Skip to main content

OpenAI SDK Integration

The OpenAI SDK is the most straightforward way to integrate Vexrail. You configure the SDK to point at the Vexrail API and pass your authentication keys.

JavaScript / TypeScript​

Installation​

npm install openai

Setup​

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.vexrail.com/v1",
  apiKey: "unused", // Required by SDK but not used for auth
  defaultHeaders: {
    "x-publishable-key": process.env.VEXRAIL_PUBLISHABLE_KEY,
    "x-secret-key": process.env.VEXRAIL_SECRET_KEY,
    "x-conversation-id": "your-conversation-id",
  },
});

Chat Completion​

const response = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "What tools can help me with project management?" },
  ],
});

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

Streaming​

const stream = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [
    { role: "user", content: "Recommend a good design tool." },
  ],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

Python​

Installation​

pip install openai

Setup​

from openai import OpenAI

client = OpenAI(
    base_url="https://api.vexrail.com/v1",
    api_key="unused",  # Required by SDK but not used for auth
    default_headers={
        "x-publishable-key": "pk_live_your_publishable_key",
        "x-secret-key": "sk_live_your_secret_key",
        "x-conversation-id": "your-conversation-id",
    },
)

Chat Completion​

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What tools can help me with project management?"},
    ],
)

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

Streaming​

stream = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "user", "content": "Recommend a good design tool."},
    ],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Environment Variables​

We recommend storing your keys in environment variables:

VEXRAIL_PUBLISHABLE_KEY=pk_live_your_publishable_key
VEXRAIL_SECRET_KEY=sk_live_your_secret_key

Then reference them in your code instead of hardcoding the values.

Next Steps​