Update src/streamlit_app.py

src/streamlit_app.py

@@ -74,13 +74,16 @@ st.write("Dataset columns:", data.features.keys())
 text_field = "text" if "text" in data.features else list(data.features.keys())[0]
 
 # Then use dynamic access:
-text_embeddings = embed_texts(data[text_field])
+#text_embeddings = embed_texts(data[text_field])
 
 # ========== 🧠 Embedding Function ==========
 @st.cache_data(show_spinner=False)
 def embed_texts(texts):
     return text_model.encode(texts, convert_to_tensor=True)
 
+# Pick which text column to use
+TEXT_COLUMN = "complaints"  # or "general_complaint", depending on your needs
+
 # ========== 🧑‍⚕️ App UI ==========
 st.title("🩺 Multimodal Medical Chatbot")
 
@@ -88,7 +91,7 @@ query = st.text_input("Enter your medical question or symptom description:")
 
 if query:
     with st.spinner("Searching medical cases..."):
-        text_embeddings = embed_texts(data['description'])
+        text_embeddings = embed_texts(data[TEXT_COLUMN])
         query_embedding = embed_texts([query])[0]
 
         # Compute similarity
@@ -101,11 +104,11 @@ if query:
         st.image(selected['image'], caption="Most relevant medical image", use_column_width=True)
 
         # Show Text
-        st.markdown(f"**Case Description:** {selected['description']}")
+        st.markdown(f"**Case Description:** {selected[TEXT_COLUMN]}")
 
         # GPT Explanation
         if openai.api_key:
-            prompt = f"Explain this case in plain English: {selected['description']}"
+            prompt = f"Explain this case in plain English: {selected[TEXT_COLUMN]}"
             response = openai.ChatCompletion.create(
                 model="gpt-4",
                 messages=[{"role": "user", "content": prompt}],