app.py

import openai
from transformers import MBartForConditionalGeneration, MBart50Tokenizer
import gradio as gr
import requests
import io
from PIL import Image
import os
import time  # Importing time to add delays for sequential execution

# Set up your OpenAI API key (make sure it's stored as an environment variable)
openai_api_key = os.getenv("OPENAI_API_KEY")
if openai_api_key is None:
    raise ValueError("OpenAI API key not found! Please set 'OPENAI_API_KEY' environment variable.")
else:
    openai.api_key = openai_api_key

# Load the translation model and tokenizer
model_name = "facebook/mbart-large-50-many-to-one-mmt"
tokenizer = MBart50Tokenizer.from_pretrained(model_name)
model = MBartForConditionalGeneration.from_pretrained(model_name)

# Use the Hugging Face API key from environment variables for text-to-image model
hf_api_key = os.getenv("full_token")
if hf_api_key is None:
    raise ValueError("Hugging Face API key not found! Please set 'hf_token' environment variable.")
else:
    headers = {"Authorization": f"Bearer {hf_api_key}"}

API_URL = "https://api-inference.huggingface.co/models/ZB-Tech/Text-to-Image"

# Define the OpenAI GPT-3 text generation function with error handling
def generate_with_gpt3(prompt, max_tokens=150, temperature=0.7):
    try:
        print("Generating text with GPT-3...")
        response = openai.Completion.create(
            engine="text-davinci-003",  # Use "text-davinci-003" for high-quality outputs
            prompt=prompt,
            max_tokens=max_tokens,
            temperature=temperature,
            top_p=0.9,
            frequency_penalty=0.0,
            presence_penalty=0.0
        )
        generated_text = response.choices[0].text.strip()
        print("Text generation completed.")
        return generated_text
    except Exception as e:
        print(f"OpenAI API Error: {e}")
        return "Error generating text with GPT-3. Check the OpenAI API settings."

# Define the translation, GPT-3 text generation, and image generation function
def translate_and_generate_image(tamil_text):
    # Step 1: Translate Tamil text to English using mbart-large-50
    try:
        print("Translating Tamil text to English...")
        tokenizer.src_lang = "ta_IN"
        inputs = tokenizer(tamil_text, return_tensors="pt")
        translated_tokens = model.generate(**inputs, forced_bos_token_id=tokenizer.lang_code_to_id["en_XX"])
        translated_text = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0]
        print(f"Translation completed: {translated_text}")
    except Exception as e:
        return "Error during translation: " + str(e), "", None

    # Ensure sequential flow by waiting before moving to the next step
    time.sleep(1)  # Optional: Add a small delay to ensure proper execution order

    # Step 2: Generate high-quality descriptive text using OpenAI's GPT-3
    try:
        print("Generating descriptive text from translated English text...")
        prompt = f"Create a detailed and creative description based on the following text: {translated_text}"
        generated_text = generate_with_gpt3(prompt, max_tokens=150, temperature=0.7)
        print(f"Text generation completed: {generated_text}")
    except Exception as e:
        return translated_text, f"Error during text generation: {e}", None

    # Ensure sequential flow by waiting before moving to the next step
    time.sleep(1)  # Optional: Add a small delay to ensure proper execution order

    # Step 3: Use the generated English text to create an image
    try:
        print("Generating image from the generated descriptive text...")
        def query(payload):
            response = requests.post(API_URL, headers=headers, json=payload)
            response.raise_for_status()  # Raise error if request fails
            return response.content

        # Generate image using the descriptive text
        image_bytes = query({"inputs": generated_text})
        image = Image.open(io.BytesIO(image_bytes))
        print("Image generation completed.")
    except Exception as e:
        return translated_text, generated_text, f"Error during image generation: {e}"

    return translated_text, generated_text, image

# Gradio interface setup
iface = gr.Interface(
    fn=translate_and_generate_image,
    inputs=gr.Textbox(lines=2, placeholder="Enter Tamil text here..."),
    outputs=[gr.Textbox(label="Translated English Text"), 
             gr.Textbox(label="Generated Descriptive Text"),
             gr.Image(label="Generated Image")],
    title="Tamil to English Translation, GPT-3 Text Generation, and Image Creation",
    description="Translate Tamil text to English using Facebook's mbart-large-50 model, generate high-quality text using GPT-3, and create an image using the generated text.",
)

# Launch Gradio app without `share=True`
iface.launch()