Documentation

Developer Resources

Everything you need to build with STP Networks. APIs, SDKs, tutorials, and guides to get you started.

Quick Start

Get up and running with STP Networks in minutes

  • Authentication
  • Your First API Call
  • Deploy Your First Model
  • Basic Examples

API Reference

Complete API documentation with examples

  • REST API
  • GraphQL API
  • WebSocket API
  • Rate Limits

SDKs & Libraries

Official SDKs for popular programming languages

  • Python SDK
  • Node.js SDK
  • Go SDK
  • Java SDK

Infrastructure

Deploy and manage your AI infrastructure

  • GPU Instances
  • Model Deployment
  • Scaling & Load Balancing
  • Monitoring & Logging

Security & Compliance

Security best practices and compliance guides

  • Authentication
  • Data Encryption
  • POPIA Compliance
  • Security Audit

Tutorials

Step-by-step tutorials for common use cases

  • Building a Chatbot
  • Fine-tuning Models
  • Vector Search
  • Real-time Inference

Code Examples

Get started quickly with these code examples

Deploy a Model

curl
curl -X POST https://api.stpnetworks.co.za/v1/models/deploy \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-llama-model",
    "model_id": "llama-2-7b",
    "instance_type": "gpu.large",
    "replicas": 2,
    "environment": {
      "MAX_TOKENS": "2048",
      "TEMPERATURE": "0.7"
    }
  }'

Make a Prediction

Node.js
const { STPClient } = require('@stpnetworks/sdk');

const client = new STPClient({
  apiKey: process.env.STP_API_KEY,
  region: 'africa-south'
});

async function predict() {
  const response = await client.predict({
    model: 'gpt-4',
    prompt: 'Explain quantum computing in simple terms',
    max_tokens: 150,
    temperature: 0.7
  });
  
  console.log(response.choices[0].text);
}

predict();

Fine-tune a Model

Python
from stpnetworks import STPClient

client = STPClient(api_key="your-api-key")

# Upload training data
training_data = client.data.upload(
    file_path="./training_data.jsonl",
    format="jsonl"
)

# Start fine-tuning
job = client.fine_tuning.create(
    model="llama-2-7b",
    training_data=training_data.id,
    hyperparameters={
        "learning_rate": 2e-5,
        "batch_size": 4,
        "epochs": 3
    }
)

# Monitor progress
print(f"Fine-tuning job started: {job.id}")
print(f"Status: {job.status}")

Need Help Getting Started?

Our developer support team is here to help you succeed. Get personalized assistance with integration, best practices, and optimization.

24/7 developer support
Integration assistance
Performance optimization
Best practices guidance

Get Developer Support

Join our developer community and get help from our team and other developers.