LE prompt with reasoning

app.py

@@ -494,7 +494,7 @@ CRITICAL: When analyzing timestamps, you must verify that in the duration specif
 in the transcript: {transcript}
 
 Your job is to generate the thinking about the short social media clips for each speaker where they discuss. Think step by step and return a JSON at the end of the thinking.
-Generate the thinking for atleast 2 clips for each speaker.
+You can skip a speaker if they don't have enough content to generate the clips.
 Return Format:
 - Name of the Speaker
 - Detailed Step by Step Thinking for each speaker from thier content and the topic they are talking about
@@ -502,7 +502,7 @@ After you have completed the thinking, give me a JSON of the thinking.
 ```json
 [
     {{
-        "Speaker 0": [
+        "Speaker Name1": [
             {{
                 "Topic Title": "...",
                 "Starting Sentence of that speaker": "...",
@@ -516,7 +516,7 @@ After you have completed the thinking, give me a JSON of the thinking.
         ]
     }},
     {{
-        "Speaker 1": [
+        "Speaker Name2": [
             {{
                 "Topic Title": "....",
                 "Starting Sentence of that speaker": ".....",