Create app.py

app.py

@@ -0,0 +1,51 @@
+import streamlit as st
+from transformers import pipeline
+import pytesseract
+import cv2
+import numpy as np
+from PIL import Image
+
+# Load the model
+model = pipeline("text2text-generation", model="google/paligemma-3b-mix-224")
+
+# Function to extract text from image using OCR
+def extract_text_from_image(image_file):
+    image = Image.open(image_file)
+    img_cv = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2GRAY)
+    text = pytesseract.image_to_string(img_cv)
+    return text
+
+# Function to get AI interpretation of the prescription
+def interpret_prescription(text):
+    response = model(text)
+    return response[0]['generated_text'].strip()
+
+# Set Streamlit page configuration
+st.set_page_config(
+    page_title="Prescription Reader",
+    page_icon="💊",
+    layout="centered",
+)
+
+# Header
+st.title("Doctor's Prescription Reader 💊")
+
+# Upload prescription image
+uploaded_file = st.file_uploader("Upload Prescription Image", type=["jpg", "jpeg", "png"])
+
+if uploaded_file is not None:
+    # Display uploaded image
+    st.image(uploaded_file, caption="Uploaded Prescription", use_column_width=True)
+
+    with st.spinner("Extracting text from prescription..."):
+        # Extract text from image using OCR
+        extracted_text = extract_text_from_image(uploaded_file)
+        st.subheader("Extracted Text from Prescription:")
+        st.text(extracted_text)
+
+        if extracted_text:
+            # Interpret extracted text using the model
+            with st.spinner("Interpreting the prescription..."):
+                ai_response = interpret_prescription(extracted_text)
+                st.subheader("AI Interpretation:")
+                st.text(ai_response)