synacktraa/tool-parse
Making LLM Tool-Calling Simpler.
This project helps software developers integrate custom functions and data structures with large language models (LLMs) more easily. It takes Python functions, Pydantic models, or TypedDicts you define and automatically generates the structured descriptions (schemas) that LLMs need to understand and use them. Developers can then use these schemas to allow LLMs to 'call' their code for specific tasks, bridging the gap between an LLM's understanding and executable program logic.
No commits in the last 6 months. Available on PyPI.
Use this if you are a Python developer building applications with LLMs and need a structured way to expose your custom code functions and data models for LLM 'tool-calling' or 'function-calling'.
Not ideal if you are looking for an LLM client library to interact directly with AI models or if you are not a Python developer who writes code.
Stars
30
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 03, 2024
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/synacktraa/tool-parse"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVIDIA/sphinx-llm
LLM extensions for Sphinx Documentation
tensorchord/modelz-llm
OpenAI compatible API for LLMs and embeddings (LLaMA, Vicuna, ChatGLM and many others)
gusye1234/llm-as-function
Embed your LLM into a python function
caua1503/llm-tool-fusion
llm-tool-fusion é uma biblioteca Python que unifica e simplifica o uso de ferramentas com LLMs....
murphyhoucn/llm-dev
LLM Dev