| Name | mtllm JSON |
| Version |
0.3.9
JSON |
| download |
| home_page | None |
| Summary | MTLLM Provides Easy to use APIs for different LLM Providers to be used with Jaseci's Jaclang Programming Language. |
| upload_time | 2025-07-16 03:40:54 |
| maintainer | Jason Mars |
| docs_url | None |
| author | Jason Mars |
| requires_python | None |
| license | MIT |
| keywords |
llm
jaclang
jaseci
mtllm
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# MTLLM - AI Integration Framework for Jac-lang
[](https://pypi.org/project/mtllm/) [](https://github.com/jaseci-labs/jaseci/actions/workflows/test-jaseci.yml)
Meaning Typed Programming (MTP) is a programming paradigm for AI integration where prompt engineering is hidden through code semantics. MTLLM is the plugin built, exploring this hypothesis. MTLLM is built as a plugin to the Jaseci ecosystem. This plugin can be installed as a PyPI package.
```bash
pip install mtllm
```
## Basic Example
A basic usecase of MTP can be demonstrated as follows:
```python
import from mtllm{Model}
glob llm = Model(model_name="openai\gpt-4o");
def translate_to(language: str, phrase: str) -> str by llm();
with entry {
output = translate_to(language="Welsh", phrase="Hello world");
print(output);
}
```
## AI-Powered Object Generation
```python
import from mtllm {Model}
glob llm = Model(model_name="gpt-4o");
obj Task {
has description: str,
priority: int,
estimated_time: int;
}
sem Task.priority = "priority between 0 (highest priority) and 10(lowest priority)";
def create_task(description: str, previous_tasks: list[Task]) -> Task by llm();
with entry {
tasks = [];
new_task = create_task("Write documentation for the API", tasks);
print(f"Task: {new_task.description}, Priority: {new_task.priority}, Time: {new_task.estimated_time}min");
}
```
The `by` abstraction allows to automate semantic extraction from existing code semantics, eliminating manual prompt engineering while leveraging type annotations for structured AI responses.
## Documentation and Examples
**📚 Full Documentation**: [Jac MTLLM Documentation](https://www.jac-lang.org/learn/jac-mtllm/with_llm/)
**🎮 Complete Examples**:
- [Fantasy Trading Game](https://www.jac-lang.org/learn/examples/mtp_examples/fantasy_trading_game/) - Interactive RPG with AI-generated characters
- [RPG Level Generator](https://www.jac-lang.org/learn/examples/mtp_examples/rpg_game/) - AI-powered game level creation
- [RAG Chatbot Tutorial](https://www.jac-lang.org/learn/examples/rag_chatbot/Overview/) - Building chatbots with document retrieval
**🔬 Research**: The research journey of MTP is available on [Arxiv](https://arxiv.org/abs/2405.08965).
## Quick Links
- [Getting Started Guide](https://www.jac-lang.org/learn/jac-mtllm/with_llm/)
- [Model Configuration](https://www.jac-lang.org/learn/jac-mtllm/model_declaration/)
- [Jac Language Documentation](https://www.jac-lang.org/)
- [GitHub Repository](https://github.com/jaseci-labs/jaseci)
Raw data
{
"_id": null,
"home_page": null,
"name": "mtllm",
"maintainer": "Jason Mars",
"docs_url": null,
"requires_python": null,
"maintainer_email": "jason@jaseci.org",
"keywords": "llm, jaclang, jaseci, mtllm",
"author": "Jason Mars",
"author_email": "jason@jaseci.org",
"download_url": "https://files.pythonhosted.org/packages/ec/6c/5953b91773375856bbb6087948f57f0ea0b5b7d71ea544bc2959acfea79a/mtllm-0.3.9.tar.gz",
"platform": null,
