| Name | vtk-prompt JSON |
| Version |
0.1.0
JSON |
| download |
| home_page | None |
| Summary | A project combining VTK visualization with LLM APIs (Anthropic, OpenAI, NVIDIA NIM) |
| upload_time | 2025-10-24 21:19:12 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.10 |
| license | None |
| keywords |
vtk
visualization
llm
ai
anthropic
openai
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# VTK Prompt
[](https://github.com/vicentebolea/vtk-prompt/actions/workflows/ci.yml)
[](https://github.com/vicentebolea/vtk-prompt/actions/workflows/publish.yml)
[](https://badge.fury.io/py/vtk-prompt)
[](https://www.python.org/downloads/)
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)
```bash
pip install vtk-prompt
```
### From TestPyPI (Latest Development)
```bash
pip install -i https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ vtk-prompt
```
### From Source
```bash
git clone https://github.com/vicentebolea/vtk-prompt.git
cd vtk-prompt
pip install -e .
```
## Quick Start
### 1. Set up API keys
```bash
export ANTHROPIC_API_KEY="your-anthropic-key"
export OPENAI_API_KEY="your-openai-key" # Optional
```
### 2. Launch Web UI (Recommended)
```bash
vtk-prompt-ui
```
Access the UI at `http://localhost:8080`
### 3. Or use CLI
```bash
# 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
```bash
# 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):
```bash
vtk-build-rag
```
2. **Test RAG system** (optional):
```bash
vtk-test-rag "How to create a cube in VTK"
```
3. **Use RAG in queries**:
```bash
vtk-prompt "Create a vtkSphereSource with texture mapping" --rag
```
### Python API
```python
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:
```bash
# 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](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](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](https://pypi.org/project/vtk-prompt/)
- [Documentation](https://github.com/vicentebolea/vtk-prompt)
- [Issues](https://github.com/vicentebolea/vtk-prompt/issues)
- [VTK Documentation](https://vtk.org/documentation/)
---
Made with care for the VTK and scientific visualization community.
Raw data
{
"_id": null,
"home_page": null,
"name": "vtk-prompt",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "vtk, visualization, llm, ai, anthropic, openai",
"author": null,
"author_email": "Vicente Adolfo Bolea Sanchez <vicente.bolea@kitware.com>",
"download_url": "https://files.pythonhosted.org/packages/2d/25/cc3bd422e412d1d9cb19a71f244d19e76d2c2656470dfb98238b2b5a0eab/vtk_prompt-0.1.0.tar.gz",
"platform": null,
"description": "# VTK Prompt\n\n[](https://github.com/vicentebolea/vtk-prompt/actions/workflows/ci.yml)\n[](https://github.com/vicentebolea/vtk-prompt/actions/workflows/publish.yml)\n[](https://badge.fury.io/py/vtk-prompt)\n[](https://www.python.org/downloads/)\n\nA command-line interface and web-based UI for generating VTK visualization code\nusing Large Language Models (Anthropic Claude, OpenAI GPT, NVIDIA NIM, and local\nmodels).\n\n\n\n## Features\n\n- Multiple LLM providers: Anthropic Claude, OpenAI GPT, NVIDIA NIM, and local\n models\n- Interactive web UI with live VTK rendering\n- Retrieval-Augmented Generation (RAG) with VTK examples database\n- Real-time visualization of generated code\n- Token usage tracking and cost monitoring\n- CLI and Python API for integration\n\n## Installation\n\n### From PyPI (Stable)\n\n```bash\npip install vtk-prompt\n```\n\n### From TestPyPI (Latest Development)\n\n```bash\npip install -i https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ vtk-prompt\n```\n\n### From Source\n\n```bash\ngit clone https://github.com/vicentebolea/vtk-prompt.git\ncd vtk-prompt\npip install -e .