AdvancedAI & Machine LearningPython · JavaScript

Run this module

cd "AI Development"
python "chatbot.py"
node "chatbot.js"

View source on GitHub

---

Gemini API Chatbot

Command-line chatbots for Google's Gemini API, implemented in both Python and Node.js. This module demonstrates how to integrate a hosted large language model into a simple interactive application.

External API: This utility calls the Gemini API for chat responses. A network connection and a valid API key are required. All surrounding logic runs locally.

Files

File	Description
chatbot.py	Python CLI chatbot using the Gemini API
chatbot.js	Node.js CLI chatbot using the Gemini API
requirements.txt	Python dependencies
package.json	Node.js dependencies

Requirements

• Python: 3.9+
• Node.js: v18+
• A Gemini API key from Google AI Studio

The default model is gemini-2.5-flash, chosen for low latency and high throughput.

Setup

1. Install dependencies:

   pip install -r requirements.txt   # Python
   npm install                       # Node.js
   

2. Provide your API key via a .env file (recommended over hardcoding):

   GEMINI_API_KEY=your_api_key_here
   

3. Python — load it at startup:

   from dotenv import load_dotenv
   load_dotenv()
   # access with os.getenv("GEMINI_API_KEY")
   

4. Node.js — load it at startup:

   import 'dotenv/config';
   // access with process.env.GEMINI_API_KEY
   

Usage

python chatbot.py   # Python
node chatbot.js     # Node.js

Type a message and press Enter to chat. Type exit to quit.

Security

Never commit or share your API key. Always load credentials from environment variables or a .env file, and keep that file out of version control.

References

• Gemini API Quickstart (Python)
• Gemini API Rate Limits

License

MIT

---

Continue in AI & Machine Learning

• Learning Platform

  An all-in-one learning hub that delivers progressive Python lessons through both a guided CLI and a hostable Flask web interface. Lessons combine narrative walkthroughs, executable code examples, mini quizzes, and follow-up practice ideas geared toward aspiring quantitative developers.

• Machine Learning - Cross Validation

  A model scored on the data it was trained on is a student grading their own

• Machine Learning - Feature Engineering

  The dirty secret of quant machine learning: the model is rarely the bottleneck.

• Machine Learning - Gradient Descent

  Gradient descent is the engine inside almost every model that learns. The idea

• Machine Learning - K Nearest Neighbors

  Most models squeeze a training set down into a handful of parameters and then

• Machine Learning - K-Means Clustering

  Given a few hundred stocks and their return characteristics, which ones behave

Browse all modules Learning paths