app.py

import os
import cv2
import numpy as np
from PIL import Image
import pytesseract
import gradio as gr
from pdf2image import convert_from_path
import PyPDF2
from llama_index.core import VectorStoreIndex, Document
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.llms.openai import OpenAI
from llama_index.core import get_response_synthesizer
from sentence_transformers import SentenceTransformer, util
import logging
from openai_tts_tool import generate_audio_and_text
import tempfile

# Set up logging configuration
logging.basicConfig(level=logging.INFO, format='%(asctime)s | %(levelname)s | %(message)s')

# Initialize global variables
vector_index = None
query_log = []
sentence_model = SentenceTransformer('all-MiniLM-L6-v2')

# Define available languages for TTS
AVAILABLE_LANGUAGES = [
    ("en", "English"),
    ("ar", "Arabic"),
    ("de", "German"),
    ("mr", "Marathi"),
    ("kn", "Kannada"),
    ("tl", "Filipino (Tagalog)"),
    ("fr", "French"),
    ("gu", "Gujarati"),
    ("hi", "Hindi"),
    ("ml", "Malayalam"),
    ("ta", "Tamil"),
    ("te", "Telugu"),
    ("ur", "Urdu"),
    ("si", "Sinhala")
]

# Get available languages for OCR
try:
    langs = os.popen('tesseract --list-langs').read().split('\n')[1:-1]
except:
    langs = ['eng']  # Fallback to English if tesseract isn't properly configured

# ... (keep all the existing functions until create_gradio_interface unchanged) ...

def create_gradio_interface():
    with gr.Blocks(title="Document Processing and TTS App") as demo:
        gr.Markdown("# 📄 Document Processing, Text & Audio Generation App")
        
        with gr.Tab("📤 Upload Documents"):
            api_key_input = gr.Textbox(
                label="Enter OpenAI API Key",
                placeholder="Paste your OpenAI API Key here",
                type="password"
            )
            file_upload = gr.File(label="Upload Files", file_count="multiple", type="filepath")
            lang_dropdown = gr.Dropdown(choices=langs, label="Select OCR Language", value='eng')
            upload_button = gr.Button("Upload and Index")
            upload_status = gr.Textbox(label="Status", interactive=False)

        with gr.Tab("❓ Ask a Question"):
            query_input = gr.Textbox(label="Enter your question")
            model_dropdown = gr.Dropdown(
                choices=["gpt-4-0125-preview", "gpt-3.5-turbo-0125"],
                label="Select Model",
                value="gpt-3.5-turbo-0125"
            )
            similarity_checkbox = gr.Checkbox(label="Use Similarity Check", value=False)
            query_button = gr.Button("Ask")
            answer_output = gr.Textbox(label="Answer", interactive=False)

        with gr.Tab("🗣️ Generate Audio and Text"):
            text_input = gr.Textbox(label="Enter text for generation")
            voice_type = gr.Dropdown(
                choices=["alloy", "echo", "fable", "onyx", "nova", "shimmer"],
                label="Voice Type",
                value="alloy"
            )
            voice_speed = gr.Slider(
                minimum=0.25,
                maximum=4.0,
                value=1.0,
                label="Voice Speed"
            )
            language = gr.Dropdown(
                choices=[(code, name) for code, name in AVAILABLE_LANGUAGES],
                label="Language for Audio and Script",
                value="en",
                type="value"
            )
            output_option = gr.Radio(
                choices=["audio", "script_text", "both"],
                label="Output Option",
                value="both"
            )
            generate_button = gr.Button("Generate")
            audio_output = gr.Audio(label="Generated Audio")
            script_output = gr.File(label="Script Text File")
            status_output = gr.Textbox(label="Status", interactive=False)

        # Wire up the components
        upload_button.click(
            fn=process_upload,
            inputs=[api_key_input, file_upload, lang_dropdown],
            outputs=[upload_status]
        )
        
        query_button.click(
            fn=query_app,
            inputs=[query_input, model_dropdown, similarity_checkbox, api_key_input],
            outputs=[answer_output]
        )
        
        answer_output.change(
            fn=lambda ans: ans,
            inputs=[answer_output],
            outputs=[text_input]
        )
        
        generate_button.click(
            fn=generate_audio_and_text,
            inputs=[
                api_key_input, text_input, model_dropdown, voice_type,
                voice_speed, language, output_option
            ],
            outputs=[audio_output, script_output, status_output]
        )

    return demo

if __name__ == "__main__":
    demo = create_gradio_interface()
    demo.launch()
else:
    demo = create_gradio_interface()