Update app.py

app.py

@@ -114,7 +114,7 @@ def break_up_file(tokens, chunk_size, overlap_size):
         yield from break_up_file(tokens[chunk_size-overlap_size:], chunk_size, overlap_size)
 
 
-def break_up_file_to_chunks(filename, chunk_size=2000, overlap_size=100):
+def break_up_file_to_chunks(filename, chunk_size=4000, overlap_size=100):
     with open(filename, 'r') as f:
         text = f.read()
     tokens = word_tokenize(text)
@@ -127,24 +127,6 @@ def convert_to_prompt_text(tokenized_text):
     return prompt_text
 
 
-def markdown_to_docx(md_text, output_file):
-    # Convert the Markdown text to HTML
-    html_text = markdown.markdown(md_text)
-
-    # Create a new Document object
-    doc = Document()
-
-    # Parse the HTML and add its content to the .docx document
-    for p in html_text.split('</p>'):
-        if '<p>' in p:
-            clean_p = p.replace('<p>', '').strip()
-            if clean_p:
-                doc.add_paragraph(clean_p)
-
-    # Save the document to the specified file
-    doc.save(output_file)
-
-
 @backoff.on_exception(backoff.expo, openai.error.RateLimitError)
 @backoff.on_exception(backoff.expo, openai.error.APIConnectionError)
 def summarize_meeting(filepath):
@@ -161,12 +143,12 @@ def summarize_meeting(filepath):
 
         messages = [
             {"role": "system", "content": "Summarize this meeting transcript in the same language as the user's input."}]
-        messages.append({"role": "user", "content": "Summarize this meeting transcript in the same language as the meeting transcript. Meeting Transcript:" + prompt_request})
+        messages.append({"role": "user", "content": prompt_request})
 
         response = openai.ChatCompletion.create(
-            model="gpt-3.5-turbo",
+            model="gpt-4",
             messages=messages,
-            temperature=.5,
+            temperature=.4,
             top_p=1,
             frequency_penalty=0,
             presence_penalty=0
@@ -177,30 +159,20 @@ def summarize_meeting(filepath):
 
     # Consolidate these meeting summaries.
     prompt_request = str(prompt_response)
-    tokens_PR = word_tokenize(prompt_request)
-    count_tokens_PR =  len(tokens_PR)
 
-    if count_tokens_PR <2000:
-        # Summarize the text of the meeting transcripts.
-        messages = [{"role": "system", "content": "Consolidate, and summarize the text of the meeting transcripts. The output format should be markdown in the same language as the user's input. Start with a brief summary of the meeting, continue with bullets outlining the most important points of discussion. Finally, provide a table to show the list of action items with 3 columns: Action, Assigned Person, Due Date."}]
-        messages.append({"role": "user", "content": "Consolidate, and summarize the text of the meeting transcripts. The output format should be markdown in the same language as the meeting summary. Start with a brief summary of the meeting, continue with bullets outlining the most important points of discussion. Finally, provide a table to show the list of action items with 3 columns: Action, Assigned Person, Due Date. Meeting summary:"+ prompt_request})
-        response = openai.ChatCompletion.create(
-            model="gpt-3.5-turbo",
-            messages=messages,
-            temperature=.3,
-            top_p=1,
-            frequency_penalty=0,
-            presence_penalty=0
-        )
-    
-        summary_text = response["choices"][0]["message"]['content'].strip()
-    #outfilepath = "Resumen-Minuta-" + datetime.now().strftime("%d-%m-%Y-%H-%M") + ".docx"
-    # Convert the summary to a .docx file with the name "Resumen-Minuta-<download-date>.docx"
-    #markdown_to_docx(
-    #    summary_text, outfilepath)
-    else: 
-        summary_text = "Error: Contacta al administrador de Minuteevo."
-    
+    # Summarize the text of the meeting transcripts.
+    messages = [{"role": "system", "content": "Consolidate, and summarize the text of the meeting transcripts. The output format should be markdown in the same language as the user's input. Start with a brief summary of the meeting, continue with bullets outlining the most important points of discussion. Finally, provide a table to show the list of action items with 3 columns: Action, Assigned Person, Due Date."}]
+    messages.append({"role": "user", "content":  prompt_request})
+    response = openai.ChatCompletion.create(
+        model="gpt-4",
+        messages=messages,
+        temperature=.3,
+        top_p=1,
+        frequency_penalty=0,
+        presence_penalty=0
+    )
+
+    summary_text = response["choices"][0]["message"]['content'].strip()
 
     return summary_text