VTK Prompt

A command-line interface and web-based UI for generating VTK visualization code using Large Language Models (Anthropic Claude, OpenAI GPT, NVIDIA NIM, and local models).

Features

• Multiple LLM providers: Anthropic Claude, OpenAI GPT, NVIDIA NIM, and local models
• Interactive web UI with live VTK rendering
• Retrieval-Augmented Generation (RAG) with VTK examples database
• Real-time visualization of generated code
• Token usage tracking and cost monitoring
• CLI and Python API for integration

Installation

From PyPI (Stable)

pip install vtk-prompt

From TestPyPI (Latest Development)

pip install -i https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ vtk-prompt

From Source

git clone https://github.com/vicentebolea/vtk-prompt.git
cd vtk-prompt
pip install -e .

Quick Start

1. Set up API keys

export ANTHROPIC_API_KEY="your-anthropic-key"
export OPENAI_API_KEY="your-openai-key"  # Optional

2. Launch Web UI (Recommended)

vtk-prompt-ui

Access the UI at http://localhost:8080

3. Or use CLI

# Generate VTK code
vtk-prompt "Create a red sphere"

# With RAG enhancement
vtk-prompt "Create a sphere with custom resolution" --rag

# Different providers
vtk-prompt "Create a blue cube" --provider openai
vtk-prompt "Create a cone" --provider nim --token YOUR_NIM_TOKEN

Usage

Web UI Features

The web interface provides:

• Model selection: Choose between Claude models (Haiku, Sonnet 4) and other providers
• Token control: Adjust maximum tokens for responses
• Usage tracking: Real-time display of input/output tokens and costs
• RAG integration: Toggle retrieval-augmented generation for better results
• Live preview: See VTK visualizations rendered in real-time
• Code export: View, edit, and copy generated VTK code
• Local & cloud support: Both cloud APIs and local model endpoints

Command Line Interface

# Basic usage
vtk-prompt "Create a red sphere"

# Advanced options
vtk-prompt "Create a textured cone with 32 resolution" \
  --provider anthropic \
  --model claude-opus-4-1-20250805 \
  --max-tokens 4000 \
  --rag \
  --verbose

# Using different providers
vtk-prompt "Create a blue cube" --provider openai --model gpt-5
vtk-prompt "Create a cylinder" --provider nim --model meta/llama3-70b-instruct

RAG (Retrieval Augmented Generation)

Enhance code generation with relevant VTK examples:

1. Build RAG database (one-time setup):

vtk-build-rag

2. Test RAG system (optional):

vtk-test-rag "How to create a cube in VTK"

3. Use RAG in queries:

vtk-prompt "Create a vtkSphereSource with texture mapping" --rag

Python API

from vtk_prompt import VTKPromptClient

client = VTKPromptClient()
code = client.generate_code("Create a red sphere")
print(code)

Configuration

Environment Variables

• ANTHROPIC_API_KEY - Anthropic Claude API key
• OPENAI_API_KEY - OpenAI API key (also used for NVIDIA NIM)

Supported Providers & Models

Provider	Default Model	Base URL
anthropic	claude-opus-4-1-20250805	https://api.anthropic.com/v1
openai	gpt-5	https://api.openai.com/v1
nim	meta/llama3-70b-instruct	https://integrate.api.nvidia.com/v1
custom	User-defined	User-defined (for local models)

Custom/Local Models

You can use local models via OpenAI-compatible APIs:

# Using Ollama
vtk-prompt "Create a sphere" \
  --provider custom \
  --base-url http://localhost:11434/v1 \
  --model llama2

# Using LM Studio
vtk-prompt "Create a cube" \
  --provider custom \
  --base-url http://localhost:1234/v1 \
  --model local-model

CLI Reference

usage: vtk-prompt [-h] [--provider {anthropic,openai,nim,custom}]
                  [-m MODEL] [-k MAX_TOKENS] [-t TOKEN] [--base-url BASE_URL]
                  [-r] [-v] [--collection COLLECTION] [--database DATABASE]
                  [--top-k TOP_K] input_string

Generate VTK visualization code using Large Language Models

positional arguments:
  input_string          Description of the VTK visualization to generate

options:
  -h, --help            Show this help message and exit
  -m MODEL, --model MODEL
                        Model name to use
  -k MAX_TOKENS, --max-tokens MAX_TOKENS
                        Maximum number of tokens to generate
  -t TOKEN, --token TOKEN
                        API token (defaults to environment variable)
  --base-url BASE_URL   Base URL for API (for custom/local models)
  -r, --rag             Use Retrieval Augmented Generation
  -v, --verbose         Show generated source code
  --provider {anthropic,openai,nim,custom}
                        LLM provider to use

RAG Options:
  --collection COLLECTION
                        Collection name for RAG (default: vtk-examples)
  --database DATABASE   Database path for RAG (default: ./db/codesage-codesage-large-v2)
  --top-k TOP_K         Number of examples to retrieve (default: 5)

Available Commands

• vtk-prompt - Main CLI for code generation
• vtk-prompt-ui - Launch web interface
• vtk-build-rag - Build RAG database from VTK examples
• vtk-test-rag - Test RAG functionality
• gen-vtk-file - Generate VTK XML files
• rag-chat - Interactive RAG chat interface

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

For detailed development instructions, see DEVELOPMENT.md which covers:

• Setting up the development environment
• Running tests and linting
• Developer mode for the web UI
• Code formatting and type checking
• Pre-commit hooks

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Architecture

• Core: Python package with CLI and API
• UI: Trame-based web interface with VTK rendering
• RAG: ChromaDB + Llama Index for code example retrieval
• Providers: Unified interface for multiple LLM APIs

Links

• PyPI Package
• Documentation
• Issues
• VTK Documentation

---

Made with care for the VTK and scientific visualization community.