Update app.py

app.py

@@ -12,8 +12,8 @@ from llama_index.llms.openai import OpenAI
 from llama_index.core import get_response_synthesizer
 from dotenv import load_dotenv
 from sentence_transformers import SentenceTransformer, util
-from openai_tts_tool import text_to_speech_openai  # Importing updated TTS tool
 import logging
+from openai_tts_tool import generate_audio_and_text  # Importing the TTS tool
 
 # Set up logging configuration
 logging.basicConfig(level=logging.INFO, format='%(asctime)s | %(levelname)s | %(message)s')
@@ -24,7 +24,6 @@ load_dotenv()
 # Initialize global variables
 vector_index = None
 query_log = []
-answer_state = gr.State()  # State object to hold answer
 sentence_model = SentenceTransformer('all-MiniLM-L6-v2')
 
 langs = os.popen('tesseract --list-langs').read().split('\n')[1:-1]
@@ -127,12 +126,8 @@ def calculate_similarity(response, ground_truth):
 
     return similarity_percentage
 
-def process_tts(api_key, text, model_name, voice_type, voice_speed, language, output_option, summary_length, additional_prompt):
-    audio_path = "output_audio.wav"  # Define the output path for the audio
-    return text_to_speech_openai(text, audio_path, voice_type, voice_speed)
-
-def query_app(query, model_name, use_similarity_check, openai_api_key):
-    global vector_index, query_log, answer_state
+def query_app(query, model_name, use_similarity_check, openai_api_key, answer_state):
+    global vector_index, query_log
 
     if vector_index is None:
         logging.error("No documents indexed yet. Please upload documents first.")
@@ -158,7 +153,6 @@ def query_app(query, model_name, use_similarity_check, openai_api_key):
         return f"Error during query processing: {e}", None
 
     generated_response = response.response
-    answer_state.value = generated_response  # Update the answer state
     query_log.append({
         "query_id": str(len(query_log) + 1),
         "query": query,
@@ -179,72 +173,51 @@ def query_app(query, model_name, use_similarity_check, openai_api_key):
             logging.error(f"Error during similarity calculation: {e}")
             metrics['error'] = f"Error during similarity calculation: {e}"
 
+    if answer_state is None:
+        answer_state = gr.State()
+
+    answer_state.value = generated_response
+
     return generated_response, metrics if use_similarity_check else None
 
+def process_tts(api_key, text, model_name, voice_type, voice_speed, language, output_option, summary_length, additional_prompt):
+    return generate_audio_and_text(api_key, text, model_name, voice_type, voice_speed, language, output_option, summary_length, additional_prompt)
+
 def main():
-    with gr.Blocks(title="Document Processing App") as demo:
-        gr.Markdown("# 📄 Document Processing and Querying App")
+    with gr.Blocks(title="Document Processing and TTS App") as demo:
+        gr.Markdown("# 📄 Document Processing, Text & Audio Generation App")
 
+        # Upload documents and chat functionality
         with gr.Tab("📤 Upload Documents"):
-            gr.Markdown("### Enter your OpenAI API Key and Upload PDF, DOCX, or TXT files to index")
-            
             api_key_input = gr.Textbox(label="Enter OpenAI API Key", placeholder="Paste your OpenAI API Key here")
-            
-            with gr.Row():
-                file_upload = gr.File(label="Upload Files", file_count="multiple", type="filepath")
-                lang_dropdown = gr.Dropdown(choices=langs, label="Select OCR Language", value='eng')
+            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)
+            upload_button.click(fn=process_upload, inputs=[api_key_input, file_upload, lang_dropdown], outputs=[upload_status])
 