"description": "# MTLLM - AI Integration Framework for Jac-lang\n\n[](https://pypi.org/project/mtllm/) [](https://github.com/jaseci-labs/jaseci/actions/workflows/test-jaseci.yml)\n\nMeaning Typed Programming (MTP) is a programming paradigm for AI integration where prompt engineering is hidden through code semantics. MTLLM is the plugin built, exploring this hypothesis. MTLLM is built as a plugin to the Jaseci ecosystem. This plugin can be installed as a PyPI package.\n\n```bash\npip install mtllm\n```\n\n## Basic Example\n\nA basic usecase of MTP can be demonstrated as follows:\n\n```python\nimport from mtllm{Model}\n\nglob llm = Model(model_name=\"openai\\gpt-4o\");\n\ndef translate_to(language: str, phrase: str) -> str by llm();\n\nwith entry {\n output = translate_to(language=\"Welsh\", phrase=\"Hello world\");\n print(output);\n}\n```\n\n## AI-Powered Object Generation\n\n```python\nimport from mtllm {Model}\n\nglob llm = Model(model_name=\"gpt-4o\");\n\nobj Task {\n has description: str,\n priority: int,\n estimated_time: int;\n}\n\nsem Task.priority = \"priority between 0 (highest priority) and 10(lowest priority)\";\n\ndef create_task(description: str, previous_tasks: list[Task]) -> Task by llm();\n\nwith entry {\n tasks = [];\n new_task = create_task(\"Write documentation for the API\", tasks);\n print(f\"Task: {new_task.description}, Priority: {new_task.priority}, Time: {new_task.estimated_time}min\");\n}\n```\n\nThe `by` abstraction allows to automate semantic extraction from existing code semantics, eliminating manual prompt engineering while leveraging type annotations for structured AI responses.\n\n## Documentation and Examples\n\n**\ud83d\udcda Full Documentation**: [Jac MTLLM Documentation](https://www.jac-lang.org/learn/jac-mtllm/with_llm/)\n\n**\ud83c\udfae Complete Examples**:\n- [Fantasy Trading Game](https://www.jac-lang.org/learn/examples/mtp_examples/fantasy_trading_game/) - Interactive RPG with AI-generated characters\n- [RPG Level Generator](https://www.jac-lang.org/learn/examples/mtp_examples/rpg_game/) - AI-powered game level creation\n- [RAG Chatbot Tutorial](https://www.jac-lang.org/learn/examples/rag_chatbot/Overview/) - Building chatbots with document retrieval\n\n**\ud83d\udd2c Research**: The research journey of MTP is available on [Arxiv](https://arxiv.org/abs/2405.08965).\n\n## Quick Links\n\n- [Getting Started Guide](https://www.jac-lang.org/learn/jac-mtllm/with_llm/)\n- [Model Configuration](https://www.jac-lang.org/learn/jac-mtllm/model_declaration/)\n- [Jac Language Documentation](https://www.jac-lang.org/)\n- [GitHub Repository](https://github.com/jaseci-labs/jaseci)",
"bugtrack_url": null,
"license": "MIT",
"summary": "MTLLM Provides Easy to use APIs for different LLM Providers to be used with Jaseci's Jaclang Programming Language.",
"version": "0.3.9",
"project_urls": null,
"split_keywords": [
"llm",
" jaclang",
" jaseci",
" mtllm"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "6d80c5a3339e958fb18497841ed427246b3260fff7fac3bfb3d44caf494609fe",
"md5": "9c8d50a4ba7fc995ff22990fe69560e2",
"sha256": "73516f32d07b31e8f7283bb3ca5e7bba16023d79fcfaa9ebf1428abf2e7c48c2"
},
"downloads": -1,
"filename": "mtllm-0.3.9-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "9c8d50a4ba7fc995ff22990fe69560e2",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": null,
"size": 13773,
"upload_time": "2025-07-16T03:40:53",
"upload_time_iso_8601": "2025-07-16T03:40:53.408445Z",
"url": "https://files.pythonhosted.org/packages/6d/80/c5a3339e958fb18497841ed427246b3260fff7fac3bfb3d44caf494609fe/mtllm-0.3.9-py2.py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "ec6c5953b91773375856bbb6087948f57f0ea0b5b7d71ea544bc2959acfea79a",
"md5": "4ed7ed1bb2a09025f3833e1d36103b62",
"sha256": "6d2f935314060b9e1d59facccb61841ba099a1adee79728b1eba7e19ced656c6"
},
"downloads": -1,
"filename": "mtllm-0.3.9.tar.gz",
"has_sig": false,
"md5_digest": "4ed7ed1bb2a09025f3833e1d36103b62",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 12895,
"upload_time": "2025-07-16T03:40:54",
"upload_time_iso_8601": "2025-07-16T03:40:54.881925Z",
"url": "https://files.pythonhosted.org/packages/ec/6c/5953b91773375856bbb6087948f57f0ea0b5b7d71ea544bc2959acfea79a/mtllm-0.3.9.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-16 03:40:54",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "mtllm"
}
