Update utils.py

utils.py

@@ -42,32 +42,32 @@ def process_local_pdf(pdf_bytes: bytes):
         prompt: The prompt template to use (should contain {page_num} if needed)
         api_key: Your Google AI Studio API key
     """
-    # Configure Gemini
-prompt = """Please analyze the provided images of the real estate document set and perform the following actions:
-
-1. **Identify Parties**: Determine and list all present parties involved in the transaction. Always identify and include **Seller 1** and **Buyer 1** if they are present in the documents. Additionally, include **Seller 2** and **Buyer 2** only if they are explicitly mentioned.
-
-2. **Identify Missing Items**: For each identified party, including at minimum **Seller 1** and **Buyer 1**, check all pages for any missing signatures or initials. Only check for **Seller 2** or **Buyer 2** if they were identified in step 1.
-
-3. **Identify Checked Boxes**: Locate and list all checkboxes that have been marked or checked.
-
-4. **Generate Secondary Questions**: For checkboxes that indicate significant waivers (e.g., home warranty, inspection rights, lead paint assessment), specific conditions (e.g., cash sale, contingency status), potential conflicts, or reference other documents, formulate a relevant 'Secondary Question' designed to prompt confirmation or clarification from the user/parties involved.
-
-5. **Check for Required Paperwork**: Based only on the checkboxes identified in step 3 that explicitly state or strongly imply a specific addendum or disclosure document should be attached (e.g., "Lead Based Paint Disclosure Addendum attached", "See Counter Offer Addendum", "Seller's Disclosure...Addendum attached", "Retainer Addendum attached", etc.), check if a document matching that description appears to be present within the provided image set. Note whether this implied paperwork is 'Found', 'Missing', or 'Potentially Missing/Ambiguous'.
-
-6. **Identify Conflicts**: Specifically look for and note any directly contradictory information or conflicting checked boxes (like the conflicting inspection clauses found previously).
-
-7. **Provide Location**: For every identified item (missing signature/initial, checked box, required paperwork status, party identification, conflict), specify the approximate line number(s) or clear location on the page (e.g., Bottom Right Initials, Seller Signature Block).
-
-8. **Format Output**: Present all findings in CSV format with the following columns:
-   - **Category**: (e.g., Parties, Missing Item, Checked Box, Required Paperwork, Conflict)
-   - **Location**: (e.g., Sale Contract (Image 8 Pg 1))
-   - **Line Item(s)**: (e.g., 4)
-   - **Item Type**: (e.g., Seller 1, Buyer 1, Seller Signature, Seller Initials)
-   - **Status**: (e.g., Identified, Missing, Checked, Found, Potentially Missing, Conflict)
-   - **Details**: (e.g., "Seller signature line (top line) is empty.", "Two initial boxes for Seller (approx line 106-107 area) are empty.")
-   - **Secondary Question** (if applicable): (e.g., "Is the Buyer aware they are waiving the home warranty?", "Has the Buyer received and reviewed the Seller's Disclosure?")
-"""
+        # Configure Gemini
+    prompt = """Please analyze the provided images of the real estate document set and perform the following actions:
+    
+    1. **Identify Parties**: Determine and list all present parties involved in the transaction. Always identify and include **Seller 1** and **Buyer 1** if they are present in the documents. Additionally, include **Seller 2** and **Buyer 2** only if they are explicitly mentioned.
+    
+    2. **Identify Missing Items**: For each identified party, including at minimum **Seller 1** and **Buyer 1**, check all pages for any missing signatures or initials. Only check for **Seller 2** or **Buyer 2** if they were identified in step 1.
+    
+    3. **Identify Checked Boxes**: Locate and list all checkboxes that have been marked or checked.
+    
+    4. **Generate Secondary Questions**: For checkboxes that indicate significant waivers (e.g., home warranty, inspection rights, lead paint assessment), specific conditions (e.g., cash sale, contingency status), potential conflicts, or reference other documents, formulate a relevant 'Secondary Question' designed to prompt confirmation or clarification from the user/parties involved.
+    
+    5. **Check for Required Paperwork**: Based only on the checkboxes identified in step 3 that explicitly state or strongly imply a specific addendum or disclosure document should be attached (e.g., "Lead Based Paint Disclosure Addendum attached", "See Counter Offer Addendum", "Seller's Disclosure...Addendum attached", "Retainer Addendum attached", etc.), check if a document matching that description appears to be present within the provided image set. Note whether this implied paperwork is 'Found', 'Missing', or 'Potentially Missing/Ambiguous'.
+    
+    6. **Identify Conflicts**: Specifically look for and note any directly contradictory information or conflicting checked boxes (like the conflicting inspection clauses found previously).
+    
+    7. **Provide Location**: For every identified item (missing signature/initial, checked box, required paperwork status, party identification, conflict), specify the approximate line number(s) or clear location on the page (e.g., Bottom Right Initials, Seller Signature Block).
+    
+    8. **Format Output**: Present all findings in CSV format with the following columns:
+       - **Category**: (e.g., Parties, Missing Item, Checked Box, Required Paperwork, Conflict)
+       - **Location**: (e.g., Sale Contract (Image 8 Pg 1))
+       - **Line Item(s)**: (e.g., 4)
+       - **Item Type**: (e.g., Seller 1, Buyer 1, Seller Signature, Seller Initials)
+       - **Status**: (e.g., Identified, Missing, Checked, Found, Potentially Missing, Conflict)
+       - **Details**: (e.g., "Seller signature line (top line) is empty.", "Two initial boxes for Seller (approx line 106-107 area) are empty.")
+       - **Secondary Question** (if applicable): (e.g., "Is the Buyer aware they are waiving the home warranty?", "Has the Buyer received and reviewed the Seller's Disclosure?")
+    """
 
     # Convert to images
     images = pdf_to_images(pdf_bytes)