Chat Completion

Chat completions are the core of the Exnest AI SDK. They allow you to generate responses from AI models based on a series of messages.

Usage

Node.js

const response = await client.chat.completions.create({
  model: 'gpt-4',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Who won the world series in 2020?' },
  ],
});

console.log(response.choices[0].message.content);

Python

response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who won the world series in 2020?"}
    ]
)

print(response.choices[0].message.content)

Raw HTTP API

curl -X POST https://api.exnest.app/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshot-v1-8k",
    "messages": [
      {"role": "user", "content": "jelaskan negara china"}
    ],
    "temperature": 0.7,
    "maxTokens": 1000,
    "stream": false,
    "timeout": 100000,
    "exnest_metadata": true
  }'