Streaming Responses

Response streaming can be enabled by setting stream: true, modifying function calls to return an AsyncGenerator where each part is an object in the stream.

const ollama = useOllama()

const message = { role: 'user', content: 'Why is the sky blue?' }
const response = await ollama.chat({ model: 'llama3.1', messages: [message], stream: true })

for await (const part of response) {
  process.stdout.write(part.message.content)
}