Update app.py

app.py

@@ -31,9 +31,13 @@ class PDFTextExtractor:
                 image.save(img_buffer, format='PNG')
                 img_base64 = base64.b64encode(img_buffer.getvalue()).decode('utf-8')
                 
-                response = self.client.messages.create(
+                # Updated OpenAI API call using the correct format for newer SDK versions
+                response = self.client.chat.completions.create(
                     model="gpt-4o",
-                    system="""You are a doctor at a hospital. You can understand sloppy handwriting and convert it to readable text. Extract all the data from the form according to the markdown structure given below.
+                    messages=[
+                        {
+                            "role": "system",
+                            "content": """You are a doctor at a hospital. You can understand sloppy handwriting and convert it to readable text. Extract all the data from the form according to the markdown structure given below.
                             Follow this exact markdown structure:
                             # PATIENT ADMISSION FORM
                             ## DR.KAMAKSHI MEMORIAL HOSPITAL, PALLIKARANAI, CHENNAI.
@@ -119,9 +123,8 @@ class PDFTextExtractor:
                             
                             ---
                             *Form No: KMHIPF002V3*
-                            """,
-                    max_tokens=4096,
-                    messages=[
+                            """
+                        },
                         {
                             "role": "user",
                             "content": [
@@ -130,32 +133,32 @@ class PDFTextExtractor:
                                     "text": "Extract and format the Patient Admission Form from this image according to the specified markdown format. Even if the handwriting is sloppy, try to extract the text accurately. Preserve all form fields and checkboxes (as □)."
                                 },
                                 {
-                                    "type": "image",
-                                    "source": {
-                                        "type": "base64",
-                                        "media_type": "image/png",
-                                        "data": img_base64
+                                    "type": "image_url",
+                                    "image_url": {
+                                        "url": f"data:image/png;base64,{img_base64}"
                                     }
                                 }
                             ]
                         }
-                    ]
+                    ],
+                    max_tokens=4096
                 )
-                    
+                
+                # Updated response parsing for newer SDK versions
                 extracted_texts.append({
                     'page': i + 1,
-                    'text': response.content[0].text
+                    'text': response.choices[0].message.content
                 })
             
             return extracted_texts
                 
         except Exception as e:
             print(f"Error in text extraction: {str(e)}")
-            return None
+            return [{'page': 0, 'text': f"Error: {str(e)}"}]
 
 def extract_text(pdf_file):
     if OPENAI_API_KEY is None:
-        return "Error: OpenAI API key not found. Please set the ANTHROPIC_API_KEY environment variable."
+        return "Error: OpenAI API key not found. Please set the OPENAI_API_KEY environment variable."
 
     extractor = PDFTextExtractor(OPENAI_API_KEY)
     
@@ -163,6 +166,9 @@ def extract_text(pdf_file):
     extracted_texts = asyncio.run(extractor.extract_text_from_pdf(pdf_path))
     
     if extracted_texts:
+        if extracted_texts[0].get('text', '').startswith('Error:'):
+            return extracted_texts[0]['text']
+            
         output = ""
         for page in extracted_texts:
             output += f"\n\n=== Page {page['page']} ===\n\n"