Build the Future of Autonomous AI with ASDEX

Technical Deep Dive

For developers ready to dive into the specifics of integrating with ASDEX, here's a closer look at our API, data structures, and how to get started with code.

Example API Request (Python)

Here's a quick example of how an AI agent might fetch a list of synthetic datasets from the ASDEX API using Python. Your API key will authenticate the request.

import requests
import json

API_BASE_URL = "https://api.asdex.io/v1"
YOUR_API_KEY = "YOUR_API_KEY_HERE" # Replace with your actual API Key

headers = {
    "X-API-Key": YOUR_API_KEY,
    "Content-Type": "application/json"
}

# Endpoint for listing datasets
endpoint = "/datasets"
params = {
    "dataType": "tabular",
    "query": "financial fraud",
    "limit": 5
}

try:
    response = requests.get(f"{API_BASE_URL}{endpoint}", headers=headers, params=params)
    response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx)

    datasets = response.json()
    print("Successfully fetched datasets:")
    for dataset in datasets.get("datasets", []):
        print(f"  - {dataset.get('name')} (Price: ${dataset.get('price'):.2f})")

except requests.exceptions.HTTPError as err:
    print(f"HTTP error occurred: {err}")
    if err.response:
        print(f"Response body: {err.response.text}")
except requests.exceptions.ConnectionError as err:
    print(f"Connection error occurred: {err}")
except requests.exceptions.Timeout as err:
    print(f"Timeout error occurred: {err}")
except requests.exceptions.RequestException as err:
    print(f"An unexpected error occurred: {err}")
except json.JSONDecodeError:
    print(f"Failed to decode JSON from response: {response.text}")
                    

Find more API details in our API Documentation.

Dataset Formats and Schema

ASDEX supports a variety of synthetic dataset formats, with clear schema definitions for structured data to ensure seamless integration into your AI models. Understanding the data structure is key to effective utilization.

• Tabular Data: Typically provided in CSV or JSON formats, accompanied by a detailed schema (field names, data types, descriptions).
• Image Data: Common formats include PNG, JPG. Metadata specifies image dimensions, content (e.g., object categories), and generation details.
• Text Data: Provided in plain text or structured JSON, with metadata on content type (e.g., reviews, dialogues) and language.
• Time-Series Data: Often in CSV or JSON, with clear timestamps and feature definitions.

Learn more about specific formats and schema standards in the Documentation.

Code Examples and Libraries

We provide a growing repository of code examples and plan to develop SDKs (Software Development Kits) in popular languages to simplify your integration process. These resources will demonstrate common operations like dataset querying, purchase, and agent configuration.

• Python SDK (Planned)
• JavaScript Examples
• Open-Sourced Emergence Engine Code (GitHub)

Integration Guides

Connect ASDEX data and agent capabilities with the AI development tools and frameworks you already use:

• Integrating with TensorFlow/Keras
• Integrating with PyTorch
• Connecting with scikit-learn
• Using ASDEX data in Cloud AI Platforms (AWS Sagemaker, Google AI Platform)