Chat

const reply = await RunAnywhere.llm.generate([
  { role: 'system', content: 'You are a concise assistant.' },
  { role: 'user', content: 'What is on-device inference?' },
  { role: 'assistant', content: 'Running the model on your own hardware.' },
  { role: 'user', content: 'Why does that matter?' },
])

for await (const event of RunAnywhere.llm.generateStream(messages)) {
  if (event.type === 'textDelta') reply += event.text
}

import type { ChatMessage } from '@runanywhere/web'

const messages: ChatMessage[] = [{ role: 'system', content: 'You are a helpful assistant.' }]

async function send(text: string): Promise<void> {
  messages.push({ role: 'user', content: text })

  let reply = ''
  for await (const event of RunAnywhere.llm.generateStream(messages)) {
    if (event.type === 'textDelta') {
      reply += event.text
      render(reply)
    }
  }

  messages.push({ role: 'assistant', content: reply })
}

if (messages.length > 21) {
  messages.splice(1, messages.length - 21)
}