A Python tool for processing CSV and Google Sheets data using Perplexity and OpenAI APIs. This tool supports both CLI and API modes, allowing for flexible integration into various workflows.

• Process CSV files and Google Sheets
• Support for both Perplexity and OpenAI APIs
• Interactive CLI mode
• RESTful API mode
• Asynchronous processing for better performance
• Column selection and custom prompts
• Automatic output column naming

1. Clone the repository:

git clone <repository-url>
cd <repository-name>

2. Create and activate a virtual environment:

python -m venv env
source env/bin/activate  # On Windows: env\Scripts\activate

3. Install dependencies:

pip install -r requirements.txt

Create a .env file with your API keys and Google Sheets credentials:

PERPLEXITY_API_KEY=your_perplexity_api_key
OPENAI_API_KEY=your_openai_api_key
GOOGLE_SHEETS_CREDENTIALS_PATH=path/to/your/credentials.json

1. Interactive mode:

python -m src

2. Command line mode:

python -m src -i "https://docs.google.com/spreadsheets/d/YOUR_SHEET_ID" -c "col1,col2" -p "Your prompt"

Options:

• -i, --input: Input CSV file or Google Sheets URL
• -c, --columns: Comma-separated list of columns to use
• -p, --prompt: Prompt to process
• --credentials: Path to Google Sheets credentials JSON file
• --openai: Use OpenAI instead of Perplexity
• --output-column-name: Name for the output column

1. Start the server:

python -m src api

2. API Endpoints:

• POST /initialize: Initialize sheet connection
• GET /columns: Get available columns
• POST /process: Process data with configuration

Example API usage:

import requests

# Initialize sheet
response = requests.post("http://localhost:8000/initialize", json={
    "input_source": "https://docs.google.com/spreadsheets/d/YOUR_SHEET_ID",
    "credentials_path": "path/to/credentials.json"
})

# Get columns
columns = requests.get("http://localhost:8000/columns").json()

# Process data
response = requests.post("http://localhost:8000/process", json={
    "columns": ["col1", "col2"],
    "prompt": "Your prompt",
    "use_openai": False,
    "output_column_name": "result"
})

The project structure is organized as follows:

src/
├── __init__.py          # Main entry point
├── clients/             # API clients
├── models/             # Data models
├── services/           # Business logic
├── utils/              # Utilities
├── cli/               # CLI interface
└── api/               # API interface

MIT License