Ollama preload keep alive

[frangin2003]

Issue

N/A

Change

In order to ensure that Ollama model is ready to go at startup, I have introduced an optional preload boolean keyword argument (default set to False) to the Ollama LLM, allowing the model to be preloaded into memory during the initialization phase. This feature includes a preload_model method to trigger preloading at a later time if desired. The preloading process leverages the Ollama FAQ's recommended approach of calling generate with an empty prompt (see how-can-i-pre-load-a-model-to-get-faster-response-times).
Additionally, the keep_alive parameter is now usable to be passed and tell for how long the model stays in memory.

General checklist

• There are no breaking changes
• I have added unit and integration tests for my change
• I have manually run all the unit and integration tests in the module I have added/changed, and they are all green
• I have manually run all the unit and integration tests in the core and main modules, and they are all green

• I have added/updated the documentation
• I have added an example in the examples repo (only for "big" features)