| Name | struktx-ai JSON |
| Version |
0.0.2b1
JSON |
| download |
| home_page | None |
| Summary | A configurable, typed AI framework with swappable LLM, classifier, handlers, and optional memory |
| upload_time | 2025-08-28 21:34:20 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.10.0 |
| license | MIT |
| keywords |
ai
chatbot
framework
langchain
llm
nlp
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<div align="center">
<img src="/docs/public/logo-blue.png" alt="StruktX Logo" width="120" height="120">
<br>
<img src="/docs/public/nobg-both-white.png" alt="StruktX" width="200">
A configurable, typed AI framework with swappable LLM, classifier, handlers, and memory for Natural Language to Action apps
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/MIT)
</div>
## Quick Install
### Using uv (Recommended)
```bash
# Install with core dependencies only
uv pip install struktx-ai
# Install with LLM support (LangChain)
uv pip install struktx-ai[llm]
# Install with vector store support
uv pip install struktx-ai[vector]
# Install with all optional dependencies
uv pip install struktx-ai[all]
# Install for development
uv pip install struktx-ai[dev]
```
### Using pip
```bash
# Install with core dependencies only
pip install struktx-ai
# Install with LLM support (LangChain)
pip install struktx-ai[llm]
# Install with vector store support
pip install struktx-ai[vector]
# Install with all optional dependencies
pip install struktx-ai[all]
```
### Source
```bash
# Create virtual env
uv venv
# Activate environment
source .venv/bin/activate
# Sync and install pyproject dependencies
uv sync
# Install finall Strukt package
uv pip install struktx-ai[all]
```
## Quick Start with LangChain
```python
from strukt import create, StruktConfig, HandlersConfig, LLMClientConfig, ClassifierConfig
from strukt.classifiers.llm_classifier import DefaultLLMClassifier
from strukt.prompts import DEFAULT_CLASSIFIER_TEMPLATE
from strukt.examples.time_handler import TimeHandler
from langchain_openai import ChatOpenAI
from strukt.langchain_helpers import LangChainLLMClient
# Create LangChain LLM client
langchain_llm = ChatOpenAI(api_key="your-openai-api-key")
llm = LangChainLLMClient(langchain_llm)
app = create(StruktConfig(
llm=LLMClientConfig(llm),
classifier=ClassifierConfig(
factory=DefaultLLMClassifier(
llm=llm,
prompt_template=DEFAULT_CLASSIFIER_TEMPLATE,
allowed_types=["time_service", "weather", "general"],
max_parts=4,
)
),
handlers=HandlersConfig(
registry={"time_service": TimeHandler(llm)},
default_route="general",
),
))
app.invoke("What is the time in Tokyo?")
```
## What is StruktX?
StruktX is a Python framework for building AI applications with focus on natural language -> actions
- **🔄 Swappable Components**: LLM clients, classifiers, handlers, and memory engines
- **📝 Type Safety**: Full type hints and Pydantic models
- **⚙️ Configurable**: Factory-based configuration system
- **🔌 Extensible**: Easy to add custom components
- **🧠 Memory Support**: Optional conversation memory
- **🔧 Middleware**: Pre/post processing hooks
## Features
- **LLM Integration**: Support for any LLM via the `LLMClient` interface
- **Query Classification**: Route requests to appropriate handlers
- **Structured Outputs**: Pydantic model integration
- **Memory Engines**: Conversation history and context
- **Middleware System**: Pre/post processing hooks
- **LangChain Helpers**: Easy integration with LangChain ecosystem
## Requirements
- Python 3.10+
- Core: `pydantic>=2.0.0`, `python-dotenv>=1.0.0`
- Optional: LangChain packages, vector stores, etc.
## License
MIT License - see [LICENSE](LICENSE) file for details.
## Contributing
Contributions are welcome! Please report any issues, bugs, improvements, or features on GitHub.
