awacke1 commited on
Commit
36e0d75
1 Parent(s): ac37df8

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -24
app.py CHANGED
@@ -1800,18 +1800,19 @@ if AddAFileForContext:
1800
 
1801
 
1802
  def main():
1803
- #st.markdown("### OpenAI GPT-4o Model")
1804
  st.markdown("##### GPT-4o Omni Model: Text, Audio, Image, & Video")
1805
  option = st.selectbox("Select an option", ("Text", "Image", "Audio", "Video"))
1806
  if option == "Text":
1807
  text_input = st.text_input("Enter your text:")
1808
  if (text_input > ''):
1809
  textResponse = process_text(text_input)
 
1810
  elif option == "Image":
1811
  text = "Help me understand what is in this picture and list ten facts as markdown outline with appropriate emojis that describes what you see."
1812
  text_input = st.text_input(label="Enter text prompt to use with Image context.", value=text)
1813
  image_input = st.file_uploader("Upload an image", type=["png"])
1814
- image_response = process_image(image_input, text_input)
 
1815
 
1816
  elif option == "Audio":
1817
  text = "You are generating a transcript summary. Create a summary of the provided transcription. Respond in Markdown."
@@ -1824,7 +1825,6 @@ def main():
1824
  process_audio(audio_input, text_input)
1825
 
1826
  elif option == "Audio old":
1827
- #text = "Transcribe and answer questions as a helpful audio music and speech assistant. "
1828
  text = "You are generating a transcript summary. Create a summary of the provided transcription. Respond in Markdown."
1829
  text_input = st.text_input(label="Enter text prompt to use with Audio context.", value=text)
1830
 
@@ -1851,7 +1851,6 @@ def main():
1851
  video_input = st.file_uploader("Upload a video file", type=["mp4"])
1852
  process_audio_and_video(video_input)
1853
 
1854
-
1855
  # Enter the GPT-4o omni model in streamlit chatbot
1856
  current_messages=[]
1857
  for message in st.session_state.messages:
@@ -1859,8 +1858,6 @@ for message in st.session_state.messages:
1859
  current_messages.append(message)
1860
  st.markdown(message["content"])
1861
 
1862
-
1863
-
1864
  # 🎵 Wav Audio files - Transcription History in Wav
1865
  audio_files = glob.glob("*.wav")
1866
  audio_files = [file for file in audio_files if len(os.path.splitext(file)[0]) >= 10] # exclude files with short names
@@ -1881,9 +1878,6 @@ video_files_mp3 = glob.glob("*.mp3")
1881
  video_files_mp3 = [file for file in video_files_mp3 if len(os.path.splitext(file)[0]) >= 10] # exclude files with short names
1882
  video_files_mp3.sort(key=lambda x: (os.path.splitext(x)[1], x), reverse=True) # sort by file type and file name in descending order
1883
 
1884
-
1885
-
1886
-
1887
  main()
1888
 
1889
  # Delete All button for each file type
@@ -1962,10 +1956,6 @@ for file in video_files_mp3:
1962
  os.remove(file)
1963
  st.rerun()
1964
 
1965
-
1966
-
1967
-
1968
-
1969
  # ChatBot Entry
1970
  if prompt := st.chat_input("GPT-4o Multimodal ChatBot - What can I help you with?"):
1971
  st.session_state.messages.append({"role": "user", "content": prompt})
@@ -1980,10 +1970,6 @@ if prompt := st.chat_input("GPT-4o Multimodal ChatBot - What can I help you with
1980
  response = process_text2(text_input=prompt)
1981
  st.session_state.messages.append({"role": "assistant", "content": response})
1982
 
1983
-
1984
-
1985
-
1986
-
1987
  # Image and Video Galleries
1988
  num_columns_images=st.slider(key="num_columns_images", label="Choose Number of Image Columns", min_value=1, max_value=15, value=3)
1989
  display_images_and_wikipedia_summaries(num_columns_images) # Image Jump Grid
@@ -1991,7 +1977,6 @@ display_images_and_wikipedia_summaries(num_columns_images) # Image Jump Grid
1991
  num_columns_video=st.slider(key="num_columns_video", label="Choose Number of Video Columns", min_value=1, max_value=15, value=3)
1992
  display_videos_and_links(num_columns_video) # Video Jump Grid
1993
 
