fix image similarity detection

src/streamlit_app.py

@@ -143,8 +143,6 @@ TEXT_COLUMN = "complaints"  # or "general_complaint", depending on your needs
 st.title("🩺 Multimodal Medical Chatbot")
 
 query = st.text_input("Enter your medical question or symptom description:")
-uploaded_files = st.file_uploader("Upload an image to find similar medical cases:", type=["png", "jpg", "jpeg"], accept_multiple_files=True)
-
 
 if query:
     with st.spinner("Searching medical cases..."):
@@ -170,37 +168,42 @@ if query:
         else:
             st.warning("OpenAI API key not found. Please set OPENAI_API_KEY as a secret environment variable.")
 
+
+uploaded_files = st.file_uploader("Upload an image to find similar medical cases:", type=["png", "jpg", "jpeg"], accept_multiple_files=True)
+
 if uploaded_files is not None:
     with st.spinner("Searching medical cases..."):
-        st.write("Processing img")
         st.write(f"Number of files: {len(uploaded_files)}")
         for uploaded_file in uploaded_files:
             st.write(f"File name: {uploaded_file.name}")
 
-        print(uploaded_files)
-        uploaded_file = uploaded_files[0]
-        st.write(f'uploading file {uploaded_file.name}')
-        query_image = Image.open(uploaded_file).convert("RGB")
-        st.image(query_image, caption="Your uploaded image", use_container_width=True)
+        st.write(uploaded_files)
 
-        # Embed uploaded image
-        inputs = clip_processor(images=query_image, return_tensors="pt")
-        with torch.no_grad():
-            query_feat = clip_model.get_image_features(**inputs)
-        query_feat /= query_feat.norm(p=2, dim=-1, keepdim=True)
+        if len(uploaded_files) > 0:
+            print(uploaded_files)
+            uploaded_file = uploaded_files[0]
+            st.write(f'uploading file {uploaded_file.name}')
+            query_image = Image.open(uploaded_file).convert("RGB")
+            st.image(query_image, caption="Your uploaded image", use_container_width=True)
+
+            # Embed uploaded image
+            inputs = clip_processor(images=query_image, return_tensors="pt")
+            with torch.no_grad():
+                query_feat = clip_model.get_image_features(**inputs)
+            query_feat /= query_feat.norm(p=2, dim=-1, keepdim=True)
 
-        # Compute cosine similarity
-        similarities = (dataset_image_features @ query_feat.T).squeeze(1)  # [num_dataset_images]
+            # Compute cosine similarity
+            similarities = (dataset_image_features @ query_feat.T).squeeze(1)  # [num_dataset_images]
 
-        top_k = 3
-        top_results = torch.topk(similarities, k=top_k)
+            top_k = 3
+            top_results = torch.topk(similarities, k=top_k)
 
-        st.write(f"Top {top_k} similar medical cases:")
+            st.write(f"Top {top_k} similar medical cases:")
 
-        for rank, idx in enumerate(top_results.indices):
-            score = top_results.values[rank].item()
-            similar_img = data[int(idx)]['image']
-            st.image(similar_img, caption=f"Similarity: {score:.3f}", use_container_width=True)
-            st.markdown(f"**Case description:** {data[int(idx)]['complaints']}")
+            for rank, idx in enumerate(top_results.indices):
+                score = top_results.values[rank].item()
+                similar_img = data[int(idx)]['image']
+                st.image(similar_img, caption=f"Similarity: {score:.3f}", use_container_width=True)
+                st.markdown(f"**Case description:** {data[int(idx)]['complaints']}")
 
 st.caption("This chatbot is for educational purposes only and does not provide medical advice.")