Shuyib/tool_calling_api

This project demonstrates function-calling with Python and Ollama, utilizing the Africa's Talking API to send airtime and messages to phone numbers using natural language prompts. Ollama + LLM w/ functions + Natural language = User Interface for non-coders.

45
/ 100
Emerging

Based on the README's architecture and implementation details, here's a technical summary: The system uses a modular multi-container architecture with Ollama running locally for tool calling via the Inspect safety framework, enabling offline execution of Africa's Talking API operations (SMS, airtime, voice calls, USSD, WhatsApp) through natural language routing. It provides three interface layers—Gradio web UI, CLI, and voice STT mode—all converging through a safety evaluation pipeline before LLM inference. Supports optional Groq API fallback and integrates monitoring via Langtrace and callback servers via ngrok for asynchronous voice operations.

No Package No Dependents
Maintenance 13 / 25
Adoption 6 / 25
Maturity 9 / 25
Community 17 / 25

How are scores calculated?

Stars

20

Forks

11

Language

Python

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Shuyib/tool_calling_api"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.