1994
-
1995
  # Optional UI's
1996
  showExtendedTextInterface=False
1997
  if showExtendedTextInterface:
@@ -1999,9 +1984,3 @@ if showExtendedTextInterface:
1999
  num_columns_text=st.slider(key="num_columns_text", label="Choose Number of Text Columns", min_value=1, max_value=15, value=4)
2000
  display_buttons_with_scores(num_columns_text) # Feedback Jump Grid
2001
  st.markdown(personality_factors)
2002
-
2003
-
2004
-
2005
-
2006
- #if __name__ == "__main__":
2007
-
 
1800
 
1801
 
1802
  def main():
 
1803
  st.markdown("##### GPT-4o Omni Model: Text, Audio, Image, & Video")
1804
  option = st.selectbox("Select an option", ("Text", "Image", "Audio", "Video"))
1805
  if option == "Text":
1806
  text_input = st.text_input("Enter your text:")
1807
  if (text_input > ''):
1808
  textResponse = process_text(text_input)
1809
+
1810
  elif option == "Image":
1811
  text = "Help me understand what is in this picture and list ten facts as markdown outline with appropriate emojis that describes what you see."
1812
  text_input = st.text_input(label="Enter text prompt to use with Image context.", value=text)
1813
  image_input = st.file_uploader("Upload an image", type=["png"])
1814
+ if (image_input is not None):
1815
+ image_response = process_image(image_input, text_input)
1816
 
1817
  elif option == "Audio":
1818
  text = "You are generating a transcript summary. Create a summary of the provided transcription. Respond in Markdown."
 
1825
  process_audio(audio_input, text_input)
1826
 
1827
  elif option == "Audio old":
 
1828
  text = "You are generating a transcript summary. Create a summary of the provided transcription. Respond in Markdown."
1829
  text_input = st.text_input(label="Enter text prompt to use with Audio context.", value=text)
1830
 
 
1851
  video_input = st.file_uploader("Upload a video file", type=["mp4"])
1852
  process_audio_and_video(video_input)
1853
 
 
1854
  # Enter the GPT-4o omni model in streamlit chatbot
1855
  current_messages=[]
1856
  for message in st.session_state.messages:
 
1858
  current_messages.append(message)
1859
  st.markdown(message["content"])
1860
 
 
 
1861
  # 🎵 Wav Audio files - Transcription History in Wav
1862
  audio_files = glob.glob("*.wav")
1863
  audio_files = [file for file in audio_files if len(os.path.splitext(file)[0]) >= 10] # exclude files with short names
 
1878
  video_files_mp3 = [file for file in video_files_mp3 if len(os.path.splitext(file)[0]) >= 10] # exclude files with short names
1879
  video_files_mp3.sort(key=lambda x: (os.path.splitext(x)[1], x), reverse=True) # sort by file type and file name in descending order
1880
 
 
 
 
1881
  main()
1882
 
1883
  # Delete All button for each file type
 
1956
  os.remove(file)
1957
  st.rerun()
1958
 
 
 
 
 
1959
  # ChatBot Entry
1960
  if prompt := st.chat_input("GPT-4o Multimodal ChatBot - What can I help you with?"):
1961
  st.session_state.messages.append({"role": "user", "content": prompt})
 
1970
  response = process_text2(text_input=prompt)
1971
  st.session_state.messages.append({"role": "assistant", "content": response})
1972
 
 
 
 
 
1973
  # Image and Video Galleries
1974
  num_columns_images=st.slider(key="num_columns_images", label="Choose Number of Image Columns", min_value=1, max_value=15, value=3)
1975
  display_images_and_wikipedia_summaries(num_columns_images) # Image Jump Grid
 
1977
  num_columns_video=st.slider(key="num_columns_video", label="Choose Number of Video Columns", min_value=1, max_value=15, value=3)
1978
  display_videos_and_links(num_columns_video) # Video Jump Grid
1979
 
 
1980
  # Optional UI's
1981
  showExtendedTextInterface=False
1982
  if showExtendedTextInterface:
 
1984
  num_columns_text=st.slider(key="num_columns_text", label="Choose Number of Text Columns", min_value=1, max_value=15, value=4)
1985
  display_buttons_with_scores(num_columns_text) # Feedback Jump Grid
1986
  st.markdown(personality_factors)