Sends a character chain to a Groq model and retrieves the corresponding RFC 5646 language code (Groq API key needed)

groq_language_detector.py

import os
import json
from groq import Groq

def get_language_code(text: str, api_key: str = None) -> str:
    """
    Identify the RFC 5646 language code of given text using Groq API.
    
    Args:
        text: The text to identify
        api_key: Your Groq API key (or set GROQ_API_KEY env variable)
    
    Returns:
        RFC 5646 language code (e.g., 'en', 'fr', 'es')
    """
    client = Groq(api_key=api_key or os.environ.get("GROQ_API_KEY"))
    
    prompt = f"""Identify the language of the following text and return ONLY a JSON object with this exact format:
{{"code": "RFC 5646 language code"}}

Do not include any explanation, markdown formatting, or additional text. Only return the JSON object.

Text: "{text}"
"""
    
    chat_completion = client.chat.completions.create(
        messages=[{"role": "user", "content": prompt}],
        model="llama-3.3-70b-versatile",
        temperature=0.1,
        max_tokens=50,
    )
    
    response_text = chat_completion.choices[0].message.content.strip()
    
    # Remove markdown code blocks if present
    if response_text.startswith("```"):
        response_text = response_text.split("```")[1]
        if response_text.startswith("json"):
            response_text = response_text[4:]
        response_text = response_text.strip()
    
    result = json.loads(response_text)
    return result["code"]


# Example usage
if __name__ == "__main__":
    examples = [
        "Bonjour, comment allez-vous?",
        "Hello, how are you?",
        "¿Hola, cómo estás?",
        "Guten Tag!",
    ]
    
    for text in examples:
        code = get_language_code(text)
        print(f"{text} → {code}")