## Support
- 📖 [Documentation](https://struktx.snowheap.ai/docs)
- 🐛 [Issue Tracker](https://github.com/snowheapllc/StruktX/issues)
- 💬 [Discussions](https://github.com/snowheapllc/StruktX/discussions)
<div align="right">
<a href="https://github.com/snowheapllc">
<img src="/docs/public/snowheap.png" alt="Snowheap LLC Logo" width="100">
</a>
</div>
Raw data
{
"_id": null,
"home_page": null,
"name": "struktx-ai",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10.0",
"maintainer_email": "Snowheap LLC <info@snowheap.com>",
"keywords": "ai, chatbot, framework, langchain, llm, nlp",
"author": null,
"author_email": "Snowheap LLC <info@snowheap.com>",
"download_url": "https://files.pythonhosted.org/packages/ee/6c/27f161f3f505559f129dc9df2282643132cd46a014a33b684e13fc54a87f/struktx_ai-0.0.2b1.tar.gz",
"platform": null,
"description": "<div align=\"center\">\n <img src=\"/docs/public/logo-blue.png\" alt=\"StruktX Logo\" width=\"120\" height=\"120\">\n <br>\n <img src=\"/docs/public/nobg-both-white.png\" alt=\"StruktX\" width=\"200\">\n \n A configurable, typed AI framework with swappable LLM, classifier, handlers, and memory for Natural Language to Action apps\n \n [](https://www.python.org/downloads/)\n [](https://opensource.org/licenses/MIT)\n</div>\n\n\n\n\n\n\n## Quick Install\n\n### Using uv (Recommended)\n```bash\n# Install with core dependencies only\nuv pip install struktx-ai\n\n# Install with LLM support (LangChain)\nuv pip install struktx-ai[llm]\n\n# Install with vector store support\nuv pip install struktx-ai[vector]\n\n# Install with all optional dependencies\nuv pip install struktx-ai[all]\n\n# Install for development\nuv pip install struktx-ai[dev]\n```\n\n### Using pip\n```bash\n# Install with core dependencies only\npip install struktx-ai\n\n# Install with LLM support (LangChain)\npip install struktx-ai[llm]\n\n# Install with vector store support\npip install struktx-ai[vector]\n\n# Install with all optional dependencies\npip install struktx-ai[all]\n```\n\n### Source\n```bash\n# Create virtual env\nuv venv\n\n# Activate environment\nsource .venv/bin/activate\n\n# Sync and install pyproject dependencies\nuv sync\n\n# Install finall Strukt package\nuv pip install struktx-ai[all]\n```\n\n## Quick Start with LangChain\n```python\nfrom strukt import create, StruktConfig, HandlersConfig, LLMClientConfig, ClassifierConfig\nfrom strukt.classifiers.llm_classifier import DefaultLLMClassifier\nfrom strukt.prompts import DEFAULT_CLASSIFIER_TEMPLATE\nfrom strukt.examples.time_handler import TimeHandler\n\nfrom langchain_openai import ChatOpenAI\nfrom strukt.langchain_helpers import LangChainLLMClient\n\n# Create LangChain LLM client\nlangchain_llm = ChatOpenAI(api_key=\"your-openai-api-key\")\nllm = LangChainLLMClient(langchain_llm)\n\napp = create(StruktConfig(\n llm=LLMClientConfig(llm),\n classifier=ClassifierConfig(\n factory=DefaultLLMClassifier(\n llm=llm,\n prompt_template=DEFAULT_CLASSIFIER_TEMPLATE,\n allowed_types=[\"time_service\", \"weather\", \"general\"],\n max_parts=4,\n )\n ),\n handlers=HandlersConfig(\n registry={\"time_service\": TimeHandler(llm)},\n default_route=\"general\",\n ),\n))\n\napp.invoke(\"What is the time in Tokyo?\")\n```\n\n## What is StruktX?