Update app.py

app.py

@@ -52,16 +52,18 @@ def analyze_blood_test(file):
         inputs = tokenizer(extracted_text, return_tensors="pt", truncation=True, padding=True)
         outputs = model(**inputs)
 
-        # Generate labels and scores
+        # Step 3: Process logits and generate meaningful labels
         logits = outputs.logits
         predictions = logits.softmax(dim=-1)
 
         # Generate analysis report
         analysis_report = "🔍 Analysis Results:\n"
         for i, score in enumerate(predictions[0]):
-            analysis_report += f"- {tokenizer.decode([i])}: {score.item():.2f}\n"
+            token = tokenizer.decode([i]).strip()
+            if token not in ["[PAD]", "[unused1]"]:  # Filter out invalid tokens
+                analysis_report += f"- {token}: {score.item():.2f}\n"
 
-        # Step 3: Generate a PDF report
+        # Step 4: Generate a PDF report
         output_pdf = "analysis_report.pdf"
         create_pdf_report(f"Extracted Text:\n{extracted_text}\n\n{analysis_report}", output_pdf)