u

app.py

@@ -23,29 +23,14 @@ def extract_text(file):
 # Load Hugging Face model for medical explanation
 @st.cache_resource
 def load_explainer():
-    return pipeline("text2text-generation", model="google/flan-t5-base")
-
-# Visual card mapping
-def get_visual_card(term):
-    visuals = {
-        "ct scan": "visuals/ct_scan.png",
-        "mri": "visuals/mri.png",
-        "hemoglobin": "visuals/hemoglobin.png",
-        "creatinine": "visuals/creatinine.png",
-        "platelets": "visuals/platelets.png",
-        "ecg": "visuals/ecg.png"
-    }
-    for key in visuals:
-        if key in term.lower():
-            return visuals[key]
-    return None
+    return pipeline("text2text-generation", model="google/flan-t5-large")
 
 # Main logic
 if uploaded_file:
     text_data = extract_text(uploaded_file)
     st.success("Health Report Uploaded Successfully!")
 
-    # Display the report text without label
+    # Display the report text
     st.markdown("### 📄 Health Report Content")
     st.write(text_data)
 
@@ -53,8 +38,6 @@ if uploaded_file:
 
     # Store extracted text in session
     st.session_state['report_text'] = text_data
-    if 'chat_history' not in st.session_state:
-        st.session_state['chat_history'] = []
 
     # Chatbot
     st.subheader("💬 Ask About Any Medical Term or Part of the Report")
@@ -63,43 +46,28 @@ if uploaded_file:
 
     if st.button("Get AI Explanation") and user_question:
         with st.spinner("Thinking..."):
-            previous_context = "\n".join([
-                f"Q: {q}\nA: {a}" for q, a in st.session_state['chat_history'][-3:]
-            ])
-            
+
+            # Enhanced prompt for better answers
             prompt = (
-                f"You are a helpful medical assistant. "
-                f"Please explain the following medical term or phrase in very simple words.\n"
-                f"Health Report Content:\n{st.session_state['report_text']}\n"
-                f"Previous Conversation:\n{previous_context}\n"
-                f"Current Question: {user_question}\n"
-                f"Answer in easy language."
+                f"You are a friendly and experienced medical assistant. "
+                f"Explain this term in very simple language. "
+                f"Provide a short definition and mention why it's important or what it means in a report.\n\n"
+                f"Question: {user_question}"
             )
 
-            response = explainer(prompt)[0]['generated_text']
-            st.session_state['chat_history'].append((user_question, response))
+            response = explainer(prompt, max_length=300)[0]['generated_text']
 
         st.success("Explanation:")
         st.write(response)
 
-        # Visual card
-        image_path = get_visual_card(user_question)
-        if image_path and os.path.exists(image_path):
-            st.image(image_path, caption=f"Visual aid for: {user_question}", use_column_width=True)
-
-        # Text-to-speech
-        if st.button("🔊 Listen to this explanation"):
-            tts = gTTS(text=response)
-            with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
-                tts.save(tmp_file.name)
-                st.audio(tmp_file.name, format='audio/mp3')
-
-    # Display chat history
-    if st.session_state['chat_history']:
-        st.markdown("---")
-        st.markdown("### 💬 Chat History")
-        for q, a in reversed(st.session_state['chat_history']):
-            st.markdown(f"**You:** {q}")
-            st.markdown(f"**AI:** {a}")
+        # Text-to-speech using gTTS
+        tts = gTTS(text=response)
+        temp_audio = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
+        tts.save(temp_audio.name)
+
+        audio_file = open(temp_audio.name, 'rb')
+        audio_bytes = audio_file.read()
+        st.audio(audio_bytes, format='audio/mp3')
+
 else:
     st.info("Upload a PDF Health Report to begin.")