\n\nStruktX is a Python framework for building AI applications with focus on natural language -> actions\n\n- **\ud83d\udd04 Swappable Components**: LLM clients, classifiers, handlers, and memory engines\n- **\ud83d\udcdd Type Safety**: Full type hints and Pydantic models\n- **\u2699\ufe0f Configurable**: Factory-based configuration system\n- **\ud83d\udd0c Extensible**: Easy to add custom components\n- **\ud83e\udde0 Memory Support**: Optional conversation memory\n- **\ud83d\udd27 Middleware**: Pre/post processing hooks\n\n## Features\n\n- **LLM Integration**: Support for any LLM via the `LLMClient` interface\n- **Query Classification**: Route requests to appropriate handlers\n- **Structured Outputs**: Pydantic model integration\n- **Memory Engines**: Conversation history and context\n- **Middleware System**: Pre/post processing hooks\n- **LangChain Helpers**: Easy integration with LangChain ecosystem\n\n## Requirements\n\n- Python 3.10+\n- Core: `pydantic>=2.0.0`, `python-dotenv>=1.0.0`\n- Optional: LangChain packages, vector stores, etc.\n\n## License\n\nMIT License - see [LICENSE](LICENSE) file for details.\n\n## Contributing\n\nContributions are welcome! Please report any issues, bugs, improvements, or features on GitHub.\n\n## Support\n\n- \ud83d\udcd6 [Documentation](https://struktx.snowheap.ai/docs)\n- \ud83d\udc1b [Issue Tracker](https://github.com/snowheapllc/StruktX/issues)\n- \ud83d\udcac [Discussions](https://github.com/snowheapllc/StruktX/discussions)\n\n<div align=\"right\">\n <a href=\"https://github.com/snowheapllc\">\n <img src=\"/docs/public/snowheap.png\" alt=\"Snowheap LLC Logo\" width=\"100\">\n </a>\n</div>\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A configurable, typed AI framework with swappable LLM, classifier, handlers, and optional memory",
"version": "0.0.2b1",
"project_urls": {
"Bug Tracker": "https://github.com/snowheapllc/struktx/issues",
"Documentation": "https://struktx.snowheap.ai",
"Homepage": "https://github.com/snowheapllc/struktx",
"Repository": "https://github.com/snowheapllc/struktx.git",
"Source Code": "https://github.com/snowheapllc/struktx"
},
"split_keywords": [
"ai",
" chatbot",
" framework",
" langchain",
" llm",
" nlp"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "97c6453e5f18e86a570d70125dd9cb4319ad39ff110170dece9c7f12fd1a4e4f",
"md5": "528712e8418282bd8042917cf1010103",
"sha256": "dac78566881403e68905e34f72f1a40806e743f0fedcc933a5f86436eaf22b53"
},
"downloads": -1,
"filename": "struktx_ai-0.0.2b1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "528712e8418282bd8042917cf1010103",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10.0",
"size": 70354,
"upload_time": "2025-08-28T21:34:18",
"upload_time_iso_8601": "2025-08-28T21:34:18.915198Z",
"url": "https://files.pythonhosted.org/packages/97/c6/453e5f18e86a570d70125dd9cb4319ad39ff110170dece9c7f12fd1a4e4f/struktx_ai-0.0.2b1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "ee6c27f161f3f505559f129dc9df2282643132cd46a014a33b684e13fc54a87f",
"md5": "929df52d5239630004e6ee6965c269d2",
"sha256": "5a683b093ad71ba10a5556f76ba84ef0782c99acb1a95dd0c06e31194ae66ccd"
},
"downloads": -1,
"filename": "struktx_ai-0.0.2b1.tar.gz",
"has_sig": false,
"md5_digest": "929df52d5239630004e6ee6965c269d2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10.0",
"size": 53972,
"upload_time": "2025-08-28T21:34:20",
"upload_time_iso_8601": "2025-08-28T21:34:20.300024Z",
"url": "https://files.pythonhosted.org/packages/ee/6c/27f161f3f505559f129dc9df2282643132cd46a014a33b684e13fc54a87f/struktx_ai-0.0.2b1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-28 21:34:20",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "snowheapllc",
"github_project": "struktx",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "struktx-ai"
}
