Update app.py

app.py

@@ -6,6 +6,7 @@ from moviepy.editor import VideoFileClip
 from datetime import datetime
 import pytz
 from audio_recorder_streamlit import audio_recorder
+from PIL import Image
 
 openai.api_key, openai.organization = os.getenv('OPENAI_API_KEY'), os.getenv('OPENAI_ORG_ID') 
 client = OpenAI(api_key=os.getenv('OPENAI_API_KEY'), organization=os.getenv('OPENAI_ORG_ID'))
@@ -102,12 +103,12 @@ def process_audio_for_video(video_input):
     if video_input:
         st.session_state.messages.append({"role": "user", "content": video_input})
         transcription = client.audio.transcriptions.create(model="whisper-1", file=video_input)
-        response = client.chat.completions.create(model=MODEL, messages=[{"role": "system", "content":"You are generating a transcript summary. Create a summary of the provided transcription. Respond in Markdown."}, {"role": "user", "content": [{"type": "text", "text": f"The audio transcription is: {transcription}"}]}], temperature=0)
+        response = client.chat.completions.create(model=MODEL, messages=[{"role": "system", "content":"You are generating a transcript summary. Create a summary of the provided transcription. Respond in Markdown."}, {"role": "user", "content": [{"type": "text", "text": f"The audio transcription is: {transcription.text}"}]}], temperature=0)
         video_response = response.choices[0].message.content
         with st.chat_message("assistant"):
             st.markdown(video_response)
-        filename = generate_filename(transcription, "md")
-        create_file(filename, transcription, video_response, should_save=True)
+        filename = generate_filename(transcription.text, "md")
+        create_file(filename, transcription.text, video_response, should_save=True)
         st.session_state.messages.append({"role": "assistant", "content": video_response})
         return video_response
 
@@ -147,6 +148,39 @@ def save_and_play_audio(audio_recorder):
         return filename
     return None
 
+@st.cache_resource
+def display_videos_and_links(num_columns):
+    video_files = [f for f in os.listdir('.') if f.endswith('.mp4')]
+    if not video_files:
+        st.write("No MP4 videos found in the current directory.")
+        return
+    video_files_sorted = sorted(video_files, key=lambda x: len(x.split('.')[0]))
+    cols = st.columns(num_columns) # Define num_columns columns outside the loop
+    col_index = 0 # Initialize column index
+    for video_file in video_files_sorted:
+        with cols[col_index % num_columns]: # Use modulo 2 to alternate between the first and second column
+            k = video_file.split('.')[0] # Assumes keyword is the file name without extension
+            st.video(video_file, format='video/mp4', start_time=0)
+            display_glossary_entity(k)
+        col_index += 1 # Increment column index to place the next video in the next column
+
+@st.cache_resource
+def display_images_and_wikipedia_summaries(num_columns=4):
+    image_files = [f for f in os.listdir('.') if f.endswith('.png')]
+    if not image_files:
+        st.write("No PNG images found in the current directory.")
+        return
+    image_files_sorted = sorted(image_files, key=lambda x: len(x.split('.')[0]))
+    cols = st.columns(num_columns) # Use specified num_columns for layout
+    col_index = 0 # Initialize column index for cycling through columns
+    for image_file in image_files_sorted:
+        with cols[col_index % num_columns]: # Cycle through columns based on num_columns
+            image = Image.open(image_file)
+            st.image(image, caption=image_file, use_column_width=True)
+            k = image_file.split('.')[0] # Assumes keyword is the file name without extension
+            display_glossary_entity(k)
+        col_index += 1 # Increment to move to the next column in the next iteration
+
 def main():
     st.markdown("##### GPT-4o Omni Model: Text, Audio, Image, & Video")
     option = st.selectbox("Select an option", ("Text", "Image", "Audio", "Video"))
@@ -192,5 +226,12 @@ def main():
             response = process_text2(text_input=prompt)
         st.session_state.messages.append({"role": "assistant", "content": response})
 
+    # Image and Video Galleries
+    num_columns_images=st.slider(key="num_columns_images", label="Choose Number of Image Columns", min_value=1, max_value=15, value=5)
+    display_images_and_wikipedia_summaries(num_columns_images) # Image Jump Grid
+
+    num_columns_video=st.slider(key="num_columns_video", label="Choose Number of Video Columns", min_value=1, max_value=15, value=5)
+    display_videos_and_links(num_columns_video) # Video Jump Grid
+
 if __name__ == "__main__":
     main()