📄️ Introduction
Follow some guidance to configure different LLM providers from those supported.
📄️ Gemini
Gemini offers a simplified access to the LLM offering by Google.
📄️ Groq
Groq offers probably the fastest LLM inference service as of writing. Unfortunately, the billing settings are not yet avail and the free tier is limited.
📄️ Hugging Face
Hugging Face offers a Pro subscription for LLM inference and custom hardware for enterprise usage
📄️ Antrophic
Antrophic has an offering for chat inference
📄️ Mistral
Mistral has an offering for chat inference and embedding
📄️ Ollama
Let's setup a local LLMs service to run inference.
📄️ OpenAI
OpenAI offers chat completions and embeddings suport. Additionaly it covers STT/TTS and real time interaction API.