Update app.py

app.py

@@ -8,7 +8,6 @@ import mistune
 import pytz
 import math
 import requests
-import pandas as pd
 
 from datetime import datetime
 from openai import ChatCompletion
@@ -17,46 +16,22 @@ from bs4 import BeautifulSoup
 from collections import deque
 from audio_recorder_streamlit import audio_recorder
 
-openai.api_key = os.getenv('OPENAI_KEY')
-st.set_page_config(page_title="GPT Streamlit Document Reasoner",layout="wide")
-
-menu = ["txt", "htm", "md", "py", "csv", "xlsx"]
-choice = st.sidebar.selectbox("Output File Type:", menu)
-model_choice = st.sidebar.radio("Select Model:", ('gpt-3.5-turbo', 'gpt-3.5-turbo-0301'))
-
 def generate_filename(prompt, file_type):
     central = pytz.timezone('US/Central')
     safe_date_time = datetime.now(central).strftime("%m%d_%I%M")  
     safe_prompt = "".join(x for x in prompt if x.isalnum())[:45]
     return f"{safe_date_time}_{safe_prompt}.{file_type}"
 
-TEMPERATURE = st.sidebar.slider("Adjust Creativity:", min_value=0.1, max_value=1.0, value=0.5, step=0.1)
 def chat_with_model(prompt, document_section):
     model = model_choice
     conversation = [{'role': 'system', 'content': 'You are a helpful assistant.'}]
     conversation.append({'role': 'user', 'content': prompt})
-    conversation.append({'role': 'assistant', 'content': document_section})
-    response = openai.ChatCompletion.create(model=model, messages=conversation, temperature=TEMPERATURE)
+    if len(document_section)>0:
+        conversation.append({'role': 'assistant', 'content': document_section})
+    response = openai.ChatCompletion.create(model=model, messages=conversation)
+    #return response
     return response['choices'][0]['message']['content']
     
-def create_file(filename, prompt, response):
-    if filename.endswith(".txt"):
-        with open(filename, 'w') as file:
-            file.write(f"Prompt:\n{prompt}\nResponse:\n{response}")
-    elif filename.endswith(".htm"):
-        with open(filename, 'w') as file:
-            file.write(f"<h1>Prompt:</h1> <p>{prompt}</p> <h1>Response:</h1> <p>{response}</p>")
-    elif filename.endswith(".md"):
-        with open(filename, 'w') as file:
-            file.write(f"# Prompt:\n{prompt}\n# Response:\n{response}")
-    elif filename.endswith(".csv"):
-        response_df = pd.DataFrame({"Prompt": [prompt], "Response": [response]})
-        response_df.to_csv(filename, index=False)
-    elif filename.endswith(".xlsx"):
-        response_df = pd.DataFrame({"Prompt": [prompt], "Response": [response]})
-        response_df.to_excel(filename, index=False)
-    
-# Updated to auto process transcript to chatgpt in AI pipeline from Whisper to ChatGPT
 def transcribe_audio(openai_key, file_path, model):
     OPENAI_API_URL = "https://api.openai.com/v1/audio/transcriptions"
     headers = {
@@ -66,19 +41,18 @@ def transcribe_audio(openai_key, file_path, model):
         data = {'file': f}
         response = requests.post(OPENAI_API_URL, headers=headers, files=data, data={'model': model})
     if response.status_code == 200:
-        st.write('Reasoning with your transcription..')
-        transcript=response.json().get('text')
-        st.write(transcript)
-        gptResponse = chat_with_model(transcript, '') # send transcript to ChatGPT
-        filename = generate_filename(transcript, choice) # auto name file with date and prompt per output file type
-        create_file(filename, transcript, gptResponse) # write output file 
-        return gptResponse
+        st.write(response.json())
+        
+        response2 = chat_with_model(response.json().get('text'), '') # *************************************
+        st.write('Responses:')
+        #st.write(response)
+        st.write(response2)
+        return response.json().get('text')
     else:
         st.write(response.json())
         st.error("Error in API call.")
         return None
 
