lower the similarity threshold

app.py

@@ -78,7 +78,7 @@ def upsert_data(dataset_split):
 upsert_data(dataset['train'])
 
 # Define retrieval function with similarity threshold
-def retrieve_relevant_text(input_text, similarity_threshold=0.1):  # Lower threshold to capture more results
+def retrieve_relevant_text(input_text, similarity_threshold=1.0):  # Lower threshold to capture more results
     input_embedding = embed_text([input_text])[0]
     results = collection.query(
         query_embeddings=[input_embedding],
@@ -103,7 +103,7 @@ def retrieve_relevant_text(input_text, similarity_threshold=0.1):  # Lower thres
     return output
 
 # Evaluate retrieval efficiency on the validation/test set
-def evaluate_efficiency(dataset_split, similarity_threshold=0.1):
+def evaluate_efficiency(dataset_split, similarity_threshold=1.0):
     y_true = []
     y_pred = []
     total_similarity = 0