\n```\n\n## Quick Start\n\n### 1. Set up API keys\n\n```bash\nexport ANTHROPIC_API_KEY=\"your-anthropic-key\"\nexport OPENAI_API_KEY=\"your-openai-key\" # Optional\n```\n\n### 2. Launch Web UI (Recommended)\n\n```bash\nvtk-prompt-ui\n```\n\nAccess the UI at `http://localhost:8080`\n\n### 3. Or use CLI\n\n```bash\n# Generate VTK code\nvtk-prompt \"Create a red sphere\"\n\n# With RAG enhancement\nvtk-prompt \"Create a sphere with custom resolution\" --rag\n\n# Different providers\nvtk-prompt \"Create a blue cube\" --provider openai\nvtk-prompt \"Create a cone\" --provider nim --token YOUR_NIM_TOKEN\n```\n\n## Usage\n\n### Web UI Features\n\nThe web interface provides:\n\n- Model selection: Choose between Claude models (Haiku, Sonnet 4) and other\n providers\n- Token control: Adjust maximum tokens for responses\n- Usage tracking: Real-time display of input/output tokens and costs\n- RAG integration: Toggle retrieval-augmented generation for better results\n- Live preview: See VTK visualizations rendered in real-time\n- Code export: View, edit, and copy generated VTK code\n- Local & cloud support: Both cloud APIs and local model endpoints\n\n### Command Line Interface\n\n```bash\n# Basic usage\nvtk-prompt \"Create a red sphere\"\n\n# Advanced options\nvtk-prompt \"Create a textured cone with 32 resolution\" \\\n --provider anthropic \\\n --model claude-opus-4-1-20250805 \\\n --max-tokens 4000 \\\n --rag \\\n --verbose\n\n# Using different providers\nvtk-prompt \"Create a blue cube\" --provider openai --model gpt-5\nvtk-prompt \"Create a cylinder\" --provider nim --model meta/llama3-70b-instruct\n```\n\n### RAG (Retrieval Augmented Generation)\n\nEnhance code generation with relevant VTK examples:\n\n1. **Build RAG database** (one-time setup):\n\n```bash\nvtk-build-rag\n```\n\n2. **Test RAG system** (optional):\n\n```bash\nvtk-test-rag \"How to create a cube in VTK\"\n```\n\n3. **Use RAG in queries**:\n\n```bash\nvtk-prompt \"Create a vtkSphereSource with texture mapping\" --rag\n```\n\n### Python API\n\n```python\nfrom vtk_prompt import VTKPromptClient\n\nclient = VTKPromptClient()\ncode = client.generate_code(\"Create a red sphere\")\nprint(code)\n```\n\n## Configuration\n\n### Environment Variables\n\n- `ANTHROPIC_API_KEY` - Anthropic Claude API key\n- `OPENAI_API_KEY` - OpenAI API key (also used for NVIDIA NIM)\n\n### Supported Providers & Models\n\n| Provider | Default Model | Base URL |\n| ------------- | ------------------------ | ----------------------------------- |\n| **anthropic** | claude-opus-4-1-20250805 | https://api.anthropic.com/v1 |\n| **openai** | gpt-5 | https://api.openai.com/v1 |\n| **nim** | meta/llama3-70b-instruct | https://integrate.api.nvidia.com/v1 |\n| **custom** | User-defined | User-defined (for local models) |\n\n### Custom/Local Models\n\nYou can use local models via OpenAI-compatible APIs:\n\n```bash\n# Using Ollama\nvtk-prompt \"Create a sphere\" \\\n --provider custom \\\n --base-url http://localhost:11434/v1 \\\n --model llama2\n\n# Using LM Studio\nvtk-prompt \"Create a cube\" \\\n --provider custom \\\n --base-url http://localhost:1234/v1 \\\n --model local-model\n```\n\n## CLI Reference\n\n```\nusage: vtk-prompt [-h] [--provider {anthropic,openai,nim,custom}]\n [-m MODEL] [-k MAX_TOKENS] [-t TOKEN] [--base-url BASE_URL]\n [-r] [-v] [--collection COLLECTION] [--database DATABASE]\n [--top-k TOP_K] input_string\n\nGenerate VTK visualization code using Large Language Models\n\npositional arguments:\n input_string Description of the VTK visualization to generate\n\noptions:\n -h, --help Show this help message and exit\n -m MODEL, --model MODEL\n Model name to use\n -k MAX_TOKENS, --max-tokens MAX_TOKENS\n Maximum number of tokens to generate\n -t TOKEN, --token TOKEN\n API token (defaults to environment variable)\n --base-url BASE_URL Base URL for API (for custom/local models)\n -r, --rag Use Retrieval