---
title: Geoai Coding Agent
emoji: 🌍
colorFrom: pink
colorTo: red
sdk: gradio
sdk_version: 6.3.0
app_file: app.py
pinned: false
license: agpl-3.0
tags:
  - geospatial
  - geospatial-ai
  - AI
  - ML
  - DL
  - LLM
  - satellite-data
  - earth-observation
  - nlp
  - maps
  - data-visualization
  - natural-language
  - gradio
  - huggingface
short_description: GeoAI Coding Agent - Geospatial AI Coding Assistant"
---

# 🌍 GeoAI Coding Agent

A **Geospatial AI Coding Assistant** powered by multiple LLMs via HuggingFace Inference Providers.

Specialized in **GDAL/OGR**, **Rasterio**, **GeoPandas**, **xarray**, and geospatial development across multiple programming languages. Designed for **beginner and intermediate learners** with educational explanations.

![Python](https://img.shields.io/badge/Python-3.10+-blue.svg)
![Gradio](https://img.shields.io/badge/Gradio-6.3+-orange.svg)
![License](https://img.shields.io/badge/License-AGPL--3.0-green.svg)

## ✨ Features

- **🤖 Multiple AI Models**: Choose from 6 different models (DeepSeek, Kimi, Llama, MiniMax, GLM, Mistral)
- **🗺️ Geospatial Expertise**: Deep knowledge of GDAL, Rasterio, GeoPandas, PyProj, xarray, and rioxarray
- **📚 Educational Focus**: Responses include code explanations, step-by-step logic, and tips for beginners
- **💻 Multi-Language Support**: Python, Java, C/C++, JavaScript, TypeScript, Rust
- **📥 Download Options**: Export responses as Markdown or code files
- **🎨 Code Editor Style UI**: Syntax highlighting with dark theme
- **⚡ Streaming Responses**: Real-time token streaming for better UX

## 🤖 Available Models

| Model | Provider | Speed | Best For |
|-------|----------|-------|----------|
| **DeepSeek V3.2** | Novita | Medium | Complex geospatial tasks, detailed explanations |
| **Kimi K2 Instruct** | Novita | Medium | General coding, good balance |
| **Llama 3.1 8B** | Novita | Fast | Quick answers, simple tasks |
| **MiniMax M2.1** | Novita | Medium | Creative solutions |
| **GLM 4.7 Flash** | Novita | Fast | Fast responses, basic tasks |
| **Mistral 7B v0.2** | Featherless | Fast | Quick prototyping |

> 💡 **Tip**: Larger models provide better results but take longer. Smaller models are faster for simple queries.

## 🚀 Quick Start

### Local Development

1. **Clone the repository**
   ```bash
   git clone https://github.com/rifatSDAS/geoai-coding-agent.git
   cd geoai-coding-agent
   ```

2. **Create virtual environment**
   ```bash
   python -m venv venv
   source venv/bin/activate  # Linux/Mac
   # or
   venv\Scripts\activate  # Windows
   ```

3. **Install dependencies**
   ```bash
   pip install -r requirements.txt
   ```

4. **Run the application**
   ```bash
   python app.py
   ```

5. **Open in browser**: Navigate to `http://localhost:7860`

6. **Enter your HuggingFace token**: Get one at [huggingface.co/settings/tokens](https://huggingface.co/settings/tokens)

### Run Tests

```bash
pytest test_app.py -v
```

## 🐳 HuggingFace Spaces Deployment

1. **Create a new Space** at [huggingface.co/new-space](https://huggingface.co/new-space)
   - Select **Gradio** as the SDK
   - Choose **CPU basic** (free tier)

2. **Upload files**
   - `app.py`
   - `config.py`
   - `requirements.txt`
   - `README.md` (optional)

3. **That's it!** The Space will automatically build and deploy.

## 📁 Project Structure

```
geoai-coding-agent/
├── app.py              # Main Gradio application
├── config.py           # Configuration, prompts, templates
├── test_app.py         # Unit tests
├── requirements.txt    # Python dependencies
├── .gitignore          # Git ignore rules
└── README.md           # This file
```

## 🎯 Example Queries

- *"Read a GeoTIFF with rasterio and calculate NDVI from Sentinel-2 bands"*
- *"Convert shapefile to GeoJSON using GDAL/OGR in Python"*
- *"Reproject a raster from EPSG:4326 to EPSG:32632 using rasterio"*
- *"Clip a large COG raster to a polygon boundary using rioxarray"*
- *"Create a spatial join between two GeoDataFrames in GeoPandas"*
- *"Implement parallel raster processing with GDAL in C++"*

## ⚙️ Configuration

Key settings in `config.py`:

| Parameter          | Default           | Description                                 |
| ------------------ | ----------------- | ------------------------------------------- |
| `DEFAULT_MODEL`    | `DeepSeek V3.2`   | Default model selection                     |
| `MAX_NEW_TOKENS`   | `2048`            | Maximum response length                     |
| `TEMPERATURE`      | `0.3`             | Sampling temperature (lower = more focused) |
| `TOP_P`            | `0.9`             | Nucleus sampling threshold                  |
| `AVAILABLE_MODELS` | (see table above) | Dictionary of available models & providers  |

## 🔑 API Token

This application requires a **HuggingFace API token** with Inference Provider permissions.

**Required permissions**:
- ✅ Make calls to Inference Providers

Get your free token at: [huggingface.co/settings/tokens](https://huggingface.co/settings/tokens)

For HuggingFace Spaces deployment, add the token as a **Secret** named `HF_TOKEN` in Space Settings.

## 🛠️ Supported Languages

| Language   | Extension    | Use Case                      |
|------------|--------------|-------------------------------|
| Python     | `.py`        | GDAL, Rasterio, GeoPandas     |
| Java       | `.java`      | GeoTools, JTS                 |
| C/C++      | `.c`, `.cpp` | GDAL C API, performance       |
| JavaScript | `.js`        | Leaflet, OpenLayers, Turf.js  |
| TypeScript | `.ts`        | Type-safe geospatial apps     |
| Rust       | `.rs`        | GDAL Rust bindings, geo crate |

## 📦 Dependencies

- **gradio**: Web UI framework
- **huggingface-hub**: HF Inference API client
- **pytest**: Testing framework

## 🙏 Acknowledgments

- Inspired by [GeoAI-Assistance-Ext](https://github.com/rifatSDAS/GeoAI-Assistance-Ext) VS Code Extension
- Powered by multiple LLMs via [HuggingFace Inference Providers](https://huggingface.co/docs/huggingface_hub/guides/inference)
- Built with [Gradio](https://gradio.app/)

## About the Developer

Built by Dr. Kazi Rifat Ahmed, a Full Stack Geospatial AI Engineer, Co-founder and Technical Lead for Satellite Data Services business in Space sector.

## Contributing

Contributions welcome! Please feel free to submit issues and pull requests.

## Contact

For collaboration opportunities in satellite data services & applications, large-scale satellite data analytics, geospatial AI, blockchain & quantum computing for geospatial applications, or advanced geospatial science, technology & applications, feel free to reach out!

Portfolio at https://rifatsdas.github.io/

## 📄 License

This project is licensed under the **GNU Affero General Public License v3.0** (AGPL-3.0).

See [LICENSE](LICENSE.md) for details.

---

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