rsazure-openai-toolkit 0.2.0

Toolkit for fast and flexible integration with Azure OpenAI

---

rsazure-openai-toolkit

A lightweight, independent toolkit (with CLI support) to simplify and accelerate integration with Azure OpenAI.

---

Installation

From PyPI:

pip install rsazure-openai-toolkit

From GitHub:

pip install git+https://github.com/renan-siqueira/rsazure-openai-toolkit

---

Usage

from rsazure_openai_toolkit import call_azure_openai_handler

response = call_azure_openai_handler(
    api_key="your-api-key",
    azure_endpoint="https://your-resource.openai.azure.com/",
    api_version="2023-12-01-preview",
    deployment_name="gpt-35-turbo",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Summarize what artificial intelligence is."}
    ]
)

print(response)

---

Environment Configuration

To simplify local development and testing, this toolkit supports loading environment variables from a .env file.

Create a .env file in your project root (or copy the provided .env.example) and add your Azure OpenAI credentials:

AZURE_OPENAI_API_KEY=your-api-key
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/
AZURE_OPENAI_API_VERSION=2023-12-01-preview
AZURE_DEPLOYMENT_NAME=your-deployment-name

In your script, load the environment variables before calling the handler:

from dotenv import load_dotenv
import os

load_dotenv()  # defaults to loading from .env in the current directory

from rsazure_openai_toolkit import call_azure_openai_handler

response = call_azure_openai_handler(
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),
    azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
    api_version=os.getenv("AZURE_OPENAI_API_VERSION"),
    deployment_name=os.getenv("AZURE_DEPLOYMENT_NAME"),
    messages=[...]
)

---

🖥️ CLI Usage (rschat)

After installing the package, you can interact with Azure OpenAI directly from your terminal using:

rschat "What can you do for me?"

Make sure you have a valid .env file with your Azure credentials configured:

AZURE_OPENAI_API_KEY=your-api-key
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/
AZURE_OPENAI_API_VERSION=2023-12-01-preview
AZURE_DEPLOYMENT_NAME=your-deployment-name

You can also ask in Portuguese (or any supported language):

rschat "Resuma o que é inteligência artificial"

If any required variable is missing, the CLI will exit with a clear error message.

---

Features

• Modular and easy to extend
• Retry mechanism with exponential backoff
• Accepts OpenAI-compatible parameters
• Ready for production use
• Comes with an intuitive CLI (rschat) for direct terminal interaction

---

Requirements

• Python 3.9+
• Azure OpenAI resource and deployment

---

License

This project is open-sourced and available to everyone under the MIT License.

---

🚨 Possible Issues

• Invalid API Key or Endpoint
  Ensure your AZURE_OPENAI_API_KEY and AZURE_OPENAI_ENDPOINT are correctly set in your .env file.

• Deployment Not Found
  Check that your deployment_name matches exactly the name defined in your Azure OpenAI resource.

• Timeouts or 5xx Errors
  The toolkit includes automatic retries with exponential backoff via tenacity. If errors persist, verify network access or Azure service status.

• Missing Environment Variables
  Always ensure load_dotenv() is called before accessing os.getenv(...), especially when testing locally.

---

📝 Changelog

Check the Releases page for updates and version history.

See the full list of changes in CHANGELOG.md

---

🛡️ Security

If you discover any security issues, please report them privately via email: [e-mail].

---

🤝 Contributing

Contributions are welcome! Feel free to open issues or pull requests.

To contribute:

1. Fork the repo
2. Create a feature branch (git checkout -b feature/my-feature)
3. Commit your changes
4. Open a PR

Please follow PEP8 and ensure your code passes existing tests.

---

🧠 Design Principles

• Simplicity over complexity
• Focus on production-readiness
• Explicit configuration
• Easy to extend and maintain

---

👨‍💻 About the Author

Hi, I'm Renan Siqueira Antonio — a technical leader in Artificial Intelligence with hands-on experience in delivering real-world AI solutions across different industries.

Over the years, I've had the opportunity to collaborate with incredible teams and contribute to initiatives recognized by companies.

This project was born from a personal need: to create a clean, reusable, and production-ready way to interact with Azure OpenAI. I'm sharing it with the hope that it helps others move faster and build better.

---

📬 Contact

Feel free to reach out via:

• GitHub: github.com/renan-siqueira
• Email: [e-mail]
• Linkedin: linkedin.com/in/renan-siqueira-antonio

Contributions, suggestions, and bug reports are welcome!