-# Updated to call direct from transcription to chat inference.
 def save_and_play_audio(audio_recorder):
     audio_bytes = audio_recorder()
     if audio_bytes:
@@ -87,20 +61,21 @@ def save_and_play_audio(audio_recorder):
             f.write(audio_bytes)
         st.audio(audio_bytes, format="audio/wav")
         return filename
-USEAUDIO=False
-if USEAUDIO:
-    if st.sidebar.checkbox('Use Audio Input'):
-        filename = save_and_play_audio(audio_recorder)
-        if filename is not None:
-            #if st.button("Transcribe"):
-            transcription = transcribe_audio(openai.api_key, filename, "whisper-1")
-            st.markdown('### Transcription:')
-            st.write(transcription)
-        
+    return None
 
+def create_file(filename, prompt, response):
+    if filename.endswith(".txt"):
+        with open(filename, 'w') as file:
+            file.write(f"{prompt}\n{response}")
+    elif filename.endswith(".htm"):
+        with open(filename, 'w') as file:
+            file.write(f"{prompt}   {response}")
+    elif filename.endswith(".md"):
+        with open(filename, 'w') as file:
+            file.write(f"{prompt}\n\n{response}")
+            
 def truncate_document(document, length):
     return document[:length]
-
 def divide_document(document, max_length):
     return [document[i:i+max_length] for i in range(0, len(document), max_length)]
 
@@ -112,8 +87,12 @@ def get_table_download_link(file_path):
     ext = os.path.splitext(file_name)[1]  # get the file extension
     if ext == '.txt':
         mime_type = 'text/plain'
-    elif ext == '.wav':
-        mime_type = 'audio/x-wav'
+    elif ext == '.py':
+        mime_type = 'text/plain'
+    elif ext == '.xlsx':
+        mime_type = 'text/plain'
+    elif ext == '.csv':
+        mime_type = 'text/plain'
     elif ext == '.htm':
         mime_type = 'text/html'
     elif ext == '.md':
@@ -148,24 +127,47 @@ def read_file_content(file,max_length):
         return content
     elif file.type == "text/plain":
         return file.getvalue().decode()
-    elif file.type == "text/csv":
-        df = pd.read_csv(file)
-        return df.to_string(index=False)
-    elif file.type == "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet":
-        df = pd.read_excel(file)
-        return df.to_string(index=False)
     else:
         return ""
 
+
+
+def chat_with_file_contents(prompt, file_content):
+    conversation = [{'role': 'system', 'content': 'You are a helpful assistant.'}]
+    conversation.append({'role': 'user', 'content': prompt})
+    if len(file_content)>0:
+        conversation.append({'role': 'assistant', 'content': file_content})
+    response = openai.ChatCompletion.create(model=model_choice, messages=conversation)
+    return response['choices'][0]['message']['content']
+        
+
+# Sidebar and global
+openai.api_key = os.getenv('OPENAI_KEY')
+st.set_page_config(page_title="GPT Streamlit Document Reasoner",layout="wide")
+menu = ["htm", "txt", "xlsx", "csv", "md", "py"]  #619
+choice = st.sidebar.selectbox("Output File Type:", menu)
+model_choice = st.sidebar.radio("Select Model:", ('gpt-3.5-turbo', 'gpt-3.5-turbo-0301'))
+
+# Audio, transcribe, GPT:
+filename = save_and_play_audio(audio_recorder)
+if filename is not None:
+    transcription = transcribe_audio(openai.api_key, filename, "whisper-1")
+    st.write(transcription)
+    gptOutput = chat_with_model(transcription, '') # *************************************
+    filename = generate_filename(transcription, choice)
+    create_file(filename, transcription, gptOutput)
+    st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)
+
+
 def main():
-    # max_length = 12000 - optimal for gpt35 turbo. 2x=24000 for gpt4.  8x=96000 for gpt4-32k.
-    max_length = st.sidebar.slider("File section length for large files", min_value=1000, max_value=128000, value=12000, step=1000)
-    
-    colprompt, colupload = st.columns([5,2])  # adjust the ratio as needed
-    with colprompt:
-        user_prompt = st.text_area("Enter prompts, instructions & questions:", '', height=150)
+    user_prompt = st.text_area("Enter prompts, instructions & questions:", '', height=100)
+
+    collength, colupload = st.columns([2,3])  # adjust the ratio as needed
+    with collength:
+        #max_length = 12000 - optimal for gpt35 turbo. 2x=24000 for gpt4.  8x=96000 for gpt4-32k.
+        max_length = st.slider("File section length for large files", min_value=1000, max_value=128000, value=12000, step=1000)
     with colupload:
-        uploaded_file = st.file_uploader("Add a file for context:", type=["xml", "json", "html", "htm", "txt"])
+        uploaded_file = st.file_uploader("Add a file for context:", type=["xml", "json", "xlsx","csv","html", "htm", "md", "txt"])
     
