Spaces:

suvradeepp
/

BTP_2026

Build error

Create a new Space:
- Go to https://huggingface.co/spaces
- Click "Create new Space"
- Choose a name (e.g., "crystallization-predictor")
- Select Streamlit as the SDK
- Choose visibility (Public or Private)
- Click "Create Space"
Upload files:
- Click "Files" tab in your Space
- Click "Add file" → "Upload files"
- Drag and drop ALL files from this huggingface_app folder:
  - app.py
  - requirements.txt
  - README.md
  - .gitattributes
  - .gitignore
  - models/ folder (with all subfolders)
  - visualizations/ folder (with all images)
- Click "Commit changes to main"
Wait for build:
- Hugging Face will automatically build your Space
- Check the "Logs" tab to monitor progress
- Usually takes 2-5 minutes
Test your app:
- Once built, click on the "App" tab
- Your Streamlit app should be running!

Option 2: Git Command Line (Advanced)

Initialize Git LFS:

cd huggingface_app
git lfs install

Clone your Space repository:

git clone https://huggingface.co/spaces/YOUR_USERNAME/YOUR_SPACE_NAME
cd YOUR_SPACE_NAME

Copy files:

# Copy all files from huggingface_app to your cloned repo
# On Windows:
xcopy ..\huggingface_app\* . /E /H /Y

# On Linux/Mac:
cp -r ../huggingface_app/* .

Commit and push:

git add .
git commit -m "Initial deployment of crystallization predictor"
git push

Check deployment:
- Visit your Space URL: https://huggingface.co/spaces/YOUR_USERNAME/YOUR_SPACE_NAME
- Monitor build logs in the "Logs" tab

📁 Files Included

huggingface_app/
├── app.py                          # Main Streamlit application
├── requirements.txt                # Python dependencies
├── README.md                       # Documentation (shown on Space page)
├── .gitattributes                  # Git LFS configuration
├── .gitignore                      # Files to ignore
├── DEPLOYMENT_GUIDE.md            # This file
├── models/
│   ├── simple_baseline/
│   │   ├── model_component_name.pkl
│   │   ├── model_component_ph.pkl
│   │   ├── label_encoder_name.pkl
│   │   ├── scaler.pkl
│   │   ├── tfidf.pkl
│   │   └── training_results.json
│   └── advanced_baseline/
│       ├── model_component_name.pkl
│       ├── model_component_conc.pkl
│       ├── model_component_ph.pkl
│       ├── label_encoder_name.pkl
│       ├── scaler.pkl
│       ├── tfidf.pkl
│       └── training_results.json
└── visualizations/
    ├── 01_component_name_comparison.png
    ├── 02_component_conc_comparison.png
    ├── 03_component_ph_comparison.png
    ├── 04_all_approaches_heatmap.png
    └── 05_complete_comparison.png

🔍 Troubleshooting

Build Fails

Problem: "Could not install packages due to an OSError"

Solution: Check that all dependencies in requirements.txt are compatible
Try pinning versions or using newer versions

Problem: "ModuleNotFoundError"

Solution: Ensure the missing module is in requirements.txt

Model Loading Errors

Problem: "FileNotFoundError: [Errno 2] No such file or directory: 'models/...'"

Solution: Verify all model files were uploaded correctly
Check that folder structure is preserved

Problem: Large file upload fails

Solution: Ensure Git LFS is properly configured
Files over 10MB should use LFS (already configured in .gitattributes)

App Crashes

Problem: "Memory limit exceeded"

Solution: Hugging Face Spaces have memory limits
Consider using smaller models or optimizing loading

Problem: Slow loading

Solution: Models are loaded on first prediction (not at startup)
This is intentional for faster app startup

🎨 Customization

Change App Title/Icon

Edit the `README.md` header: ```yaml

title: Your Custom Title emoji: 🧬 # Change emoji colorFrom: blue # Change colors colorTo: purple


### Modify the App
Edit `app.py` and commit changes. The Space will rebuild automatically.

### Add More Models
1. Add model files to `models/` folder
2. Update `app.py` to load and use new models
3. Update `README.md` to document changes

## 📊 Monitoring

- **Logs**: Check the "Logs" tab in your Space
- **Analytics**: View usage statistics in Space settings
- **Updates**: Any push to the main branch triggers a rebuild

## 🔒 Security & Privacy

- **Public Spaces**: Anyone can use your app and see the code
- **Private Spaces**: Only you and collaborators can access
- **No User Data**: The app doesn't collect or store user inputs
- **Model Files**: Ensure you have rights to distribute the models

## 💰 Costs

- **Free Tier**: 
  - CPU: 2 vCPU, 16GB RAM
  - Perfect for this app
  - No credit card required
  
- **Paid Tiers**: 
  - Available for GPU or more resources
  - Not needed for this application

## 🔗 Useful Links

- Hugging Face Spaces Docs: https://huggingface.co/docs/hub/spaces
- Streamlit Docs: https://docs.streamlit.io/
- Git LFS: https://git-lfs.github.com/

## 📞 Support

If you encounter issues:
1. Check the "Logs" tab in your Space
2. Review Hugging Face Spaces documentation
3. Search Hugging Face forums
4. Open an issue on the repository

## ✅ Pre-Deployment Checklist

- [ ] All model files copied to `models/` folders
- [ ] Visualizations copied to `visualizations/` folder
- [ ] `requirements.txt` has all dependencies
- [ ] `README.md` header configured with title/emoji
- [ ] Tested app locally (`streamlit run app.py`)
- [ ] Git LFS installed and configured
- [ ] Hugging Face account created
- [ ] Space created on Hugging Face

## 🎉 Post-Deployment

After successful deployment:
1. Test all features in the live app
2. Share your Space URL with others
3. Monitor logs for any errors
4. Consider adding:
   - Example inputs/outputs
   - Tutorial video
   - Publication link
   - Citation information

---

**Good luck with your deployment! 🚀**

Your app will be accessible at:
`https://huggingface.co/spaces/YOUR_USERNAME/YOUR_SPACE_NAME`

🚀 Deployment Guide for Hugging Face Spaces

📋 Prerequisites

🔧 Step-by-Step Deployment

Option 1: Web UI Upload (Easiest)