Metadata-Version: 2.4
Name: piptalk-cli
Version: 1.0.1
Summary: A command-line interface for interacting with Google's Gemini AI models
Home-page: https://github.com/YOUR_USERNAME/gemini-cli
Author: Kartikeya Ranjan
Author-email: Kartikeya Ranjan <kartikeyaranjan01@gmail.com>
License: ISC
Project-URL: Homepage, https://github.com/YOUR_USERNAME/gemini-cli
Project-URL: Repository, https://github.com/YOUR_USERNAME/gemini-cli
Keywords: gemini,ai,cli,google,generative-ai,chat,command-line
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: ISC License (ISCL)
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: google-generativeai>=0.3.0
Requires-Dist: colorama>=0.4.6
Requires-Dist: python-dotenv>=1.0.0
Dynamic: author
Dynamic: home-page
Dynamic: license-file
Dynamic: requires-python

# Piptalk CLI (Python)

A command-line interface for interacting with Google's Gemini AI models. Chat with Gemini AI directly from your terminal!

This is the Python version of the Gemini CLI tool. For the Node.js version, see [@karitkeyaranjan/talk-cli](https://www.npmjs.com/package/@karitkeyaranjan/talk-cli).

## Installation

### From PyPI (when published):

```bash
pip install piptalk-cli
```

### From source:

```bash
git clone <repository-url>
cd gemini-cli-python
pip install -e .
```

## Setup

1. Get your Gemini API key from [Google AI Studio](https://makersuite.google.com/app/apikey)
2. Set it as an environment variable:

```bash
export GEMINI_API_KEY="your-api-key-here"
```

Or create a `.env` file in your home directory:

```
GEMINI_API_KEY=your-api-key-here
```

**Note:** The tool comes with a default API key, but it's recommended to use your own.

## Usage

### Interactive Mode

Simply run the command without any arguments:

```bash
piptalk
```

### Command Mode

Provide a prompt directly:

```bash
piptalk "Explain quantum computing in simple terms"
```

### Select a Model

Use the `--model` or `-m` flag to choose a specific model:

```bash
piptalk --model flash "Hello world"
piptalk -m 2.0-flash "Quick question"
piptalk -m 2.5-pro "Explain machine learning"
```

### Available Models

- `flash` - ⚡ Gemini 2.5 Flash (default)
- `2.0-flash` - ⚡ Gemini 2.0 Flash
- `2.5-pro` - 🟦 Gemini 2.5 Pro
- `1.5-pro` - 🟦 Gemini Pro Latest
- `pro-latest` - 🟦 Gemini Pro Latest
- `pro@latest` - 🟦 Gemini Pro Latest

### Help

```bash
piptalk --help
piptalk -h
```

## Examples

```bash
# Interactive mode
piptalk

# Quick question
piptalk "What is the capital of France?"

# Use a specific model
piptalk -m 2.0-flash "Write a Python function to sort a list"
piptalk -m 2.5-pro "Explain the difference between REST and GraphQL"

# Multi-word prompts
piptalk "Explain the difference between REST and GraphQL"
```

## Requirements

- Python >= 3.8
- A valid Gemini API key (optional, default key included)

## Features

- ✨ Beautiful formatted output with syntax highlighting
- 🎨 Color-coded responses for better readability
- 📝 Code block formatting with borders
- 📋 List and header formatting
- 🔄 Support for multiple Gemini models
- 💬 Interactive and command-line modes

## License

ISC

## Development

To set up for development:

```bash
git clone <repository-url>
cd gemini-cli-python
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt
pip install -e .
```

## Publishing to PyPI

```bash
# Install build tools
pip install build twine

# Build the package
python -m build

# Upload to PyPI (test first with test.pypi.org)
twine upload dist/*
```
