Voyage AI

Replace https://api.voyageai.com/ with https://llmfoundry.straive.com/voyageai/.

All Voyage AI embedding models are supported, including:

• voyage-3-large
• voyage-3
• voyage-3-lite
• voyage-code-3
• voyage-finance-2
• voyage-law-2
• voyage-code-2

Curl

curl -X POST https://llmfoundry.straive.com/voyageai/v1/embeddings \
  -H "Authorization: Bearer $LLMFOUNDRY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model": "voyage-3-lite", "input": "Alpha Beta Gamma"}'

Python requests

import os
import requests  # Or replace requests with httpx

response = requests.post(
    "https://llmfoundry.straive.com/voyageai/v1/embeddings",
    headers={"Authorization": f"Bearer {os.environ['LLMFOUNDRY_TOKEN']}"},
    json={"model": "voyage-3-lite", "input": "Alpha Beta Gamma"}
)
print(response.json())

JavaScript

const token = process.env.LLMFOUNDRY_TOKEN;
const response = await fetch("https://llmfoundry.straive.com/voyageai/v1/embeddings", {
  method: "POST",
  headers: { "Content-Type": "application/json", Authorization: `Bearer ${token}` },
  // If the user is already logged into LLM Foundry, use `credentials: "include"` to send **THEIR** API token instead of the `Authorization` header.
  credentials: "include",
  body: JSON.stringify({ model: "voyage-3-lite", input: "Alpha Beta Gamma" }),
});
console.log(await response.json());