Augmented Generation\n -v, --verbose Show generated source code\n --provider {anthropic,openai,nim,custom}\n LLM provider to use\n\nRAG Options:\n --collection COLLECTION\n Collection name for RAG (default: vtk-examples)\n --database DATABASE Database path for RAG (default: ./db/codesage-codesage-large-v2)\n --top-k TOP_K Number of examples to retrieve (default: 5)\n```\n\n## Available Commands\n\n- `vtk-prompt` - Main CLI for code generation\n- `vtk-prompt-ui` - Launch web interface\n- `vtk-build-rag` - Build RAG database from VTK examples\n- `vtk-test-rag` - Test RAG functionality\n- `gen-vtk-file` - Generate VTK XML files\n- `rag-chat` - Interactive RAG chat interface\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\nFor detailed development instructions, see [DEVELOPMENT.md](DEVELOPMENT.md)\nwhich covers:\n\n- Setting up the development environment\n- Running tests and linting\n- Developer mode for the web UI\n- Code formatting and type checking\n- Pre-commit hooks\n\n1. Fork the repository\n2. Create your feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'Add some amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Open a Pull Request\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file\nfor details.\n\n## Architecture\n\n- **Core**: Python package with CLI and API\n- **UI**: Trame-based web interface with VTK rendering\n- **RAG**: ChromaDB + Llama Index for code example retrieval\n- **Providers**: Unified interface for multiple LLM APIs\n\n## Links\n\n- [PyPI Package](https://pypi.org/project/vtk-prompt/)\n- [Documentation](https://github.com/vicentebolea/vtk-prompt)\n- [Issues](https://github.com/vicentebolea/vtk-prompt/issues)\n- [VTK Documentation](https://vtk.org/documentation/)\n\n---\n\nMade with care for the VTK and scientific visualization community.\n",
"bugtrack_url": null,
"license": null,
"summary": "A project combining VTK visualization with LLM APIs (Anthropic, OpenAI, NVIDIA NIM)",
"version": "0.1.0",
"project_urls": {
"Homepage": "https://github.com/vicentebolea/vtk-prompt",
"Issues": "https://github.com/vicentebolea/vtk-prompt/issues",
"Repository": "https://github.com/vicentebolea/vtk-prompt"
},
"split_keywords": [
"vtk",
" visualization",
" llm",
" ai",
" anthropic",
" openai"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "a1da44ead723596eb9d4d5d79ac94dd5666f986b9af56678ef9aee83a7419c91",
"md5": "09c8816d7199d54d26a69cf4fe4f38ad",
"sha256": "120ea07a603d85fdf2c6fb85b55cd993a9293fef4f44396164efb6b6ac5c361e"
},
"downloads": -1,
"filename": "vtk_prompt-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "09c8816d7199d54d26a69cf4fe4f38ad",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 37838,
"upload_time": "2025-10-24T21:19:11",
"upload_time_iso_8601": "2025-10-24T21:19:11.329378Z",
"url": "https://files.pythonhosted.org/packages/a1/da/44ead723596eb9d4d5d79ac94dd5666f986b9af56678ef9aee83a7419c91/vtk_prompt-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "2d25cc3bd422e412d1d9cb19a71f244d19e76d2c2656470dfb98238b2b5a0eab",
"md5": "44ff95cd7d393b3a9211f8b012f83d86",
"sha256": "a33164ba6aa22845fc230e7453c2c4d783adaa710a7e805d14759fae06901581"
},
"downloads": -1,
"filename": "vtk_prompt-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "44ff95cd7d393b3a9211f8b012f83d86",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 791652,
"upload_time": "2025-10-24T21:19:12",
"upload_time_iso_8601": "2025-10-24T21:19:12.963039Z",
"url": "https://files.pythonhosted.org/packages/2d/25/cc3bd422e412d1d9cb19a71f244d19e76d2c2656470dfb98238b2b5a0eab/vtk_prompt-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-24 21:19:12",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "vicentebolea",
"github_project": "vtk-prompt",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "vtk-prompt"
}