     document_sections = deque()
     document_responses = {}
@@ -188,7 +190,7 @@ def main():
             else:
                 if st.button(f"Chat about Section {i+1}"):
                     st.write('Reasoning with your inputs...')
-                    response = chat_with_model(user_prompt, section)
+                    response = chat_with_model(user_prompt, section) # *************************************
                     st.write('Response:')
                     st.write(response)
                     document_responses[i] = response
@@ -198,7 +200,7 @@ def main():
 
     if st.button('💬 Chat'):
         st.write('Reasoning with your inputs...')
-        response = chat_with_model(user_prompt, ''.join(list(document_sections)))
+        response = chat_with_model(user_prompt, ''.join(list(document_sections))) # *************************************
         st.write('Response:')
         st.write(response)
         
@@ -209,18 +211,48 @@ def main():
     all_files = glob.glob("*.*")
     all_files = [file for file in all_files if len(os.path.splitext(file)[0]) >= 20]  # exclude files with short names
     all_files.sort(key=lambda x: (os.path.splitext(x)[1], x), reverse=True)  # sort by file type and file name in descending order
-    
+
+    # sidebar of files
+    file_contents=''
+    next_action=''
     for file in all_files:
-        col1, col3 = st.sidebar.columns([5,1])  # adjust the ratio as needed
+        col1, col2, col3, col4, col5 = st.sidebar.columns([1,6,1,1,1])  # adjust the ratio as needed
         with col1:
-            try:
-                st.markdown(get_table_download_link(file), unsafe_allow_html=True)
-            except Exception as e:
-                st.error(f"Error occurred while processing file {file}: {str(e)}")
+            if st.button("🌐", key="md_"+file):  # md emoji button
+                with open(file, 'r') as f:
+                    file_contents = f.read()
+                    next_action='md'
+        with col2:
+            st.markdown(get_table_download_link(file), unsafe_allow_html=True)
         with col3:
+            if st.button("📂", key="open_"+file):  # open emoji button
+                with open(file, 'r') as f:
+                    file_contents = f.read()
+                    next_action='open'
+        with col4:
+            if st.button("🔍", key="read_"+file):  # search emoji button
+                with open(file, 'r') as f:
+                    file_contents = f.read()
+                    next_action='search'
+        with col5:
             if st.button("🗑", key="delete_"+file):
                 os.remove(file)
                 st.experimental_rerun()
-
+                
+    if len(file_contents) > 0:
+        if next_action=='open':
+            file_content_area = st.text_area("File Contents:", file_contents, height=500)
+        if next_action=='md':
+            st.markdown(file_contents)
+        if next_action=='search':
+            file_content_area = st.text_area("File Contents:", file_contents, height=500)
+            st.write('Reasoning with your inputs...')
+            response = chat_with_file_contents(user_prompt, file_contents)
+            st.write('Response:')
+            st.write(response)
+            filename = generate_filename(file_content_area, choice)
+            create_file(filename, file_content_area, response)
+            st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)
+                
 if __name__ == "__main__":
     main()