up

app.py

@@ -4,26 +4,11 @@ from transformers import pipeline
 from gtts import gTTS
 import tempfile
 import os
-from googletrans import Translator
 
 # Streamlit page setup
 st.set_page_config(page_title="Health Report Analyzer", page_icon="🩺")
 st.title("🩺 Health Report Analyzer")
 
-# Language selection
-lang_map = {
-    "English": "en",
-    "Hindi (हिंदी)": "hi",
-    "Punjabi (ਪੰਜਾਬੀ)": "pa",
-    "Bengali (বাংলা)": "bn",
-    "Tamil (தமிழ்)": "ta",
-    "Telugu (తెలుగు)": "te",
-    "Gujarati (ગુજરાતી)": "gu",
-    "Marathi (मराठी)": "mr"
-}
-language_choice = st.selectbox("Choose output language:", list(lang_map.keys()))
-target_lang = lang_map[language_choice]
-
 # Upload PDF
 uploaded_file = st.file_uploader("Upload a Health Report (PDF only)", type="pdf")
 
@@ -35,31 +20,26 @@ def extract_text(file):
         text += page.get_text()
     return text
 
-# Load medical explainer model
+# Load Hugging Face model for medical explanation
 @st.cache_resource
 def load_explainer():
     return pipeline("text2text-generation", model="google/flan-t5-large")
 
-# Translate text using Google Translate
-def translate_text(text, target_language):
-    if target_language == "en":
-        return text  # No translation needed
-    translator = Translator()
-    translated = translator.translate(text, dest=target_language)
-    return translated.text
-
 # Main logic
 if uploaded_file:
     text_data = extract_text(uploaded_file)
-    st.success("✅ Health Report Uploaded Successfully!")
+    st.success("Health Report Uploaded Successfully!")
 
     # Display the report text
     st.markdown("### 📄 Health Report Content")
     st.write(text_data)
 
     explainer = load_explainer()
+
+    # Store extracted text in session
     st.session_state['report_text'] = text_data
 
+    # Chatbot
     st.subheader("💬 Ask About Any Medical Term or Part of the Report")
 
     user_question = st.text_input("Enter a medical term or question (e.g. 'CT scan', 'Explain creatinine'):")
@@ -67,7 +47,7 @@ if uploaded_file:
     if st.button("Get AI Explanation") and user_question:
         with st.spinner("Thinking..."):
 
-            # Prompt to the model
+            # Enhanced prompt for better answers
             prompt = (
                 f"You are a friendly and experienced medical assistant. "
                 f"Explain this term in very simple language. "
@@ -77,19 +57,17 @@ if uploaded_file:
 
             response = explainer(prompt, max_length=300)[0]['generated_text']
 
-            # Translate if selected language is not English
-            translated_response = translate_text(response, target_lang)
-
         st.success("Explanation:")
-        st.write(translated_response)
+        st.write(response)
 
-        # Text-to-speech
-        tts = gTTS(text=translated_response, lang=target_lang)
+        # 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')
-        st.audio(audio_file.read(), format='audio/mp3')
+        audio_bytes = audio_file.read()
+        st.audio(audio_bytes, format='audio/mp3')
 
 else:
-    st.info("Upload a PDF Health Report to begin.")
+    st.info("Upload a PDF Health Report to begin.")