minor update

app.py

@@ -1,3 +1,4 @@
+# Import necessary libraries
 import gradio as gr
 import pixeltable as pxt
 import os
@@ -7,33 +8,31 @@ from pixeltable.functions import openai as pxop
 import openai
 
 
-# pixeltable setup
+# Set up Pixeltable database and table
 db_directory = "video_db"
 table_name = "video_table"
 
-# constants
-
+# Define constants
 MAX_VIDEO_SIZE_MB = 35
 GPT_MODEL = "gpt-4o-mini-2024-07-18"
 MAX_TOKENS = 500
 WHISPER_MODEL = "whisper-1"
 
-# Set your OpenAI API key
+# Set OpenAI API key
 if "OPENAI_API_KEY" not in os.environ:
     os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")
 
-
+# Clean up existing database and table if they exist
 pxt.drop_dir("video_db", force=True)
 if table_name in pxt.list_tables():
     pxt.drop_table("video_db.video_table")
 
-# Check if the directory exists, if not, create it
+# Create or use existing directory and table
 if db_directory not in pxt.list_dirs():
     pxt.create_dir(db_directory)
 else:
     print(f"Directory {db_directory} already exists. Using the existing directory.")
 
-# Check if the table exists, if not, create it
 if table_name not in pxt.list_tables():
     t = pxt.create_table(
         f"{db_directory}.{table_name}",
@@ -44,12 +43,10 @@ if table_name not in pxt.list_tables():
             "sm_post": pxt.StringType(),
         },
     )
-
 else:
     t = pxt.load_table(f"{db_directory}.{table_name}")
     print(f"Table {table_name} already exists. Using the existing table.")
 
-
 # Function to generate social media post using OpenAI GPT-4 API
 def generate_social_media_post(transcript_text, social_media_type):
     response = openai.chat.completions.create(
@@ -68,50 +65,32 @@ def generate_social_media_post(transcript_text, social_media_type):
     )
     return response.choices[0].message.content
 
-
 # Function to process the uploaded video and generate the post
 def process_and_generate_post(video_file, social_media_type):
     if video_file:
         try:
+            # Check video file size
             video_size = os.path.getsize(video_file) / (1024 * 1024)  # Convert to MB
-
             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."
 
             video_filename = os.path.basename(video_file)
             tr_audio_gen_flag = True
             sm_gen_flag = True
-            print(
-                "##################\nthe video file and social media are..."
-                + video_file
-                + "....."
-                + social_media_type
-            )
-            video_df = t.where(t.video_filename == video_filename).tail(1)
 
+            # Check if video already exists in the table
+            video_df = t.where(t.video_filename == video_filename).tail(1)
             if t.select().where(t.video_filename == video_filename).count() >= 1:
-                # print('Video Exists')
                 tr_audio_gen_flag = False
 
-            # Check if video and sm type exists
+            # Check if video and social media type combination exists
             video_type_df = t.where(
                 (t.video_filename == video_filename) & (t.sm_type == social_media_type)
             ).tail(1)
-
             if video_type_df:
-                # print('Video & Type Exists')
                 sm_gen_flag = False
 
-            # print(video_df)
-
-            # print('both the cases....')
-
-            # print(video_df  and not video_type_df)
-
-            # print(t.select().where(t.video_filename == video_filename).count() >=1 )
-
-            # print(t.select().where((t.video_filename == video_filename) & (t.sm_type == social_media_type)).count() >=1 )
-
+            # Insert video into PixelTable if it doesn't exist or if it's a new social media type
             if (
                 (t.count() < 1)
                 or not (
@@ -119,7 +98,6 @@ def process_and_generate_post(video_file, social_media_type):
                 )
                 or (video_df and not video_type_df)
             ):
-                # Insert video into PixelTable
                 t.insert(
                     [
                         {
@@ -131,9 +109,8 @@ def process_and_generate_post(video_file, social_media_type):
                     ]
                 )
 
+            # Extract audio and transcribe if needed
             if tr_audio_gen_flag:
-                # Extract audio from video
-
                 if not t.get_column(name="audio"):
                     t["audio"] = extract_audio(t.video, format="mp3")
                 else:
@@ -141,7 +118,6 @@ def process_and_generate_post(video_file, social_media_type):
 
                 print("########### processing transcription #############")
 
-                # Transcribe audio using OpenAI Whisper API
                 if not t.get_column(name="transcription"):
                     t["transcription"] = pxop.transcriptions(
                         t.audio, model=WHISPER_MODEL
@@ -149,8 +125,7 @@ def process_and_generate_post(video_file, social_media_type):
                 else:
                     t.transcription = pxop.transcriptions(t.audio, model=WHISPER_MODEL)
 
-            # cur_video_df = t.where((t.video_filename == video_filename) & (t.sm_type == social_media_type)).tail(1)[0]
-
+            # Get the current video data
             filtered_df = t.where(
                 (t.video_filename == video_filename) & (t.sm_type == social_media_type)
             ).tail(1)
@@ -161,11 +136,7 @@ def process_and_generate_post(video_file, social_media_type):
             cur_video_df = filtered_df[0]
             plain_text = cur_video_df["transcription"]["text"]
 
-            # plain_text = cur_video_df['transcription']['text']
-
-            # print(t.show())
-            # print('status of social media type')
-            # print(t.select().where((t.video_filename == video_filename) & (t.sm_type == social_media_type)).count() >=1)
+            # Generate or retrieve social media post
             if (
                 t.select()
                 .where(
@@ -176,7 +147,6 @@ def process_and_generate_post(video_file, social_media_type):
                 .count()
                 >= 1
             ):
-
                 print("retrieving existing social media post")
                 social_media_post = (
                     t.select(t.sm_post)
@@ -186,10 +156,7 @@ def process_and_generate_post(video_file, social_media_type):
                     )
                     .collect()["sm_post"]
                 )
-                return social_media_post
-
             else:
-
                 print("generating new social media post")
                 social_media_post = generate_social_media_post(
                     plain_text, social_media_type
@@ -197,8 +164,6 @@ def process_and_generate_post(video_file, social_media_type):
                 if sm_gen_flag:
                     cur_video_df.update({"sm_post": social_media_post})
 
-            #            print(t.show())
-
             return cur_video_df["sm_post"]
 
         except Exception as e:
@@ -206,10 +171,10 @@ def process_and_generate_post(video_file, social_media_type):
     else:
         return "Please upload a video file."
 
-
 # Gradio Interface
 def gradio_interface():
     with gr.Blocks(theme=gr.themes.Glass()) as demo:
+        # Set up the UI components
         gr.Markdown(
             """<center><font size=12>Video to Social Media Post Generator</center>"""
         )
@@ -236,14 +201,13 @@ def gradio_interface():
         )
         generate_btn = gr.Button("Generate Post", interactive= True)
 
-        #video_input.upload(lambda : gr.Button(interactive=True), None, generate_btn)
-
         output = gr.Textbox(label="Generated Social Media Post", show_copy_button=True)
 
         examples = gr.Examples(
             [["example1.mp4"], ["example2.mp4"]], inputs=[video_input]
         )
 
+        # Connect the generate button to the processing function
         generate_btn.click(
             fn=process_and_generate_post,
             inputs=[video_input, social_media_type],
@@ -252,5 +216,5 @@ def gradio_interface():
 
     return demo
 
-
-gradio_interface().launch(show_api=False)
+# Launch the Gradio interface
+gradio_interface().launch(show_api=False)