The ollama() function acts as an interface for interacting with local AI models via the Ollama API.
It integrates seamlessly with the main tidyllm verbs such as chat() and embed().
ollama(..., .called_from = NULL)The result of the requested action:
For chat(): An updated LLMMessage object containing the model's response.
For embed(): A matrix where each column corresponds to an embedding.
Parameters to be passed to the appropriate Ollama-specific function, such as model configuration, input text, or API-specific options.
An internal argument specifying the verb (e.g., chat, embed)
the function is invoked from. This argument is automatically managed by tidyllm and
should not be set by the user.
Some functionalities, like ollama_download_model() or ollama_list_models()
are unique to the Ollama API and do not have a general verb counterpart.
These functions can be only accessed directly.
Supported Verbs:
chat(): Sends a message to an Ollama model and retrieves the model's response.
embed(): Generates embeddings for input texts using an Ollama model.
send_batch(): Behaves different than the other send_batch() verbs since it immediately processes the answers