Update app.py

app.py

@@ -1,105 +1,26 @@
+import streamlit as st
+from PIL import Image
 import pytesseract
 import pandas as pd
 import re
 
-
-
-
-
-
-
-
-def extract_text(image):
-    """
-    Extract text from the image using Tesseract.
-    return pytesseract.image_to_string(image)
-
-
-
-def clean_and_parse_extracted_text(raw_text):
-    """
-    Parse and clean the raw text to extract structured data.
-    """
-    # Split the text into lines and clean up
-    lines = raw_text.split("\n")
-    lines = [line.strip() for line in lines if line.strip()]
-
-    # Identify and extract rows with valid components
-    data = []
-    for line in lines:
-        # Match rows containing numeric ranges and values
-        match = re.match(
-            r"^(.*?)(\d+(\.\d+)?)(\s*-?\s*\d+(\.\d+)?\s*-?\s*\d+(\.\d+)?)?\s*([a-zA-Z/%]+)?\s*(H|L|Normal)?$",
-            line,
-            unit = match.group(7)
-            flag = "Normal"  # Default flag
-
-            # Determine the flag based on value and range
-            if min_val is not None and max_val is not None:
-                if value < min_val:
-                    flag = "L"
-                elif value > max_val:
-                    flag = "H"
-
-            # Only append the data if the flag is abnormal (L or H)
-            if flag != "Normal":
-                data.append([component, value, min_val, max_val, unit, flag])
-
-    # Create a DataFrame
-    df = pd.DataFrame(data, columns=["Component", "Your Value", "Min", "Max", "Units", "Flag"])
-
-    # Fix misspellings and inconsistencies (if any known issues exist)
-    correction_map = {
-        "emoglobin": "Hemoglobin",
-        "ematocrit": "Hematocrit",
-    return df
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-def display_results(df):
-    """
-    Display the flagged abnormalities in a table format.
-    """
-
-
-
-
-
-
-    st.dataframe(df, use_container_width=True)
-
-
-
-
-
-# Streamlit app
-st.title("Blood Report Analyzer")
-st.write("Upload an image of a blood test report to analyze.")
+st.title("Blood Test Analyzer with RAG")
+st.write("Upload an image of your blood test report to analyze and get recommendations.")
 
 uploaded_file = st.file_uploader("Upload Image", type=["png", "jpg", "jpeg"])
 
-        # Parse the extracted text into a structured format
-        parsed_data = clean_and_parse_extracted_text(extracted_text)
+if uploaded_file is not None:
+    try:
+        # Load the image
+        image = Image.open(uploaded_file)
+        st.image(image, caption="Uploaded Image", use_container_width=True)
 
-        # Display the structured data (only abnormalities)
-        st.subheader("Flagged Abnormalities")
-        display_results(parsed_data)
+        # Step 1: Extract text using Tesseract
+        extracted_text = pytesseract.image_to_string(image)
+        st.text_area("Extracted Text", extracted_text, height=200)
 
-    except Exception as e:
+        # Placeholder for parsed data
+        st.subheader("Flagged Abnormalities")
+        st.write("Parsing logic and RAG recommendations will go here.")
+    except Exception as e:
+        st.error(f"An error occurred: {e}")