Create hybrid_searcher.py

hybrid_searcher.py

@@ -0,0 +1,39 @@
+from qdrant_client import QdrantClient
+
+
+class HybridSearcher:
+    DENSE_MODEL = "sentence-transformers/all-MiniLM-L6-v2"
+    SPARSE_MODEL = "prithivida/Splade_PP_en_v1"
+    def __init__(self, collection_name):
+        self.collection_name = collection_name
+        # initialize Qdrant client
+        self.qdrant_client = QdrantClient("http://localhost:6333")
+        self.qdrant_client.set_model(self.DENSE_MODEL)
+        # comment this line to use dense vectors only
+        self.qdrant_client.set_sparse_model(self.SPARSE_MODEL)
+        
+    def search(self, text: str, city: str):
+        city_of_interest = city
+
+        # Define a filter for cities
+        city_filter = models.Filter(
+            must=[
+                models.FieldCondition(
+                    key="city", 
+                    match=models.MatchValue(value=city_of_interest)
+                )
+            ]
+        )
+    
+        search_result = self.qdrant_client.query(
+            collection_name=self.collection_name,
+            query_text=text,
+            query_filter=city_filter,
+            limit=5
+        )
+        # `search_result` contains found vector ids with similarity scores 
+        # along with the stored payload
+        
+        # Select and return metadata
+        metadata = [hit.metadata for hit in search_result]
+        return metadata