Update update_docx_with_pdf.py

update_docx_with_pdf.py

@@ -9,15 +9,12 @@ def update_json_with_pdf(word_json_file, pdf_txt_file, output_file):
     with open(pdf_txt_file, "r", encoding="utf-8") as f:
         pdf_txt = f.read()
 
-
-# --- Build prompt ---
-user_prompt = f"""
+    # --- Build prompt ---
+    user_prompt = f"""
 Here is a JSON template. It contains only the fields that need updating:
 {word_json}
-
 Here is the extracted text from a PDF:
 {pdf_txt}
-
 Instructions:
 - ONLY update the fields present in the JSON template, using information from the PDF text.
 - DO NOT add any extra fields, and do not change the JSON structure.
@@ -25,7 +22,7 @@ Instructions:
 - Make sure the JSON is valid and ready to use.
 """
 
- # --- Call OpenAI API ---
+    # --- Call OpenAI API ---
     api_key = os.environ.get("OPENAI_API_KEY")
     if not api_key:
         raise RuntimeError("OPENAI_API_KEY not found in environment variables!")
@@ -40,18 +37,18 @@ Instructions:
         temperature=0
     )
 
-updated_json_str = response.choices[0].message.content.strip()
-
-# --- Try to parse as JSON ---
-try:
-    parsed = json.loads(updated_json_str)
-    with open(OUTPUT_FILE, "w", encoding="utf-8") as f:
-        json.dump(parsed, f, indent=2, ensure_ascii=False)
-    print("✅ JSON updated and saved to", OUTPUT_FILE)
-except Exception as e:
-    print("⚠️ Model did not return valid JSON. Raw output below:\n")
-    print(updated_json_str)
-    print("\n❌ Failed to parse updated JSON:", e)
+    updated_json_str = response.choices[0].message.content.strip()
+
+    # --- Try to parse as JSON ---
+    try:
+        parsed = json.loads(updated_json_str)
+        with open(output_file, "w", encoding="utf-8") as f:
+            json.dump(parsed, f, indent=2, ensure_ascii=False)
+        print("✅ JSON updated and saved to", output_file)
+    except Exception as e:
+        print("⚠️ Model did not return valid JSON. Raw output below:\n")
+        print(updated_json_str)
+        print("\n❌ Failed to parse updated JSON:", e)
 
 if __name__ == "__main__":
     import sys