Update app.py

app.py

@@ -91,10 +91,24 @@ class EventbriteRAGPipeline:
         return self.model.encode([event_to_text(event) for event in self.events])
 
     def query_events(self, query: str, top_k: int = 5) -> List[Event]:
+        # query_embedding = self.model.encode(query).reshape(1, -1)
+        # similarities = cosine_similarity(query_embedding, self.event_embeddings)[0]
+        # top_indices = similarities.argsort()[-top_k:][::-1]
+        # return [self.events[idx] for idx in top_indices]
         query_embedding = self.model.encode(query).reshape(1, -1)
         similarities = cosine_similarity(query_embedding, self.event_embeddings)[0]
-        top_indices = similarities.argsort()[-top_k:][::-1]
-        return [self.events[idx] for idx in top_indices]
+
+        top_indices = similarities.argsort()[-(top_k * 2):][::-1]  # Get extra events to filter duplicates
+
+        unique_events = {}
+        for idx in top_indices:
+            event = self.events[idx]
+            if event.id not in unique_events:
+                unique_events[event.id] = event
+            if len(unique_events) == top_k:
+                break
+
+        return list(unique_events.values())
 
 # Event Evaluator
 class EventEvaluator:
@@ -103,21 +117,40 @@ class EventEvaluator:
 
     def evaluate_query(self, query):
         """Evaluate a single query and return results."""
+        # top_events = self.pipeline.query_events(query)
+        # results = []
+        # for event in top_events:
+        #     result = {
+        #         "Event Name": event.name,
+        #         "Online Event": event.is_online_event,
+        #         "Start Time": event.start_datetime,
+        #         "Venue Address": event.primary_venue.address.address_1,
+        #         "Venue Name": event.primary_venue.name,
+        #         "Description": event.short_description,
+        #         "Tickets URL": event.tickets_url,
+        #         "Language": event.language,
+        #         "Categories": [tag.text for tag in event.tags_categories],
+        #     }
+        #     results.append(result)
         top_events = self.pipeline.query_events(query)
+    
         results = []
+        seen = set()
+    
         for event in top_events:
-            result = {
-                "Event Name": event.name,
-                "Online Event": event.is_online_event,
-                "Start Time": event.start_datetime,
-                "Venue Address": event.primary_venue.address.address_1,
-                "Venue Name": event.primary_venue.name,
-                "Description": event.short_description,
-                "Tickets URL": event.tickets_url,
-                "Language": event.language,
-                "Categories": [tag.text for tag in event.tags_categories],
-            }
-            results.append(result)
+            if event.id not in seen:  # Ensure unique events
+                seen.add(event.id)
+                results.append({
+                    "Event Name": event.name,
+                    "Online Event": event.is_online_event,
+                    "Start Time": event.start_datetime,
+                    "Venue Address": event.primary_venue.address.address_1,
+                    "Venue Name": event.primary_venue.name,
+                    "Description": event.short_description,
+                    "Tickets URL": event.tickets_url,
+                    "Language": event.language,
+                    "Categories": [tag.text for tag in event.tags_categories],
+                })
         return results
 
 # Fetch events from Eventbrite API