MrSimple01 commited on
Commit
7021e3d
·
verified ·
1 Parent(s): fadb17a

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +17 -6
app.py CHANGED
@@ -54,22 +54,30 @@ def analyze_segment_with_gemini(segment_text):
54
 
55
  prompt = f"""
56
  Analyze the following text and identify distinct segments within it and do text segmentation:
57
- 1. Segments should be STRICTLY max=10
58
  2. For each segment/topic you identify:
59
  - Provide a SPECIFIC and UNIQUE topic name (3-5 words) that clearly differentiates it from other segments
60
  - List 3-5 key concepts discussed in that segment (be precise and avoid repetition between segments)
61
  - Write a brief summary of that segment (3-5 sentences)
62
- - Create 5 quiz questions based DIRECTLY on the content in that segment only
63
-
 
64
  For each quiz question:
65
  - Create one correct answer that comes DIRECTLY from the text
66
  - Create two plausible but incorrect answers
67
  - IMPORTANT: Ensure all answer options have similar length (± 3 words)
68
  - Ensure the correct answer is clearly indicated with a ✓ symbol
69
-
 
 
 
 
 
 
 
70
  Text:
71
  {segment_text}
72
-
73
  Format your response as JSON with the following structure:
74
  {{
75
  "segments": [
@@ -99,8 +107,11 @@ def analyze_segment_with_gemini(segment_text):
99
  }}
100
  ]
101
  }}
102
-
103
  IMPORTANT: Each segment must have a DISTINCT topic name that clearly differentiates it from others.
 
 
 
104
  """
105
 
106
  response = llm.invoke(prompt)
 
54
 
55
  prompt = f"""
56
  Analyze the following text and identify distinct segments within it and do text segmentation:
57
+ 1. Segments should be STRICTLY max=15
58
  2. For each segment/topic you identify:
59
  - Provide a SPECIFIC and UNIQUE topic name (3-5 words) that clearly differentiates it from other segments
60
  - List 3-5 key concepts discussed in that segment (be precise and avoid repetition between segments)
61
  - Write a brief summary of that segment (3-5 sentences)
62
+ - Create 5 high-quality, meaningful quiz questions based DIRECTLY on the content in that segment only
63
+ - Questions and answers should be only from the content of the segment
64
+
65
  For each quiz question:
66
  - Create one correct answer that comes DIRECTLY from the text
67
  - Create two plausible but incorrect answers
68
  - IMPORTANT: Ensure all answer options have similar length (± 3 words)
69
  - Ensure the correct answer is clearly indicated with a ✓ symbol
70
+ - Questions should **require actual understanding**, NOT just basic fact recall.
71
+ - Questions Are **non-trivial**, encourage deeper thinking, and **avoid surface-level facts**.
72
+ - Are **directly based on the segment's content** (not inferred from the summary).
73
+ - Do **not include questions about document structure** (e.g., title, number of paragraphs).
74
+ - Do **not generate overly generic or obvious questions** (e.g., "What is mentioned in the text?").
75
+ - Focus on **core ideas, logical reasoning, and conceptual understanding**.
76
+
77
+
78
  Text:
79
  {segment_text}
80
+
81
  Format your response as JSON with the following structure:
82
  {{
83
  "segments": [
 
107
  }}
108
  ]
109
  }}
110
+
111
  IMPORTANT: Each segment must have a DISTINCT topic name that clearly differentiates it from others.
112
+ - **Do NOT repeat** key concepts across multiple segments unless absolutely necessary.
113
+ - **Ensure the quiz questions challenge the reader** and **are not easily guessable**.
114
+
115
  """
116
 
117
  response = llm.invoke(prompt)