ollama

type Client ¶

type Client struct {
	// contains filtered or unexported fields
}

Client is an Ollama LLM client.

Ollama allows you to run large language models locally on your machine. This client connects to a local Ollama server (default: localhost:11434) and provides the same interface as cloud-based providers.

No API key is required. The client uses a longer default timeout (60s) since local models may take more time to generate responses.

func DefaultOllamaClient() (*Client, error)

func New(config Config) (*Client, error)

func (c *Client) Chat(ctx context.Context, messages []core.Message, opts ...core.Option) (*core.Response, error)

func (c *Client) ChatStream(ctx context.Context, messages []core.Message, opts ...core.Option) (*core.Stream, error)

type Config ¶

type Config struct {
	base.Config
}

Config defines configuration for the Ollama client.

Ollama is for running LLMs locally. It doesn't require an API key.

Example:

config := ollama.Config{
    Config: base.Config{
        Model:   "llama2",
        BaseURL: "http://localhost:11434",
    },
}
client, err := ollama.New(config)