Getting Started with Hyperstack Gen AI Platform

Get up to speed with our UI in one minute:

Visit our platform at https://genai.hyperstack.cloud to access our intuitive user interface. Our UI provides a comprehensive suite of tools that make working with AI models effortless:

• Interactive Playground: Test and experiment with different models in real-time
• Dataset Management: Upload, view, and manage your training data with ease
• Model Fine-tuning: Fine-tune models through a simple point-and-click interface
• Usage Analytics: Track your API usage and model performance

No coding required, our UI makes enterprise AI accessible to everyone on your team!

Get up to speed with our API in one minute.

Hyperstack Gen AI Platform is designed to streamline the process of fine-tuning and deploying AI models. This step-by-step tutorial will guide users through getting started with Hyperstack Gen AI Platform, enabling users to transition from using OpenAI's API to a self-hosted, privacy-preserving model in just a few simple steps! By transitioning to a self-hosted model, Gen AI Platform ensures user's data remains private and secure, complying with data protection regulations and safeguarding sensitive information.

1. Create API key

First, a user must create an api key.

Once a user has created an API key, they can set their account's API key to an environment variable named API_KEY:

export API_KEY=xxxxx

2. Make your first API request

With your API key, you can make requests to the Hyperstack Gen AI Platform API. Here's an example of how to make a chat completion request:

curl -X POST "https://api.genai.hyperstack.cloud/api/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d '{
	"model": "mistralai/mistral-7b-instruct-v0.3",
	"messages": [
		{"role": "user", "content": "Hi"}
	],
	"stream": true
}'

Or using OpenAI Python SDK:

# inference_openai_example.py
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("API_KEY"),
    base_url="https://api.genai.hyperstack.cloud/api/v1"
)

response = client.chat.completions.create(
    model="mistralai/mistral-7b-instruct-v0.3",
    messages=[
        {"role": "user", "content": "Hi"}
    ],
    stream=False,
)

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

3. Next Steps

• Users can go to the Logs & Datasets page to create a dataset.
• Users can go to the Fine-tune page to view their models.
• Users can their newly trained model on the Deploy page.
• Users can interact with their models in the Playground.