increasing-similarity-score

services/qdrant_searcher.py

@@ -8,7 +8,7 @@ class QdrantSearcher:
     def __init__(self, qdrant_url, access_token):
         self.client = QdrantClient(url=qdrant_url, api_key=access_token)
 
-    def search_documents(self, collection_name, query_embedding, user_id, limit=3):
+    def search_documents(self, collection_name, query_embedding, user_id, limit=3,similarity_threshold=0.6):
         logging.info("Starting document search")
 
         # Ensure the query_embedding is in the correct format (flat list of floats)
@@ -25,7 +25,7 @@ class QdrantSearcher:
 
         # Filter by user_id
         query_filter = Filter(must=[FieldCondition(key="user_id", match={"value": user_id})])
-
+        logging.info(f"Performing search using the precomputed embeddings for user_id: {user_id}")
         try:
             hits = self.client.search(
                 collection_name=collection_name,
@@ -36,13 +36,15 @@ class QdrantSearcher:
         except Exception as e:
             logging.error(f"Error during Qdrant search: {e}")
             return None, str(e)
+        
+        filtered_hits = [hit for hit in hits if hit.score >= similarity_threshold]
 
-        if not hits:
+        if not filtered_hits:
             logging.info("No documents found for the given query")
             return None, "No documents found for the given query."
 
         hits_list = []
-        for hit in hits:
+        for hit in filtered_hits:
             hit_info = {
                 "id": hit.id,
                 "score": hit.score,