# Stream‑Mode AI Agent

A lightweight LangChain agent that streams its output token by token using the `agent.stream()` API.
The project demonstrates how to replace a single `.invoke()` call with streaming so that responses appear in real time.

---

## 📖 Description

- **Stack**:  
  - `langchain` – core framework for building agents.  
  - `langchain_ollama` – Ollama wrapper for local LLM inference.  
  - `@tool` decorator – simple tool definition.  
  - `rich.print` – pretty console output.

- **Goal**:  
  Replace the blocking `.invoke()` call with a streaming version so that the agent’s answer is printed as it is generated, improving user experience for long responses or multiple tool calls.

---

## ⚙️ Prerequisites

| Item | Version |
|------|---------|
| Python | ≥3.10 |
| Ollama | Installed locally (see [Ollama docs](https://ollama.com)) |
| LLM model | Any Ollama‑compatible model (e.g., `llama2`, `mistral`) |

> **Tip**: Ensure the chosen model is already pulled to your local Ollama instance:
> ```bash
> ollama pull llama2
> ```

---

## 🚀 Installation

```bash
# 1. Clone the repo
git clone https://github.com/your-username/stream-ai-agent.git
cd stream-ai-agent

# 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 --upgrade pip
pip install langchain langchain_ollama rich
```

---

## 🏃‍♂️ Running the Agent

```bash
python solution.py
```

The script will:

1. Connect to your local Ollama instance.
2. Create a simple agent with one custom tool (`@tool`).
3. Prompt the user for a question.
4. Stream the answer directly to the console.

---

## 📋 Example Interaction

```
$ python solution.py
Enter your question: What is the capital of France?

Answer:
The capital of France is Paris. It is known for its rich history, culture, and iconic landmarks such as the Eiffel Tower, Louvre Museum, and Notre-Dame Cathedral.
```

Notice how each token appears immediately after it is generated, rather than waiting for the entire response.

---

## 🔧 Customization

- **Change LLM**: Edit `model_name` in `solution.py`.
- **Add Tools**: Decorate new functions with `@tool` and include them when creating the agent.
- **Adjust Prompt**: Modify the initial prompt or add system messages as needed.

---

## 📄 License

MIT © 2026

---