Documentation | Venkat AI

API Quick Start

Welcome to the Venkat AI API! This guide will help you make your first inference request in just a few minutes. We'll use Python for this example, but we offer SDKs for various languages.

1. Installation

First, install the official Venkat AI Python client library using pip:

pip install venkat-ai-client

2. Get Your API Key

You'll need an API key to authenticate your requests. You can find your API key in your account dashboard after signing up.

3. Make Your First Request

Now, let's use the client library to make a prediction using the Venkat AI Spark model. Replace "your_api_key" with your actual API key.

from venkat_ai import Client
import os

# It's recommended to use environment variables for API keys
# api_key = os.environ.get("VENKAT_API_KEY")
api_key = "your_api_key" # Replace with your key for testing

if not api_key:
    raise ValueError("API key not found. Set the VENKAT_API_KEY environment variable.")

# Initialize the client
client = Client(api_key=api_key)

try:
    # Define the input data for the model
    input_data = {
        "prompt": "Translate the following English text to French: 'Hello, world!'",
        "max_tokens": 50
    }

    # Make the prediction request
    response = client.predict(
        model="venkat-spark", # Specify the model to use
        input_data=input_data
    )

    # Print the result
    print("Prediction Result:")
    print(response)

except Exception as e:
    print(f"An error occurred: {e}")

4. Understanding the Response

The response object will typically contain the model's output, along with metadata like request IDs and usage information. The exact structure depends on the model used.

{
  "id": "pred_abc123xyz",
  "model": "venkat-spark",
  "output": {
    "translation": "Bonjour, le monde!"
  },
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 4,
    "total_tokens": 19
  }
}

Next Steps

Congratulations! You've made your first API request. Here are some next steps: