openaictl

openaictl: Interactive OpenAI Chatbot CLI

openaictl is an interactive command-line chatbot built with Python. It communicates with OpenAI's GPT model using the new client-based interface (openai-python>=1.0.0). The chatbot supports conversational context, enabling dynamic and intelligent interactions.

---

Features

• Interactive Chat: Engage in real-time conversations with OpenAI's GPT model.
• Context-Aware: Maintains conversation history for context-based responses.
• Customizable: Configure model, token limits, and API key via the .env file.
• Secure API Key Handling: Loads OpenAI API key and other configurations from the .env file.
• Dockerized: Fully containerized for ease of use across different systems and architectures.
• Multiple Architecture Support: Runs on linux/armv7, linux/amd64, linux/arm64

---

Prerequisites

1. Python: Ensure Python 3.9 or newer is installed if not using Docker.
2. Docker: Install Docker for containerized execution.
3. OpenAI API Key: Obtain an API key from OpenAI.

---

Installation

Clone the Repository

git clone <repository-url>
cd <repository-directory>

Python Setup (Optional)

If running locally (not with Docker):

1. Create a virtual environment:

   python3 -m venv venv
   source venv/bin/activate  # For Linux/Mac
   venv\Scripts\activate     # For Windows

2. Install dependencies:

   pip install -r requirements.txt

---

Environment Configuration

1. Create a .env File: Add the following configuration to a .env file in the project directory:

   OPENAI_API_KEY=your_openai_api_key_here
   MODEL=gpt-3.5-turbo
   MAX_TOKENS=150

   • OPENAI_API_KEY: Your OpenAI API key.
   • MODEL: The OpenAI model to use (e.g., gpt-4, gpt-3.5-turbo).
   • MAX_TOKENS: Maximum number of tokens per response.

---

Usage

Docker

1. Build the Docker Image:

   docker build -t openaictl .

   For Multiple Architecture build on your Machine:

   docker buildx build --platform linux/amd64,linux/arm64,linux/arm/v7 -t <your container registry>/openaictl:<tag> --push .

   Note: Multiarchitecture builds will not be visible by using docker images command. Your registry will show the different images.

2. Run the Chatbot:

   docker run --rm -it --env-file .env openaictl

Local Python Execution

Run the chatbot interactively:

python cli.py

---

Example Interaction

Interactive Chatbot with OpenAI (Client-Based API)
Type 'exit' to quit.

You: Hello
AI: Hi there! How can I assist you today?

You: What's the capital of France?
AI: The capital of France is Paris.

You: exit
Goodbye!

---

Instructions for Building for Raspberry Pi 2 on a Mac

The Raspberry Pi 2 has an ARMv7 architecture, so you need to ensure the Docker image is compatible with that architecture. Here's how you can build and run openaictl for a Raspberry Pi 2 on a Mac (including Apple Silicon).

Steps to Build and Run

1. Enable Buildx on Docker:

   • Ensure Docker's buildx feature is enabled for multi-platform builds. You can check with:

     docker buildx version

   • If not enabled, install it using Docker's official instructions: Docker Buildx.

2. Set Up QEMU for Cross-Platform Emulation:

   • If you haven’t already, set up QEMU for multi-architecture emulation:

     docker run --rm --privileged multiarch/qemu-user-static --reset -p yes

3. Build the Docker Image for ARMv7:

   • Use buildx to target the Raspberry Pi 2 architecture (linux/arm/v7):

     docker buildx build --platform linux/arm/v7 -t openaictl:rpi2 .

4. Save the Image for Transfer (Optional):

   • If building the image on your Mac and transferring it to the Raspberry Pi 2, save the image as a tar file:

     docker save -o openaictl-rpi2.tar openaictl:rpi2

5. Transfer the Image to Raspberry Pi 2:

   • Copy the image file to the Raspberry Pi using scp or another file transfer method:

     scp openaictl-rpi2.tar pi@<RPI_IP>:/home/pi

6. Load and Run the Image on Raspberry Pi 2:

   • SSH into the Raspberry Pi:

     ssh pi@<RPI_IP>

   • Load the Docker image:

     docker load < openaictl-rpi2.tar

   • Run the chatbot:

     docker run --rm -it --env-file .env openaictl:rpi2

7. Direct Deployment to Raspberry Pi (Alternative):

   • If the Raspberry Pi is network-accessible, you can build and push directly to it:

     docker buildx build --platform linux/arm/v7 -t openaictl:rpi2 --push .

---

Key Files

• cli.py: Main script for the chatbot.
• Dockerfile: Configuration for building the Docker image.
• requirements.txt: Python dependencies.
• .env: Configuration file for the API key, model, and other parameters.

---

Dependencies

• openai >=1.0.0
• python-dotenv

---

Troubleshooting

Missing API Key

Ensure the .env file is properly configured with the OPENAI_API_KEY.

Other Errors

Check your .env file for incorrect values or run the script with debug logging to identify the issue.

---

License

This project is licensed under the MIT License. See the LICENSE file for details.

---

Acknowledgments

• OpenAI Python Library
• Docker