-            upload_button.click(
-                fn=process_upload,
-                inputs=[api_key_input, file_upload, lang_dropdown],
-                outputs=[upload_status]
-            )
-
+        answer_state = gr.State()  # Initialize answer state here
         with gr.Tab("❓ Ask a Question"):
-            gr.Markdown("### Query the indexed documents")
-            with gr.Column():
-                query_input = gr.Textbox(label="Enter your question", placeholder="Type your question here...")
-                model_dropdown = gr.Dropdown(
-                    choices=["gpt-4o", "gpt-4o-mini"],
-                    value="gpt-4o",
-                    label="Select Model"
-                )
-                similarity_checkbox = gr.Checkbox(label="Use Similarity Check", value=False)
-                query_button = gr.Button("Ask")
-            with gr.Column():
-                answer_output = gr.Textbox(label="Answer", interactive=False)
-                metrics_output = gr.JSON(label="Metrics")
-
-            query_button.click(
-                fn=query_app,
-                inputs=[query_input, model_dropdown, similarity_checkbox, api_key_input],
-                outputs=[answer_output, metrics_output]
-            )
-
-        with gr.Tab("🗣️ Generate Audio/Text"):
-            gr.Markdown("### Convert your text to audio or generate text summary with audio narration")
-            with gr.Row():
-                text_input = gr.Textbox(label="Enter text for generation", value=answer_state)
-                model_dropdown = gr.Dropdown(choices=["tts-1-hd"], value="tts-1-hd", label="Select TTS Model")
-                voice_type = gr.Textbox(label="Voice Type", value="female")  # Example of setting default values
-                voice_speed = gr.Slider(0.5, 2.0, 1.0, label="Voice Speed")
-            with gr.Row():
-                generate_button = gr.Button("Generate")
-                audio_output = gr.Audio(label="Generated Audio")
-                text_output = gr.Textbox(label="Generated Text", interactive=False)
-
-            generate_button.click(
-                fn=process_tts,
-                inputs=[api_key_input, text_input, model_dropdown, voice_type, voice_speed, "en", "Both", None, ""],
-                outputs=[text_output, audio_output]
-            )
-
-        gr.Markdown("""
-        ---
-        **Note:** Ensure you upload documents before attempting to query. Enter a valid OpenAI API Key to interact with the models.
-        """)
+            query_input = gr.Textbox(label="Enter your question")
+            model_dropdown = gr.Dropdown(choices=["gpt-4o", "gpt-4o-mini"], label="Select Model", value="gpt-4o")
+            similarity_checkbox = gr.Checkbox(label="Use Similarity Check", value=False)
+            query_button = gr.Button("Ask")
+            answer_output = gr.Textbox(label="Answer", interactive=False)
+            metrics_output = gr.JSON(label="Metrics")
+            query_button.click(fn=query_app, inputs=[query_input, model_dropdown, similarity_checkbox, api_key_input, answer_state], outputs=[answer_output, metrics_output])
+
+        with gr.Tab("🗣️ Generate Audio and Text"):
+            text_input = gr.Textbox(label="Enter text for generation", value=answer_state)
+            voice_type = gr.Dropdown(choices=["alloy", "echo", "fable", "onyx"], label="Voice Type", value="alloy")
+            voice_speed = gr.Dropdown(choices=["normal", "slow", "fast"], label="Voice Speed", value="normal")
+            language = gr.Dropdown(choices=["en", "ar", "de", "hi"], label="Language", value="en")
+            output_option = gr.Radio(choices=["audio", "summary_text", "both"], label="Output Option", value="both")
+            summary_length = gr.Number(label="Summary Length", value=100)
+            additional_prompt = gr.Textbox(label="Additional Prompt (Optional)")
+            generate_button = gr.Button("Generate")
+            audio_output = gr.Audio(label="Generated Audio", interactive=False)
+            summary_output = gr.Textbox(label="Generated Summary Text", interactive=False)
+            generate_button.click(fn=process_tts, inputs=[api_key_input, text_input, model_dropdown, voice_type, voice_speed, language, output_option, summary_length, additional_prompt], outputs=[audio_output, summary_output])
 
     demo.launch()