This post is part of the Voice Assistant on Raspberry Pi series.
In article #5, we injected weather data into every conversation, even for questions like “what’s your name?”. That wastes tokens. Function calling fixes this: the LLM decides when it needs a tool and only calls it when the question actually warrants it.
The complete code for this article is available on GitHub.
[Read More]This post is part of the Voice Assistant on Raspberry Pi series.
Article #2 ended with a hardcoded response, which was enough to confirm the audio pipeline works. Now we swap that line for a real HTTP call to Ollama on the pi-cerveau, and add a system prompt to give the assistant a personality and some knowledge about your home.
The complete code for this article is available on GitHub.
[Read More]This post is part of the Voice Assistant on Raspberry Pi series.
Both Pis are configured. Time to write some code. The goal: validate the full audio pipeline on the pi-client, from button press to spoken response, without a real LLM. We hardcode a reply for now. The LLM comes in article #3.
The complete code for this article is available on GitHub.
[Read More]