Can I switch it to use my own models? Would it work with Gemma 3? Is vision required (Gemma 3 has it, but unsure if it supports coordinates)?
right now package only supports models from gemini, anthropic and openai. Vision is required. PRs are very welcome! It's very easy to add new model, simply follow any providers in here https://github.com/lmnr-ai/index/tree/main/index/llm/provide...