fix image similarity detection

src/streamlit_app.py

@@ -72,7 +72,22 @@ def load_medical_data():
     )
     return dataset
 
+# Cache dataset image embeddings (takes time, so cached)
+@st.cache_data(show_spinner=True)
+def embed_dataset_images(_dataset):
+    features = []
+    for item in _dataset:
+        # Load image from URL/path or raw bytes - adapt this if needed
+        img = item["image"]
+        inputs = clip_processor(images=img, return_tensors="pt")
+        with torch.no_grad():
+            feat = clip_model.get_image_features(**inputs)
+        feat /= feat.norm(p=2, dim=-1, keepdim=True)
+        features.append(feat.cpu())
+    return torch.cat(features, dim=0)
+
 data = load_medical_data()
+dataset_image_features = embed_dataset_images(data)
 
 from openai import OpenAI
 client = OpenAI(api_key=openai.api_key)
@@ -133,21 +148,7 @@ def get_similar_prompt(query):
     idx = top_result.indices[0].item()
     return data[idx]
 
-# Cache dataset image embeddings (takes time, so cached)
-@st.cache_data(show_spinner=True)
-def embed_dataset_images(_dataset):
-    features = []
-    for item in _dataset:
-        # Load image from URL/path or raw bytes - adapt this if needed
-        img = item["image"]
-        inputs = clip_processor(images=img, return_tensors="pt")
-        with torch.no_grad():
-            feat = clip_model.get_image_features(**inputs)
-        feat /= feat.norm(p=2, dim=-1, keepdim=True)
-        features.append(feat.cpu())
-    return torch.cat(features, dim=0)
 
-dataset_image_features = embed_dataset_images(data)
 
 if query:
     with st.spinner("Searching medical cases..."):