Update app.py

app.py

@@ -99,7 +99,7 @@ def extract_invoice_data(file_data, content_type, json_schema):
     Extracts data from a PDF (converted to images) or an image.
     Only PDFs with 1 or 2 pages are allowed.
     """
-    system_prompt = "You are an expert in document data extraction."
+    system_prompt = "You are an expert in document data extraction. Extract relevant fields from the document and return structured JSON based on the provided schema."
     base64_images = []
 
     if content_type == "application/pdf":
@@ -107,13 +107,13 @@ def extract_invoice_data(file_data, content_type, json_schema):
             images = convert_from_bytes(file_data)  # Convert PDF to images
 
             if len(images) > 2:
-                raise ValueError("PDF contains more than 2 pages.")
+                raise ValueError("PDF contains more than 2 pages. Only PDFs with 1 or 2 pages are supported.")
 
-            for img in images[:2]:
+            for img in images[:2]:  # Convert up to 2 pages
                 img_byte_arr = io.BytesIO()
-                img.save(img_byte_arr, format="PNG", dpi=(300, 300))
+                img.save(img_byte_arr, format="PNG")
                 base64_encoded = base64.b64encode(img_byte_arr.getvalue()).decode('utf-8')
-                base64_images.append(f"data:image/png;base64,{base64_encoded}")
+                base64_images.append(f"data:{content_type};base64,{base64_encoded}")
 
         except Exception as e:
             logger.error(f"Error converting PDF to image: {e}")