How do i use a local ollama model as my model here?

[Travis-Barton]

This is great and looks super powerful, but the cost of so many tokens at scale is going to be huge for heavy use. One great way to cut costs is to use local models + local search (I'll save search for another time) but how can I use my local ollama models with this?

[rlancemartin]

Hi! I have a simpler version below that uses Ollama. The main differences are that 1) it skips the planning phase and 2) it doesn't perform section writing in parallel.
https://github.com/langchain-ai/ollama-deep-researcher