Text Generation

You can generate text using the Llama 3.1 8B Instruct model deployed on your Cube via an OpenAI-compatible API.

---

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://llama-eukodyne.edgescaleai-cube.com/v1/"
});

const completion = await client.chat.completions.create({
  model: "meta-llama/Llama-3.1-8B-Instruct",
  messages: [
    { role: "system", content: "You are a helpful AI assistant." },
    { role: "user",   content: "what model are you, how can you help?" }
  ],
  max_tokens: 256,
  temperature: 0.7
});

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

Python

from openai import OpenAI

client = OpenAI(
    api_key="none",
    base_url="https://llama-eukodyne.edgescaleai-cube.com/v1/"
)

completion = client.chat.completions.create(
    model="meta-llama/Llama-3.1-8B-Instruct",
    messages=[
        {"role": "system", "content": "You are a helpful AI assistant."},
        {"role": "user",   "content": "what model are you, how can you help?"}
    ],
    max_tokens=256,
    temperature=0.7
)

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

cURL

curl "https://llama-eukodyne.edgescaleai-cube.com/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
        "model": "meta-llama/Llama-3.1-8B-Instruct",
        "messages": [
          { "role": "system", "content": "You are a helpful AI assistant." },
          { "role": "user",   "content": "what model are you, how can you help?" }
        ],
        "max_tokens": 256,
        "temperature": 0.7
      }'