Update app.py

app.py

@@ -42,8 +42,8 @@ def generate_input(input_type, image=None, text=None, response_amount=3):
     return vector_search(combined_input,response_amount) #search through embedded document w/ input
 
 # load embeddings and metadata
-embeddings = np.load("netflix_embeddings.npy")  #created using sentence_transformers on kaggle
-metadata = pd.read_csv("netflix_metadata.csv") #created using sentence_transformers on kaggle
+embeddings = np.load("dog_data_embeddings.npy")  #created using sentence_transformers on kaggle
+metadata = pd.read_csv("dog_metadata.csv") #created using sentence_transformers on kaggle
 
 # vector search function
 def vector_search(query,top_n=3):
@@ -56,9 +56,9 @@ def vector_search(query,top_n=3):
     result_text=""
     for index,row in results.iterrows():   #loop through results to get Title, Description, and Genre for top n outputs
         if index!=top_n-1:
-            result_text+=f"Title: {row['title']}  Description: {row['description']}  Genre: {row['listed_in']}\n\n"
+            result_text+=f"Breed: {row['breed']}  Description: {row['description']}  Temperament: {row['temperament']} Energy Level: {row['energy_level_category']} Trainability: {row['trainability_category']} Demeanor:  {row['demeanor_category']} \n\n"
         else:
-            result_text+=f"Title: {row['title']}  Description: {row['description']}  Genre: {row['listed_in']}"
+         result_text+=f"Breed: {row['breed']}  Description: {row['description']}  Temperament: {row['temperament']} Energy Level: {row['energy_level_category']} Trainability: {row['trainability_category']} Demeanor:  {row['demeanor_category']}"
     return result_text