Stream‑режим AI‑агента

This repository contains a minimal implementation of an AI agent that streams responses from OpenAI's ChatCompletion API.

Features

• Streaming – receive model output token‑by‑token instead of waiting for the full response.
• Simple API – expose a single stream_chat generator that yields text fragments.
• Example script – quick demo showing how to use the streaming agent.

Getting Started

1. Clone the repository

   git clone https://git.brojs.ru/RK-A/stream-ai-agent-task6.git
   cd stream-ai-agent-task6
   

2. Create a virtual environment (optional but recommended)

   python -m venv venv
   source venv/bin/activate   # On Windows: venv\Scripts\activate
   

3. Install dependencies

   pip install -r requirements.txt
   

4. Set your OpenAI API key

   export OPENAI_API_KEY=sk-...
   

5. Run the demo

   python main.py
   

The demo will stream a short poem about the sea.

Usage in Your Own Code

from agent_stream import stream_chat

messages = [
    {"role": "user", "content": "Tell me a joke."}
]

for token in stream_chat(messages):
    print(token, end='', flush=True)

License

MIT © 2026