Cancel a stream

const controller = new AbortController()
stopButton.onclick = () => controller.abort()               // user pressed Stop
const timer = setTimeout(() => controller.abort(), 60_000)  // or a 60 s limit
 
let text = ''
try {
  const res = await fetch('/api/ask', {                     // your backend, which streams from Syntic
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({ q: 'Tell me a long story about a lighthouse keeper.' }),
    signal: controller.signal,
  })
  const reader = res.body.pipeThrough(new TextDecoderStream()).getReader()
  for (let r = await reader.read(); !r.done; r = await reader.read()) {
    text += r.value
    output.textContent = text
  }
} catch (err) {
  if (err.name !== 'AbortError') throw err
  output.textContent = text + ' [stopped]'
} finally {
  clearTimeout(timer)
}

// Express route (server side)
app.post('/api/ask', async (req, res) => {
  const upstreamAbort = new AbortController()
  res.on('close', () => upstreamAbort.abort())              // browser disconnected or aborted
  try {
    const upstream = await fetch('https://app.syntic.ai/v1/chat/completions', {
      method: 'POST',
      headers: { Authorization: `Bearer ${process.env.SYNTIC_API_KEY}`, 'Content-Type': 'application/json' },
      body: JSON.stringify({ model: 'Amara Quick', messages: [{ role: 'user', content: String(req.body.q) }] }),
      signal: upstreamAbort.signal,
    })
    // ...parse events and res.write() the text pieces, as in "Stream in Node.js"
  } catch (err) {
    if (err.name !== 'AbortError') console.error(err)
  }
})

import OpenAI from 'openai'
 
const client = new OpenAI({ baseURL: 'https://app.syntic.ai/v1', apiKey: process.env.SYNTIC_API_KEY })
 
const stream = await client.chat.completions.create({
  model: 'Amara S1.2',
  stream: true,
  messages: [{ role: 'user', content: 'Count slowly from 1 to 500, one number per line.' }],
})
 
let pieces = 0
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '')
  if (++pieces >= 40) {
    stream.controller.abort()   // closes the connection
    break
  }
}

import os
import time
 
from openai import OpenAI
 
client = OpenAI(base_url="https://app.syntic.ai/v1", api_key=os.environ["SYNTIC_API_KEY"])
 
stream = client.chat.completions.create(
    model="Amara S1.2",
    stream=True,
    messages=[{"role": "user", "content": "Count slowly from 1 to 500, one number per line."}],
)
deadline = time.monotonic() + 10      # stop after 10 seconds
try:
    for chunk in stream:
        if chunk.choices and chunk.choices[0].delta.content:
            print(chunk.choices[0].delta.content, end="", flush=True)
        if time.monotonic() > deadline:
            break
finally:
    stream.close()                    # closes the HTTP connection