Create a new client, with an ollama endpoint, which should be something like "http://localhost:11434/api".

Pull Model: Allow insecure connections for pulling models.

Embeddings & Chat: Controls how long the model will stay loaded into memory following the request.

Embeddings & Chat: model-specific options.

Pull Model: Stream the response as it is received.

Embeddings: Does not truncate the end of each input to fit within context length.

EmbeddingMeta is the metadata for a generated embedding vector.

Message with text or object content.

Metrics.

ModelDetails are the details of the model.

ModelMeta is the metadata for an ollama model.

PullStatus provides the status of a pull operation in a callback function.

Chat Response.

Data represents the raw binary data of an image file.

ModelInfo provides additional model parameters.