added extra time staps to chapter content

app.py

@@ -19,7 +19,6 @@ from typing import Optional, Union, Dict, Any
 import os
 import requests
 import os
-from PyPDF2 import PdfReader
 from scripts.transcriber import transcribe_media,group_words_into_sentences  # Import the transcribe_media function
 from scripts.generate_summary import general_summary,custom_summary
 # Load environment variables
@@ -170,4 +169,6 @@ async def startup_event():
 
 if __name__ == "__main__":
     import uvicorn
-    uvicorn.run("app:app", host="0.0.0.0", port=3000, reload=True)
+    uvicorn.run("app:app", host="0.0.0.0", port=5056, reload=True)
+    
+    

src/prompt.py

@@ -25,7 +25,6 @@ At the end of each section, include a field named "minutes_total" which represen
 - The JSON output must be properly formatted and valid.
 - Do not include any markdown or code block formatting markers (such as ```json) in your output.
 - Ensure that for each sentence you generate, every word in that sentence is assigned the same timestamp—the start timestamp of that sentence.
-
 **Example Output JSON:**
 
 {
@@ -38,6 +37,11 @@ At the end of each section, include a field named "minutes_total" which represen
       {
         "chapter": "Project Overview",
         "time_stamp": {"start": 5.12, "end": 5.68},
+        "content": [
+          {"text":"- overview of the project's objectives.","original_transcript_start":3.4,"original_transcript_end":5.7},
+          {"text":"- It outlines the key milestones achieved so far.", "original_transcript_start":6.7, "original_transcript_end":10.5},
+          {"text":"- main challenges faced during the project.", "original_transcript_start":10.8, "original_transcript_end":11.2}
+        ],
         "words_time_stamp": [
           {"word": "Project", "timestamp": 5.12},
           {"word": "Overview", "timestamp": 5.12}
@@ -46,13 +50,17 @@ At the end of each section, include a field named "minutes_total" which represen
       {
         "chapter": "Budget Review",
         "time_stamp": {"start": 10.50, "end": 11.20},
+        "content": [
+          {"text":"- review of the current budget allocations.","original_transcript_start":10.5,"original_transcript_end":11.0},
+          {"text":"- discussion on potential cost-saving measures.", "original_transcript_start":11.1, "original_transcript_end":12.0},
+          {"text":"- approval of the budget for the next quarter.", "original_transcript_start":12.1, "original_transcript_end":13.0}
+        ],
         "words_time_stamp": [
           {"word": "Budget", "timestamp": 10.50},
           {"word": "Review", "timestamp": 10.50}
         ]
       }
     ]
-  },
   "Outcomes": {
     "minutes_total": 3,
     "content": [
@@ -94,7 +102,7 @@ At the end of each section, include a field named "minutes_total" which represen
     ]
   }
 }
-
+NOTE: The content under each chapter provides a detailed bulleted explanation of the chapter. It includes "original_transcript_start" and "original_transcript_end," which indicate the timestamps for each bulleted point, referencing where to find it in the original transcript.
 Remember, every word in each sentence must have a single timestamp equal to the start timestamp of that sentence. Your output must strictly adhere to the provided structure, and the "minutes_total" for each section must be correctly calculated based on the start time of the first sentence and the end time of the last sentence, expressed as a decimal if necessary.
 NOTE : start and end time are in seconds , so take that into considerations when calculating the total time in mins
 """