Update app.py

app.py

@@ -23,137 +23,31 @@ 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
 
-def create_temp_dir():
-    """Create temporary directory if it doesn't exist"""
-    temp_dir = os.path.join(os.getcwd(), 'temp')
-    if not os.path.exists(temp_dir):
-        os.makedirs(temp_dir)
-    return temp_dir
-
-def preprocess_image(image_path):
-    img = cv2.imread(image_path)
-    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
-    gray = cv2.equalizeHist(gray)
-    gray = cv2.GaussianBlur(gray, (5, 5), 0)
-    processed_image = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
-                                          cv2.THRESH_BINARY, 11, 2)
-    temp_dir = create_temp_dir()
-    temp_filename = os.path.join(temp_dir, "processed_image.png")
-    cv2.imwrite(temp_filename, processed_image)
-    return temp_filename
-
-def extract_text_from_image(image_path, lang='eng'):
-    processed_image_path = preprocess_image(image_path)
-    text = pytesseract.image_to_string(Image.open(processed_image_path), lang=lang)
-    try:
-        os.remove(processed_image_path)
-    except:
-        pass
-    return text
-
-def extract_text_from_pdf(pdf_path, lang='eng'):
-    text = ""
-    temp_dir = create_temp_dir()
-    try:
-        with open(pdf_path, 'rb') as file:
-            pdf_reader = PyPDF2.PdfReader(file)
-            for page_num in range(len(pdf_reader.pages)):
-                page = pdf_reader.pages[page_num]
-                page_text = page.extract_text()
-                if page_text.strip():
-                    text += page_text
-                else:
-                    images = convert_from_path(pdf_path, first_page=page_num + 1, last_page=page_num + 1)
-                    for image in images:
-                        temp_image_path = os.path.join(temp_dir, f'temp_image_{page_num}.png')
-                        image.save(temp_image_path, 'PNG')
-                        text += extract_text_from_image(temp_image_path, lang=lang)
-                        text += f"\n[OCR applied on page {page_num + 1}]\n"
-                        try:
-                            os.remove(temp_image_path)
-                        except:
-                            pass
-    except Exception as e:
-        return f"Error processing PDF: {str(e)}"
-    return text
-
-def extract_text(file_path, lang='eng'):
-    file_ext = file_path.lower().split('.')[-1]
-    if file_ext in ['pdf']:
-        return extract_text_from_pdf(file_path, lang)
-    elif file_ext in ['png', 'jpg', 'jpeg']:
-        return extract_text_from_image(file_path, lang)
-    else:
-        return f"Unsupported file type: {file_ext}"
-
-def process_upload(api_key, files, lang):
-    global vector_index
-
-    if not api_key:
-        return "Please provide a valid OpenAI API Key."
-
-    if not files:
-        return "No files uploaded."
-
-    documents = []
-    error_messages = []
-    image_heavy_docs = []
-
-    for file_path in files:
-        try:
-            text = extract_text(file_path, lang)
-            if "This document consists of" in text and "page(s) of images" in text:
-                image_heavy_docs.append(os.path.basename(file_path))
-            documents.append(Document(text=text))
-        except Exception as e:
-            error_message = f"Error processing file {os.path.basename(file_path)}: {str(e)}"
-            logging.error(error_message)
-            error_messages.append(error_message)
-
-    if documents:
-        try:
-            embed_model = OpenAIEmbedding(model="text-embedding-3-large", api_key=api_key)
-            vector_index = VectorStoreIndex.from_documents(documents, embed_model=embed_model)
-            
-            success_message = f"Successfully indexed {len(documents)} files."
-            if image_heavy_docs:
-                success_message += f"\nNote: The following documents consist mainly of images and may require manual review: {', '.join(image_heavy_docs)}"
-            if error_messages:
-                success_message += f"\nErrors: {'; '.join(error_messages)}"
-            
-            return success_message
-        except Exception as e:
-            return f"Error creating index: {str(e)}"
-    else:
-        return f"No valid documents were indexed. Errors: {'; '.join(error_messages)}"
-
-def query_app(query, model_name, use_similarity_check, api_key):
-    global vector_index, query_log
-
-    if vector_index is None:
-        return "No documents indexed yet. Please upload documents first."
-
-    if not api_key:
-        return "Please provide a valid OpenAI API Key."
-
-    try:
-        llm = OpenAI(model=model_name, api_key=api_key)
-        response_synthesizer = get_response_synthesizer(llm=llm)
-        query_engine = vector_index.as_query_engine(llm=llm, response_synthesizer=response_synthesizer)
-        response = query_engine.query(query)
-        
-        generated_response = response.response
-        return generated_response
-
-    except Exception as e:
-        logging.error(f"Error during query processing: {e}")
-        return f"Error during query processing: {str(e)}"
+# ... (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:
@@ -173,9 +67,9 @@ def create_gradio_interface():
         with gr.Tab("❓ Ask a Question"):
             query_input = gr.Textbox(label="Enter your question")
             model_dropdown = gr.Dropdown(
-                choices=["gpt-4o-mini", "gpt-4o"],
+                choices=["gpt-4-0125-preview", "gpt-3.5-turbo-0125"],
                 label="Select Model",
-                value="gpt-4o-mini"
+                value="gpt-3.5-turbo-0125"
             )
             similarity_checkbox = gr.Checkbox(label="Use Similarity Check", value=False)
             query_button = gr.Button("Ask")
@@ -194,6 +88,12 @@ def create_gradio_interface():
                 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",
@@ -227,7 +127,7 @@ def create_gradio_interface():
             fn=generate_audio_and_text,
             inputs=[
                 api_key_input, text_input, model_dropdown, voice_type,
-                voice_speed, output_option
+                voice_speed, language, output_option
             ],
             outputs=[audio_output, script_output, status_output]
         )