Optimized prompt for brevity and clarity

deck_creation.py

@@ -15,28 +15,31 @@ if not API_KEY:
 
 openai.api_key = API_KEY
 
-# Given prompt template
 PROMPT_TEMPLATE = """
-Please come up with a title for the deck and a set of 10 index cards for memorization, 
-including a title, front, and back for each card. The index cards should completely 
-capture the main points and themes of the text. In addition, they should contain any 
-numbers or data that humans might find difficult to remember. The goal of the index 
-card set is that one who memorizes it can provide a summary of the text to someone 
-else, conveying the main points and themes.
+Please craft a title for the deck along with a set of index cards that succinctly capture the main ideas and themes of the provided text. Ensure the following:
 
-You will provide the deck title, and the titles, questions, and answers for each card 
-in a structured format as follows:
+1. Every card should have a title, a question on the front, and an answer on the back.
+2. Each answer must contain at least one concrete fact not evident from its question.
+3. Include any numbers, data, or details that may be challenging to remember.
+4. The aim is for a person who learns this set to effectively convey the text's main themes and specifics to another individual.
+5. You should craft at least one index card for every 3-5 sentences of content, depending on how much information is packed in the content.
+6. Each index card should focus on answering a single question
+7. Each index card answer shall be no longer than 3 sentences.
+
+Structure your response as:
 ```
-Deck Title: Title of the Deck
+Deck Title: [Title of the Deck]
 Cards:
-- Title: Card Title 1
-  Front: What is the capital of New York?
-  Back: Albany
-- Title: Card Title 2
-  Front: Where in the world is Carmen San Diego?
-  Back: Nobody knows
+- Title: [Card Title 1]
+  Front: [Question 1]
+  Back: [Answer 1]
+- Title: [Card Title 2]
+  Front: [Question 2]
+  Back: [Answer 2]
+... and so on
 ```
 
+Content for reference:
 {content}
 """
 

image_processing.py

@@ -44,7 +44,11 @@ def convert_image(image_path):
 
 def ocr_image(image_path):
     logging.info(f"OCR'ing {image_path}...")
-    text_filename = os.path.basename(image_path).replace(".jpg", ".txt")
+    
+    base_name = os.path.basename(image_path)
+    root_name, _ = os.path.splitext(base_name)
+    text_filename = f"{root_name}.txt"
+    
     text_path = os.path.join(CONVERTED_DIR, text_filename)
     cmd = ["tesseract", image_path, text_path.replace(".txt", "")]
     try: