Upload app.py

app.py

@@ -34,35 +34,42 @@ def load_prompt(filename):
         return f"Error loading prompt: {e}"
 
 def process_pdf_and_save_job_desc(pdf_file, job_description):
-    if not pdf_file:
-        return None, "No file provided"
-
-    doc = fitz.open(stream=pdf_file, filetype="pdf")
-
-    # Store results in a list and process all pages
-    json_data = []
-    images = []  # List to hold images of each page
-    for page_num in range(len(doc)):
-        page = doc.load_page(page_num)
-        pix = page.get_pixmap()
-        img_bytes = pix.tobytes("png")
-        image = Image.open(io.BytesIO(img_bytes))
-        images.append(image)
-
-        # ... Your image processing with the genai model
-        prompt = load_prompt("prompts/resume_parsing_prompt.txt")
-        response = model_vision.generate_content([prompt, image])
-        json_data.append(response.text) 
-
-    doc.close()
-
-    # Store data appropriately (consider a list of JSON objects, or a structured dict)
-    with open(INTERMEDIATE_JSON_PATH, "w") as json_file:
-        json.dump(json_data, json_file)
-    with open(INTERMEDIATE_JOB_DESC_PATH, "w") as file:
-        file.write(job_description)
-
-    return images, json_data  # Return the list of images
+    try:
+        
+        if not pdf_file:
+            return None, "No file provided"
+
+        doc = fitz.open(stream=pdf_file, filetype="pdf")
+
+        # Store results in a list and process all pages
+        json_data = []
+        images = []  # List to hold images of each page
+        for page_num in range(len(doc)):
+            page = doc.load_page(page_num)
+            pix = page.get_pixmap()
+            img_bytes = pix.tobytes("png")
+            image = Image.open(io.BytesIO(img_bytes))
+            images.append(image)
+
+            # ... Your image processing with the genai model
+            prompt = load_prompt("prompts/resume_parsing_prompt.txt")
+            response = model_vision.generate_content([prompt, image])
+            json_data.append(response.text) 
+
+        doc.close()
+
+        # Store data appropriately (consider a list of JSON objects, or a structured dict)
+        with open(INTERMEDIATE_JSON_PATH, "w") as json_file:
+            json.dump(json_data, json_file)
+        with open(INTERMEDIATE_JOB_DESC_PATH, "w") as file:
+            file.write(job_description)
+
+        return images, json_data  # Return the list of images
+    
+    except fitz.FitzError as e:
+        return None, f"PDF processing error: {e}"
+    except Exception as e:
+        return None, f"An unexpected error occurred: {e}"
 
 def display_json():
     try: