# 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**
   ```bash
   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)
   ```bash
   python -m venv venv
   source venv/bin/activate   # On Windows: venv\Scripts\activate
   ```

3. **Install dependencies**
   ```bash
   pip install -r requirements.txt
   ```

4. **Set your OpenAI API key**
   ```bash
   export OPENAI_API_KEY=sk-...
   ```

5. **Run the demo**
   ```bash
   python main.py
   ```

The demo will stream a short poem about the sea.

## Usage in Your Own Code

```python
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