API Integration Documentation

PYTHON SDK

1. Python Integration (`openai`)

Install package: pip install openai

main.py

from openai import OpenAI

# Initialize client pointing to Gateway
client = OpenAI(
    base_url="https://mail.giahuynexus.com/v1",
    api_key="sk-gw-your-api-key" # Retrieve from Dashboard
)

response = client.chat.completions.create(
    model="claude-3-7-sonnet", # Or gpt-4o, deepseek-chat, gemini-2.0-flash
    messages=[
        {"role": "system", "content": "You are an expert programming assistant."},
        {"role": "user", "content": "Write an optimized prime checking function in Python."}
    ],
    stream=True
)

for chunk in response:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

TYPESCRIPT / NODE.JS

2. Node.js / TypeScript Integration

Install package: npm install openai

index.ts

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://mail.giahuynexus.com/v1",
  apiKey: "sk-gw-your-api-key",
});

async function main() {
  const stream = await client.chat.completions.create({
    model: "gpt-4o",
    messages: [{ role: "user", content: "Analyze the pros and cons of microservices architecture." }],
    stream: true,
  });

  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || "");
  }
}

main();

DEV TOOLS

3. Connect with Cursor IDE, Claude Code, Cline

In your IDE or extension settings (Settings → Models / OpenAI API):

Base URL: https://mail.giahuynexus.com/v1
API Key: Paste the API Key created in your Dashboard.
Model Names: Specify models you want to use, such as claude-3-7-sonnet, gpt-4o, deepseek-chat.

ANTHROPIC NATIVE

4. Claude Code CLI & Anthropic SDK

Use the official claude CLI tool directly by setting two environment variables:

Terminal / Bash / Zsh

export ANTHROPIC_BASE_URL="https://mail.giahuynexus.com/v1"
export ANTHROPIC_API_KEY="sk-gw-your-api-key"

# Launch Claude Code CLI
claude

EMBEDDINGS & RAG

5. Generate Vector Embeddings (/v1/embeddings)

Generate embeddings for LangChain, LlamaIndex, or Vector Databases (Chroma, Pinecone, Qdrant):

curl command

curl https://mail.giahuynexus.com/v1/embeddings \
  -H "Authorization: Bearer sk-gw-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "Machine learning and artificial intelligence are revolutionizing modern software engineering."
  }'

Technical Documentation & Integration

1. Python Integration (`openai`)

2. Node.js / TypeScript Integration

3. Connect with Cursor IDE, Claude Code, Cline

4. Claude Code CLI & Anthropic SDK

5. Generate Vector Embeddings (/v1/embeddings)