OpenAI to Azure OpenAI Converter CLI

A command-line tool that converts OpenAI code (curl, Python, JavaScript/TypeScript, LangChain) to Azure OpenAI compatible code.

Installation

# Install globally from npm
npm install -g openai-to-azure-openai-cli

# Or use directly with npx
npx openai-to-azure-openai-cli --help

From Source

# Clone the repository
git clone https://github.com/davidhou17/openai-to-azure-openai-cli.git
cd openai-to-azure-openai-cli

# Install dependencies
npm install

# Build the project
npm run build

# Link globally (optional)
npm link

Usage

Basic Usage

# From stdin
echo 'your code here' | openai-to-azure

# From file
openai-to-azure -f input.py

# From string argument
openai-to-azure 'curl https://api.openai.com/v1/chat/completions ...'

Options

Usage: openai-to-azure [options] [input]

Arguments:
  input                    Input code string or file path

Options:
  -V, --version            output the version number
  -f, --file <path>        Read input from a file
  -l, --language <lang>    Specify the language (curl, python, javascript, typescript, langchain)
  --no-comments            Disable adding environment variable comments to output
  -o, --output <path>      Write output to a file (default: stdout)
  -q, --quiet              Suppress warnings and info messages
  -h, --help               display help for command

Commands:
  detect [options] [input] Detect the language of the input code

Required Environment Variables

After conversion, your Azure OpenAI code will use these environment variables:

Variable	Description
AZURE_OPENAI_ENDPOINT	Your Azure OpenAI endpoint (e.g., https://your-resource.openai.azure.com)
AZURE_OPENAI_API_KEY	Your Azure OpenAI API key
OPENAI_API_VERSION	API version (e.g., 2024-02-15-preview)
AZURE_OPENAI_DEPLOYMENT	Your deployment name

Examples

cURL Conversion

Input:

curl https://api.openai.com/v1/chat/completions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4", "messages": [{"role": "user", "content": "Hello!"}]}'

Output:

curl ${AZURE_OPENAI_ENDPOINT}/openai/deployments/${AZURE_OPENAI_DEPLOYMENT}/chat/completions?api-version=${OPENAI_API_VERSION:-2024-02-15-preview} \
  -H "api-key: $AZURE_OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4", "messages": [{"role": "user", "content": "Hello!"}]}'

Python Conversion

Input:

from openai import OpenAI

client = OpenAI(api_key="sk-xxx")
response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello!"}]
)

Output:

from openai import AzureOpenAI
import os

client = AzureOpenAI(
    azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),
    api_version=os.getenv("OPENAI_API_VERSION", "2024-02-15-preview")
)
response = client.chat.completions.create(
    model=os.getenv("AZURE_OPENAI_DEPLOYMENT"),
    messages=[{"role": "user", "content": "Hello!"}]
)

JavaScript/TypeScript Conversion

Input:

import OpenAI from 'openai';

const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
const response = await client.chat.completions.create({
  model: 'gpt-4',
  messages: [{ role: 'user', content: 'Hello!' }],
});

Output:

import { AzureOpenAI } from 'openai';

const client = new AzureOpenAI({
  apiKey: process.env.AZURE_OPENAI_API_KEY,
  endpoint: process.env.AZURE_OPENAI_ENDPOINT,
  apiVersion: process.env.OPENAI_API_VERSION || '2024-02-15-preview',
});
const response = await client.chat.completions.create({
  model: process.env.AZURE_OPENAI_DEPLOYMENT,
  messages: [{ role: 'user', content: 'Hello!' }],
});

LangChain Conversion

Input:

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-4",
    temperature=0,
    max_tokens=None,
)

messages = [("system", "You are a helpful assistant."), ("human", "Hello!")]
response = llm.invoke(messages)

Output:

import os
from langchain_openai import AzureChatOpenAI

llm = AzureChatOpenAI(
    azure_deployment=os.getenv("AZURE_OPENAI_DEPLOYMENT"),
    api_version=os.getenv("OPENAI_API_VERSION", "2024-02-15-preview"),
)

messages = [("system", "You are a helpful assistant."), ("human", "Hello!")]
response = llm.invoke(messages)

Supported Conversions

OpenAI SDK

• Python: OpenAI → AzureOpenAI
• JavaScript/TypeScript: OpenAI → AzureOpenAI

LangChain

• Python: ChatOpenAI → AzureChatOpenAI

curl Endpoints

• /v1/chat/completions → Chat completions
• /v1/completions → Text completions
• /v1/embeddings → Embeddings
• /v1/images/generations → Image generation (DALL-E)
• /v1/audio/transcriptions → Audio transcription (Whisper)
• /v1/audio/translations → Audio translation (Whisper)

Development

Running Tests

# Run all tests
npm test

# Run tests in watch mode
npm run test:watch

Building

npm run build

License

MIT