Update app.py

app.py

@@ -110,29 +110,23 @@ def seperate_image_text_from_pdf(pdf_url):
 
 def pdf_image_text_embedding_and_text_embedding(pages_info):
     try:
-    # List to store page embeddings
         page_embeddings = []
 
         # Iterate through each page
         for page in pages_info:
             # Extract text from the page
-            text = page["text"]
+            text = page.get("text", "")
+            images = page.get("images", [])
 
-            # Extract images from the page
-            images = page["images"]
-
-            # List to store image embeddings
             image_embeddings = []
-
-            # Iterate through each image
             for image in images:
-                # Get the image embedding
-                image_embedding = get_image_embedding(image)
-                extracted_text = extract_text(image)
-                # Append the image embedding to the list
-                image_embeddings.append({"image_embedding": image_embedding.tolist() ,"extracted_text":extracted_text})
-
-            # Get the text embedding
+                try:
+                    image_embedding = get_image_embedding(image)
+                    extracted_text = extract_text(image)
+                    image_embeddings.append({"image_embedding": image_embedding.tolist(), "extracted_text": extracted_text})
+                except Exception as image_error:
+                    print(f"Error processing image: {image_error}")
+                    # Log the error or handle it as needed
 
             # Store the page embeddings in a dictionary
             page_embedding = {
@@ -140,12 +134,11 @@ def pdf_image_text_embedding_and_text_embedding(pages_info):
                 "text": text,
             }
 
-            # Append the page embedding to the list
             page_embeddings.append(page_embedding)
 
         return page_embeddings
     except Exception as e:
-        print("An error occurred:", e)
+        print(f"An error occurred: {e}")
         return "Error"