Update app.py

app.py

@@ -1,34 +1,65 @@
+import streamlit as st
 from models import initialize_models
 from models.pdf_handler import parse_pdf
 from models.image_handler import analyze_image
 from models.summarizer import summarize_text
 from models.translator import translate_text
 from models.problem_checker import flag_lab_problems
+from PIL import Image
 
-def main():
-    # Initialize Hugging Face models
-    models = initialize_models()
-    
-    # Example 1: Parse and summarize a PDF lab report
-    pdf_path = "example_lab_report.pdf"
-    pdf_text = parse_pdf(pdf_path)
-    print("Extracted Text from PDF:\n", pdf_text)
-
-    summary = summarize_text(pdf_text, models["summarize_model"])
-    print("\nSummary:\n", summary)
-
-    # Check for problems in the lab report
-    problems = flag_lab_problems(summary)
-    print("\nDetected Problems:\n", problems)
-
-    # Example 2: Translate the summary if needed
-    translated_summary = translate_text(summary, models["translation_model"])
-    print("\nTranslated Summary:\n", translated_summary)
-
-    # Example 3: Analyze an image
-    image_path = "example_lab_image.jpg"
-    image_results = analyze_image(image_path, models["image_model"])
-    print("\nImage Analysis Results:\n", image_results)
-
-if __name__ == "__main__":
-    main()
+# Initialize Models
+models = initialize_models()
+
+# Streamlit App
+st.title("Lab Test Analyzer Dashboard")
+
+# File Upload
+uploaded_file = st.file_uploader("Upload a Lab Report (PDF, Image, or Text)", type=["pdf", "png", "jpg", "jpeg", "txt"])
+
+if uploaded_file:
+    file_type = uploaded_file.name.split(".")[-1].lower()
+
+    # Extract Text Based on File Type
+    extracted_text = ""
+    if file_type == "pdf":
+        st.write("Processing PDF file...")
+        extracted_text = parse_pdf(uploaded_file)
+    elif file_type in ["png", "jpg", "jpeg"]:
+        st.write("Processing Image file...")
+        image = Image.open(uploaded_file)
+        extracted_text = analyze_image(image, models["image_model"])
+    elif file_type == "txt":
+        st.write("Processing Text file...")
+        extracted_text = uploaded_file.read().decode("utf-8")
+    else:
+        st.error("Unsupported file type.")
+
+    # Display Extracted Text
+    if extracted_text:
+        st.subheader("Extracted Content")
+        st.text_area("Extracted Text", extracted_text, height=200)
+
+        # Summarization
+        summary = summarize_text(extracted_text, models["summarize_model"])
+        st.subheader("Summary of the Report")
+        st.text_area("Summary", summary, height=150)
+
+        # Sentiment Analysis
+        st.subheader("Sentiment Analysis")
+        sentiment, confidence = analyze_sentiment(extracted_text, models["sentiment_model"])
+        st.write(f"**Sentiment**: {sentiment} (Confidence: {confidence:.2f})")
+
+        # Problem Detection
+        problems = flag_lab_problems(summary)
+        st.subheader("Detected Problems")
+        st.write(problems)
+
+        # Translation
+        st.subheader("Translations")
+        translations = translate_content(summary, models["translation_model"])
+        st.write("**English**: ", translations["English"])
+        st.write("**Hindi**: ", translations["Hindi"])
+        st.write("**Urdu**: ", translations["Urdu"])
+
+    else:
+        st.error("Could not extract text from the uploaded file.")