Request Logs

Record production data to train and improve your models’ performance.

Request logs are a powerful tool to understand your data. Even better, you can import recorded logs directly into your training datasets, making it simple to train on real-world data collected in production.

We recommend gathering request logs for both base and fine-tuned models. Fryday provides several flexible options for recording your requests.

Proxy

Fryday offers a /chat/completions endpoint that is fully compatible with OpenAI, allowing you to use features like tool calls seamlessly.

Integrating the Proxy and Logging Requests Here’s how to get started:

1. Add an OpenAI key to your project in the project settings page.

2. Set the authorization token in your request to be your Fryday API key.

3. Set the destination URL of your request to be https://api.fryday.ai/v1/chat/completions or if you're using the OpenAI SDK, set the base URL as https://api.fryday.ai/v1

4. (Optional) Add a Prompt ID: Include the prompt ID using the X-Prompt-ID header to help track and identify specific prompts. Check the example on how to do this.

Example

JavaScript

import OpenAI from "openai";

// Initialize OpenAI client with API key
const openai = new OpenAI({
    apiKey: process.env.FRYDAY_API_KEY, // Replace with your actual API key
    baseURL: "https://api.fryday.ai/v1", // Fryday's base URL
});

async function createChatCompletion() {
    try {
        const chatCompletion = await openai.chat.completions.create({
            messages: [
                { role: "system", content: "You are an assistant that helps users answer simple questions." },
                { role: "user", content: "What is the capital of France?" }
            ],
            model: "gpt-4o-mini",  // Replace with your model name
            headers: {
                "X-Prompt-ID": "your_prompt_id_here"
            },
        });

        console.log(chatCompletion);
    } catch (error) {
        console.error("Error creating chat completion:", error);
    }
}

createChatCompletion();

Python

from openai import OpenAI

# Initialize client with base URL and API key
client = OpenAI(
    base_url="https://api.fryday.ai/v1",
    api_key="your_project_api_key_here",
)

# Create a chat completion
chat_completion = client.chat.completions.create(
    messages=[
        {
            "role": "system",
            "content": "You are an assistant that helps users choose between options."
        },
        {
            "role": "user",
            "content": "What is the correct option for this task?"
        }
    ],
    model="gpt-4o",  # Replace with your model name
    extra_headers={"X-Prompt-ID": "your_prompt_id_here"},
)

print(chat_completion)

Let me know if this works for you!