config.py

"""
GeoAI Coding Agent - Configuration
===================================
Configuration settings for the Geospatial AI Coding Assistant.
Supports multiple models via HuggingFace Inference Providers.
"""

# Available Models with their Inference Providers
# Format: {display_name: {"model_id": str, "provider": str}}
AVAILABLE_MODELS = {
    "DeepSeek V3.2": {
        "model_id": "deepseek-ai/DeepSeek-V3.2",
        "provider": "novita",
    },
    "Kimi K2 Instruct": {
        "model_id": "moonshotai/Kimi-K2-Instruct",
        "provider": "novita",
    },
    "Llama 3.1 8B": {
        "model_id": "meta-llama/Llama-3.1-8B-Instruct",
        "provider": "novita",
    },
    "MiniMax M2.1": {
        "model_id": "MiniMaxAI/MiniMax-M2.1",
        "provider": "novita",
    },
    "GLM 4.7 Flash": {
        "model_id": "zai-org/GLM-4.7-Flash",
        "provider": "novita",
    },
    "Mistral 7B v0.2": {
        "model_id": "mistralai/Mistral-7B-Instruct-v0.2",
        "provider": "featherless-ai",
    },
}

# Default model selection
DEFAULT_MODEL = "DeepSeek V3.2"

# Generation Parameters
MAX_NEW_TOKENS = 2048
TEMPERATURE = 0.3
TOP_P = 0.9
REPETITION_PENALTY = 1.1

# Supported Languages
SUPPORTED_LANGUAGES = {
    "python": {"extension": ".py", "highlight": "python", "mime": "text/x-python"},
    "java": {"extension": ".java", "highlight": "java", "mime": "text/x-java"},
    "cpp": {"extension": ".cpp", "highlight": "cpp", "mime": "text/x-c++src"},
    "c": {"extension": ".c", "highlight": "c", "mime": "text/x-csrc"},
    "javascript": {"extension": ".js", "highlight": "javascript", "mime": "text/javascript"},
    "typescript": {"extension": ".ts", "highlight": "typescript", "mime": "text/typescript"},
    "rust": {"extension": ".rs", "highlight": "rust", "mime": "text/x-rustsrc"},
    "markdown": {"extension": ".md", "highlight": "markdown", "mime": "text/markdown"},
    "json": {"extension": ".json", "highlight": "json", "mime": "application/json"},
    "bash": {"extension": ".sh", "highlight": "bash", "mime": "text/x-sh"},
}

# Geospatial System Prompt
SYSTEM_PROMPT = """You are GeoAI Coding Agent, an expert Geospatial Software Engineer and educator specialized in:

## Core Expertise
- **GDAL/OGR**: Raster/vector processing, format conversions, coordinate transformations
- **Rasterio & Fiona**: Pythonic interfaces for raster/vector I/O with NumPy integration
- **GeoPandas & Shapely**: Spatial dataframes, geometric operations, spatial joins
- **PyProj & PROJ**: Coordinate reference systems, transformations, geodetic calculations
- **xarray & rioxarray**: Large-scale raster processing, NetCDF/Zarr, lazy loading

## Language Proficiency
Python, Java, C/C++, JavaScript, TypeScript, Rust

## Response Guidelines
Your audience includes beginner and intermediate learners. Provide educational yet practical responses.

1. **Start with a brief overview**: Explain what the code will accomplish in 1-2 sentences
2. **Provide complete, working code**: Include imports, error handling, and type hints (Python)
3. **Add inline comments**: Explain key lines, especially geospatial-specific operations
4. **Explain the logic**: After the code, provide a "How It Works" section explaining:
    - The overall approach/algorithm
    - Why specific libraries or functions are used
    - What each major step does
5. **Set expectations**: Describe what output to expect (files created, data returned, etc.)
6. **Include tips**: Add beginner-friendly tips, common pitfalls, or alternatives when relevant
7. **Format code blocks** with language specification: ```python, ```java, ```cpp, etc.

## Response Structure
### What This Code Does
Brief overview of the solution.

```[language]
# Well-commented code here
```

### How It Works
1. **Step 1 name**: Explanation of what this step does and why
2. **Step 2 name**: Continue with key steps...

### What to Expect
- Describe the output (files, data structures, visualizations)
- Any dependencies to install

### 💡 Tips for Beginners
- Helpful tips, common mistakes to avoid, or alternative approaches

Be thorough but not overwhelming. Focus on building understanding while providing production-quality code."""

# Example prompts for UI
EXAMPLE_PROMPTS = [
    "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",
    "Read and mosaic multiple NetCDF files with xarray",
    "Implement parallel raster processing with GDAL in C++",
    "Calculate zonal statistics using rasterstats in Python",
]

# File download templates
NOTEBOOK_TEMPLATE = '''{{
    "cells": [
    {{
    "cell_type": "markdown",
    "metadata": {{}},
    "source": [
        "# GeoAI Generated Code\\n",
        "\\n",
        "Generated by GeoAI Coding Agent\\n",
        "\\n",
        "## Query\\n",
        "{query}"
    ]
    }},
    {{
    "cell_type": "code",
    "execution_count": null,
    "metadata": {{}},
    "outputs": [],
    "source": {code_cells}
    }}
    ],
    "metadata": {{
    "kernelspec": {{
    "display_name": "Python 3",
    "language": "python",
    "name": "python3"
    }},
    "language_info": {{
    "name": "python",
    "version": "3.10.0"
    }}
    }},
    "nbformat": 4,
    "nbformat_minor": 4
}}'''

MARKDOWN_TEMPLATE = """# GeoAI Generated Code

## Query
{query}

## Response
{response}

---
*Generated by GeoAI Coding Agent*
"""