Update app.py

app.py

@@ -43,10 +43,10 @@ def process_and_generate_post(video_file, social_media_type, progress=gr.Progres
     t['metadata'] = get_metadata(t.audio)
     t['transcription'] = openai.transcriptions(audio=t.audio, model='whisper-1')
     t['transcription_text'] = t.transcription.text
+
+    progress(0.1, desc="Creating UDFs...")
     
-    # Custom UDF for Generating Social Media Prompts
-    
-    #Custom User-Defined Function (UDF) for Generating Social Media Prompts
+    # Custom User-Defined Function (UDF) for Generating Social Media Prompts
     @pxt.udf
     def prompt(A: str, B: str) -> list[dict]:
         system_msg = 'You are an expert in creating social media content and you generate effective post, based on user content. Respect the social media platform guidelines and constraints.'
@@ -60,6 +60,8 @@ def process_and_generate_post(video_file, social_media_type, progress=gr.Progres
     t['message'] = prompt(t.sm_type, t.transcription_text)
     
     """## Generating Responses with OpenAI's GPT Model"""
+
+    progress(0.2, desc="Calling LLMs")
     
     # # Generate responses using OpenAI's chat completion API
     t['response'] = openai.chat_completions(messages=t.message, model='gpt-4o-mini-2024-07-18', max_tokens=500)
@@ -77,24 +79,22 @@ def process_and_generate_post(video_file, social_media_type, progress=gr.Progres
         if video_size > MAX_VIDEO_SIZE_MB:
             return f"The video file is larger than {MAX_VIDEO_SIZE_MB} MB. Please upload a smaller file.", None
 
+        progress(0.4, desc="Inserting video...")
+        
         # # Insert a video into the table. Pixeltable supports referencing external data sources like URLs
         t.insert([{
             "video": video_file,
             "sm_type": social_media_type
         }])
 
-        progress(0.2, desc="Extracting audio and frames...")
-
+        progress(0.6, desc="Generating posts...")
+        
         # Retrieve Social media posts
         social_media_post = t.select(t.answer).tail(1)['answer'][0]
 
-        progress(0.4, desc="Transcribing audio...")
-
         # Retrieve Audio
         audio = t.select(t.audio).tail(1)['audio'][0]
 
-        progress(0.6, desc="Generating posts...")
-
         # Retrieve thumbnails
         thumbnails = frames_view.select(frames_view.frame).tail(6)['frame']
 
@@ -162,8 +162,10 @@ def gradio_interface():
 
                 gr.Examples(
             examples=[["example1.mp4"], ["example2.mp4"], ["example3.mp4"]],
-            inputs=[video_input]
+            inputs=[video_input], cache_examples=True
         )
+                audio = gr.Audio(label="Extracted audio", show_download_button=True)
+                
             with gr.Column():
                 output = gr.Textbox(label="Generated Social Media Post", show_copy_button=True)
                 thumbnail = gr.Gallery(
@@ -172,7 +174,6 @@ def gradio_interface():
                     show_fullscreen_button=True,
                     height='400px'
                 )
-                audio = gr.Audio(label="Extracted audio", show_download_button=True)
 
         df_output = gr.Textbox(label="Transcription", show_copy_button=True)