Add an ollama plugin

Ollama makes it easy to run models such as llama2 locally on macOS easily:

https://ollama.ai/

The user runs a server on localhost, so the architecture of the plugin could likely follow the existing replicate plugin.

from the ollama docs:

 curl -X POST http://localhost:11434/api/generate -d '{
    "model": "llama2",
    "prompt":"Why is the sky blue?"
   }'

the output is quite straightforward and amenable to streaming:

{"model":"llama2","created_at":"2023-08-24T20:24:05.78795Z","response":" The","done":false}
{"model":"llama2","created_at":"2023-08-24T20:24:05.805889Z","response":" sky","done":false}
{"model":"llama2","created_at":"2023-08-24T20:24:05.824734Z","response":" appears","done":false}
{"model":"llama2","created_at":"2023-08-24T20:24:05.842502Z","response":" blue","done":false}
{"model":"llama2","created_at":"2023-08-24T20:24:05.860295Z","response":" because","done":false}
...

Start by reading the existing replicate plugin and the Ollama API example in the issue. Implement an Ollama plugin that connects to the localhost server, sends prompts to the generate endpoint, and handles its streaming response format; done means local Ollama generation works through the project’s plugin interface.