---
title: Agent Workshop
emoji: 🧠
colorFrom: blue
colorTo: purple
sdk: streamlit
sdk_version: 1.51.0
app_file: app.py
pinned: false
license: mit
tags:
- langchain
- gemini
- ai-agent
- crypto
- huggingface-space
---

# 🪙 Crypto AI Agent (Gemini + LangChain)

This project is a simple **AI-powered crypto assistant** built using **Google’s Gemini model** and **LangChain**.
It can intelligently respond to prompts **and** fetch **real-time cryptocurrency prices** (like Bitcoin and Ethereum) using a live API.


## 🚀 Features

✅ **Conversational AI** — Powered by `ChatGoogleGenerativeAI` (Gemini).
✅ **Live Crypto Data** — Fetches real-time prices from the [CoinCap API](https://docs.coincap.io/).
✅ **LangChain Integration** — Uses LangChain’s latest tool architecture (`Tool`).
✅ **Simple Deployment** — Can run directly on **Hugging Face Spaces** or locally.
✅ **Extendable** — Easily add more tools, prompts, or custom logic.


## 🧠 How It Works

1. The user gives a text input (e.g., “Check the Bitcoin price”).
2. The agent detects whether it should:

   * Use a tool (like the `CryptoPriceChecker`), or
   * Use the Gemini model to generate a conversational answer.
3. The result is printed or returned as a response.


## 📂 Project Structure

```
crypto-ai-agent/
│
├── app.py                # Main application code
├── requirements.txt      # All Python dependencies
└── README.md             # Project documentation
```


## 🧩 Installation

You can run this project locally or deploy it on Hugging Face.

### Option 1: Run Locally

```bash
# Clone the repository
git clone https://github.com/yourusername/crypto-ai-agent.git
cd crypto-ai-agent

# Install dependencies
pip install -r requirements.txt
```

### Option 2: Run in Google Colab

Simply upload `app.py` to your Colab environment and run:

```python
!pip install -r requirements.txt
!python app.py
```

### Option 3: Deploy on Hugging Face Spaces

1. Create a new Space.
2. Choose **“Static / Python (Gradio)”** as your Space type.
3. Upload:

   * `app.py`
   * `requirements.txt`
   * `README.md`
4. Add your **Google API key** in the Hugging Face **Secrets tab** as:

   ```
   GOOGLE_API_KEY=your_api_key_here
   ```


## 🔧 Configuration

You’ll need a valid **Google Generative AI API key** (Gemini).
You can get one from [Google AI Studio](https://makersuite.google.com/app/apikey).

Once you have it, set it as an environment variable:

```bash
export GOOGLE_API_KEY="your_api_key_here"
```

Or, on Hugging Face, use the **“Repository Secrets”** feature.


## 🧾 Example Usage

### In Python:

```python
from app import run_agent

print(run_agent("Check Bitcoin price"))
print(run_agent("What is blockchain?"))
```

### Output:

```
💰 BTC current price: $68,245.12
Blockchain is a distributed ledger technology that allows secure and transparent record-keeping.
```


## 📦 Requirements

See [`requirements.txt`](requirements.txt):

```
langchain>=0.3.0
langchain-google-genai>=0.1.0
langchain-core>=0.3.0
requests>=2.31.0
python-dotenv>=1.0.0
```


## 🧩 Future Enhancements

* Add multiple crypto symbols (e.g., ADA, XRP, DOGE)
* Integrate trading signals or portfolio management
* Add Gradio interface for user input
* Deploy on Hugging Face Space with persistent logs

## 👨‍💻 Author

**Ali Masood**
PhD in Artificial Intelligence | Founder, Zaytrics Pvt Ltd
🚀 Building world-class AI & blockchain solutions.

---