Добавлен README.md
This commit is contained in:
@@ -1,96 +1,100 @@
|
|||||||
# Stream‑Mode AI Agent
|
# Stream‑Mode AI Agent
|
||||||
|
|
||||||
A lightweight LangChain agent that prints its output **as it is generated** using the `.stream()` API.
|
A lightweight LangChain agent that streams its responses token by token using the `rich` library for pretty console output.
|
||||||
The project demonstrates how to replace a single `.invoke()` call with streaming so that users see partial responses in real time.
|
|
||||||
|
|
||||||
> **Why stream?**
|
> **Why stream?**
|
||||||
> When an LLM produces long answers or calls multiple tools, waiting for the whole result can feel like a freeze. Streaming gives instant feedback and improves UX.
|
> When an LLM generates a long answer or calls multiple tools, waiting until the entire response is ready can feel like a freeze. Streaming lets you see the answer as it is produced, improving interactivity and user experience.
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## 📦 Project Structure
|
## 📦 Features
|
||||||
|
|
||||||
```
|
- Uses **LangChain** for agent orchestration
|
||||||
.
|
- Powered by **OpenAI GPT‑4o-mini** (or any OpenAI model)
|
||||||
├── agent.py # Agent definition with streaming support
|
- Real‑time streaming via `llm.stream(...)`
|
||||||
├── client.py # Simple CLI to interact with the agent
|
- Pretty console output with **rich**
|
||||||
└── README.md
|
- Simple, single‑file implementation (`solution.py`)
|
||||||
```
|
|
||||||
|
|
||||||
- **agent.py** – creates an agent that uses a single tool (`get_price`) and streams its output.
|
|
||||||
- **client.py** – runs the agent in a loop, reading user queries from stdin.
|
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## ⚙️ Prerequisites
|
## ⚙️ Prerequisites
|
||||||
|
|
||||||
| Item | Version |
|
| Item | Minimum Version |
|
||||||
|------|---------|
|
|------|-----------------|
|
||||||
| Python | 3.10+ |
|
| Python | 3.10+ |
|
||||||
| pip | latest |
|
| pip | – |
|
||||||
| LangChain | `>=0.2.0` |
|
| OpenAI API key | Set as environment variable `OPENAI_API_KEY` |
|
||||||
| Rich | `>=13.0` |
|
|
||||||
|
|
||||||
> **Tip:** Use a virtual environment to keep dependencies isolated.
|
> **Tip:** Create a virtual environment before installing dependencies.
|
||||||
|
|
||||||
|
```bash
|
||||||
|
python -m venv .venv
|
||||||
|
source .venv/bin/activate # On Windows: .\.venv\Scripts\activate
|
||||||
|
```
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## 🚀 Installation
|
## 📥 Installation
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
# Clone the repo (or copy the files)
|
# Clone the repo (or copy solution.py into your project)
|
||||||
git clone https://github.com/your-username/stream-agent.git
|
git clone https://github.com/<your-username>/stream-ai-agent.git
|
||||||
cd stream-agent
|
cd stream-ai-agent
|
||||||
|
|
||||||
# Create and activate a venv (optional but recommended)
|
|
||||||
python -m venv .venv
|
|
||||||
source .venv/bin/activate # Windows: .venv\Scripts\activate
|
|
||||||
|
|
||||||
# Install dependencies
|
# Install dependencies
|
||||||
pip install --upgrade pip
|
pip install -r requirements.txt
|
||||||
pip install langchain rich
|
|
||||||
```
|
```
|
||||||
|
|
||||||
> If you plan to use an OpenAI model, set the API key:
|
`requirements.txt`:
|
||||||
> ```bash
|
|
||||||
> export OPENAI_API_KEY="sk-..."
|
```text
|
||||||
> ```
|
langchain==0.2.*
|
||||||
|
openai==1.*
|
||||||
|
rich==13.*
|
||||||
|
```
|
||||||
|
|
||||||
|
> Adjust the version numbers if you prefer newer releases.
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## 📖 Usage
|
## 🚀 Running the Agent
|
||||||
|
|
||||||
Run the client script and type your questions. The agent will stream its answer token‑by‑token.
|
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
python client.py
|
export OPENAI_API_KEY="sk-..." # On Windows: set OPENAI_API_KEY=sk-...
|
||||||
|
python solution.py
|
||||||
```
|
```
|
||||||
|
|
||||||
Example session:
|
The script will prompt you for a question. Type your query and press **Enter**.
|
||||||
|
You’ll see the answer appear token by token in real time.
|
||||||
```
|
|
||||||
$ python client.py
|
|
||||||
Enter your query (Ctrl+C to exit):
|
|
||||||
> What is the price of Bitcoin today?
|
|
||||||
|
|
||||||
Agent: Checking price...
|
|
||||||
Agent: Current BTC price is $42,300.00
|
|
||||||
```
|
|
||||||
|
|
||||||
The output appears progressively as the LLM generates it.
|
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## 🛠️ Customization
|
## 📄 Example
|
||||||
|
|
||||||
- **Add more tools** – decorate a function with `@tool` and pass it to `create_agent`.
|
```text
|
||||||
- **Change model** – modify the `model_name` argument in `agent.py`.
|
$ python solution.py
|
||||||
- **Adjust streaming format** – tweak the `stream()` call or use Rich’s live rendering for fancy UI.
|
🤖 What is the capital of France?
|
||||||
|
🇫🇷 Paris
|
||||||
|
```
|
||||||
|
|
||||||
|
The agent will stream each word (or token) as it arrives, giving a smooth typing‑like effect.
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## 📄 License
|
## 🔧 Customization
|
||||||
|
|
||||||
MIT © 2026
|
- **Change model** – edit `model="gpt-4o-mi"` in `solution.py`.
|
||||||
|
- **Add tools** – decorate functions with `@tool` and include them in the agent.
|
||||||
|
- **Adjust temperature** – modify `temperature=0` to a higher value for more creativity.
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
|
## 📚 Further Reading
|
||||||
|
|
||||||
|
- [LangChain Docs](https://langchain.com/docs/)
|
||||||
|
- [OpenAI API Reference](https://platform.openai.com/docs/api-reference)
|
||||||
|
- [Rich Library](https://rich.readthedocs.io/en/stable/)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
Happy streaming! 🚀
|
||||||
Reference in New Issue
Block a user