Update app.py

app.py

@@ -1,65 +1,64 @@
 import gradio as gr
 from transformers import pipeline
 from PIL import Image
-import pytesseract
 from PyPDF2 import PdfReader
 from reportlab.lib.pagesizes import letter
 from reportlab.pdfgen import canvas
-import os
 
-# Load the medical analysis model (e.g., BioGPT or PubMedBERT)
-medical_analyzer = pipeline("text-classification", model="microsoft/biogpt")
+# Load Hugging Face OCR model
+ocr_model = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
 
-# Function to extract text from images or PDFs
+# Function to extract text using Hugging Face OCR model
 def extract_text(file_path):
-    if file_path.endswith(".pdf"):
-        # Extract text from PDF
-        reader = PdfReader(file_path)
-        text = ""
-        for page in reader.pages:
-            text += page.extract_text()
-        return text.strip()
-    else:
-        # Extract text from image
-        return pytesseract.image_to_string(Image.open(file_path))
+    try:
+        # Handle PDFs
+        if file_path.endswith(".pdf"):
+            reader = PdfReader(file_path)
+            text = "".join(page.extract_text() for page in reader.pages)
+            return text.strip()
+        # Handle images
+        result = ocr_model(Image.open(file_path))
+        return result[0]['generated_text']
+    except Exception as e:
+        return f"Error processing the file: {e}"
 
 # Function to generate a PDF report
 def create_pdf_report(analysis, output_path):
     c = canvas.Canvas(output_path, pagesize=letter)
     c.drawString(100, 750, "Blood Test Report Analysis")
     c.drawString(100, 730, "---------------------------")
-    
     y_position = 700
     for line in analysis.split("\n"):
         c.drawString(100, y_position, line)
-        y_position -= 20  # Move down for the next line
-    
+        y_position -= 20
     c.save()
     return output_path
 
 # Function to analyze blood test reports
 def analyze_blood_test(file):
-    # Step 1: Extract text
-    extracted_text = extract_text(file)
-    if not extracted_text:
-        return "Could not extract text. Please upload a valid file.", None
+    try:
+        # Step 1: Extract text
+        extracted_text = extract_text(file)
+        if not extracted_text.strip():
+            return "No readable text found in the uploaded file.", None
 
-    # Step 2: Use medical model to analyze extracted text
-    analysis_results = medical_analyzer(extracted_text)
-    analysis_report = "🔍 Analysis Results:\n"
-    for item in analysis_results[:5]:  # Limit results for simplicity
-        analysis_report += f"- {item['label']}: {item['score']:.2f}\n"
+        # Step 2: Generate dummy analysis results (replace with actual logic)
+        analysis_report = "🔍 Analysis Results:\n"
+        analysis_report += "- Example: High Cholesterol Detected\n"
+        analysis_report += "- Example: Low Hemoglobin Levels\n"
 
-    # Step 3: Generate downloadable PDF report
-    output_pdf = "analysis_report.pdf"
-    create_pdf_report(f"Extracted Text:\n{extracted_text}\n\n{analysis_report}", output_pdf)
-    
-    return analysis_report, output_pdf
+        # Step 3: Generate PDF report
+        output_pdf = "analysis_report.pdf"
+        create_pdf_report(f"Extracted Text:\n{extracted_text}\n\n{analysis_report}", output_pdf)
+
+        return analysis_report, output_pdf
+    except Exception as e:
+        return f"Error processing file: {e}", None
 
 # Gradio interface setup
 interface = gr.Interface(
     fn=analyze_blood_test,
-    inputs=gr.File(label="Upload your blood test report (PNG, JPG, JPEG, or PDF)"),
+    inputs=gr.File(label="Upload your Blood Test Report (PNG, JPG, JPEG, or PDF)"),
     outputs=[
         gr.Textbox(label="Analysis Results"),
         gr.File(label="Download PDF Report")