreSQL
• Modern Dependency Management: Uses uv for fast package management

📦 Technology Stack

• Frontend: Streamlit
• Database: Supabase (PostgreSQL)
• NLP: SudachiPy (Japanese tokenization)
• ML: Sentence Transformers
• Package Manager: uv

🏃 Quick Start

See DEPLOYMENT.md for detailed setup instructions.

Local Development

# Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh

# Install package in editable mode (installs dependencies + package)
uv pip install -e .

# Set up environment variables
cp env.example .env
# Edit .env with your Supabase credentials

# Run the app
streamlit run src/daily_ra/app.py

Docker

docker build -t daily-ra .
docker run -p 7860:7860 --env-file .env daily-ra

📦 Using UV

Common Commands

# Install dependencies from pyproject.toml
uv pip install -e .

# Add a new package
uv add requests

# Add with version constraint
uv add "pandas>=2.0.0"

# Remove a package
uv remove package-name

# Update all packages
uv pip install --upgrade -e .

Deployment Guide

📦 Setup Instructions

1️⃣ Set Up Supabase Database

1. Go to your Supabase project dashboard
2. Open the SQL Editor
3. Copy and paste the contents of schema.sql
4. Run the SQL to create the tables

2️⃣ Local Development

1. Install uv (if not already installed):

   curl -LsSf https://astral.sh/uv/install.sh | sh
   

2. Create a .env file in the project root (use env.example as template):

   cp env.example .env
   

3. Fill in your Supabase connection details in .env:

   HOST=aws-1-ap-northeast-1.pooler.supabase.com
   PORT=5432
   DATABASE=postgres
   USERNAME=postgres.vvkubjwatpdqnkmgmntf
   PASSWORD=your-actual-password
   POOL_NAME=vvkubjwatpdqnkmgmntf
   

4. Install package in editable mode:

   uv pip install -e .
   

5. Run the app locally:

   streamlit run src/daily_ra/app.py
   

3️⃣ Deploy to Hugging Face Spaces

1. Push your code to the Hugging Face Space repository

2. Go to your Space Settings → Repository secrets

3. Add the following secrets (get these from your Supabase project settings):

   • HOST = aws-1-ap-northeast-1.pooler.supabase.com (your pooler host)
   • PORT = 5432
   • DATABASE = postgres
   • USERNAME = postgres.vvkubjwatpdqnkmgmntf (format: postgres.YOUR_PROJECT_REF)
   • PASSWORD = your-actual-password

4. The app will automatically rebuild and deploy

---

🔍 Troubleshooting

Connection Issues

• Verify your Supabase password is correct
• Check that your IP is not blocked in Supabase settings
• Ensure connection pooling is enabled in Supabase

Table Errors

• Make sure you've run the schema.sql in Supabase SQL Editor
• Verify the table names match exactly

Environment Variables

• On Hugging Face Spaces, use Repository secrets (not .env file)
• Variable names must match exactly: HOST, PORT, DATABASE, USERNAME, PASSWORD, POOL_NAME

---

📊 Database Tables

daily_ra Table

Stores daily risk assessment entries with work details, hazards, and mitigation measures.

rule_base Table

Stores automatically generated safety rules based on object relationships and potential risks.