# `Mead.Provider.Ollama`
[🔗](https://github.com/albertosca/mead/blob/main/lib/mead/provider/ollama.ex#L1)

`Mead.Provider` backed by the Ollama chat API, meant for the `local` slot of `Mead.Router`.

## Options

  * `:model` - the model to run, for example `"llama3.1"`. Required: there is no default, because
    the installed models cannot be known from here. A missing or empty value is `:invalid_options`.
  * `:base_url` - where Ollama listens; defaults to `http://localhost:11434`.
  * `:receive_timeout` - milliseconds to wait for the answer; defaults to 25 seconds, below the
    default turn timeout so a slow server reports its own reason first.
  * `:keep_alive` - how long Ollama keeps the model in memory after a request, as a duration string such as `"30m"` or a number of seconds (`-1` is forever); left out of the request by default, so the server's own setting applies. The first request after a model was unloaded pays the load, which took 28 s for a 2 GB model and is longer than the default `:receive_timeout`; a deployment that cannot afford that sets `:keep_alive` and raises `:receive_timeout` together with the turn timeout.
  * `:req_options` - extra options merged into the `Req` request, used by tests to stub the
    network.

Requests go to `POST {base_url}/api/chat` with `stream: false`, are never retried, and carry no
credentials. A refused connection is `{:transport, :econnrefused}`, which means Ollama is not
running.

`converse_stream/4` posts with `stream: true` and reads the answer line by line, calling `on_delta` with each piece of text; it returns what `converse/3` would, built by the same parser.

`converse/3` also sends `tools` (omitted from the request when the list is empty) in the function form Ollama expects, and returns the text of the answer followed by one `tool_use` block per tool call. Ollama gives a tool call no id, so the provider synthesizes `call_1`, `call_2`, and so on, in order of appearance; a tool result is matched back to its tool name through the assistant message right before it. A model that does not support tools answers HTTP 400, which becomes `:tools_unsupported` when tools were sent; there is no retry without tools, so the turn fails.

---

*Consult [api-reference.md](api-reference.md) for complete listing*