Update app.py

app.py

@@ -3,6 +3,17 @@ from sentence_transformers import SentenceTransformer
 import gradio as gr
 import spacy
 
+import subprocess
+
+# Run the spacy model download command
+
+try:
+    # Try to load the model to check if it's already installed
+    nlp = spacy.load("en_core_web_trf")
+except OSError:
+    # If the model is not found, download it
+    subprocess.run(["python", "-m", "spacy", "download", "en_core_web_trf"])
+    nlp = spacy.load("en_core_web_trf")
 
 model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True)
 
@@ -12,24 +23,23 @@ df_new = pd.read_csv('last_df.csv')
 df_new['country'] = df_new['country'].replace('Türkiye', 'Turkey')
 #
 #
-# nlp = spacy.load("en_core_web_trf")
-#
-# # Function to extract city name from the query
-# def get_city_name(query):
-#     text_query = nlp(query)
-#     for city in text_query.ents:
-#         if city.label_ == "GPE":
-#             return city.text.lower()
-#     return None
-#
-# # Function to filter DataFrame by location
-# def filter_by_loc(query):
-#     city_name = get_city_name(query)
-#     if city_name in df_new['locality'].str.lower().unique():
-#         filtered_df = df_new[df_new['locality'].str.lower() == city_name.lower()]
-#         return filtered_df
-#     else:
-#         return df_new
+
+# Function to extract city name from the query
+def get_city_name(query):
+    text_query = nlp(query)
+    for city in text_query.ents:
+        if city.label_ == "GPE":
+            return city.text.lower()
+    return None
+
+# Function to filter DataFrame by location
+def filter_by_loc(query):
+    city_name = get_city_name(query)
+    if city_name in df_new['locality'].str.lower().unique():
+        filtered_df = df_new[df_new['locality'].str.lower() == city_name.lower()]
+        return filtered_df
+    else:
+        return df_new
 
 
 
@@ -60,18 +70,18 @@ def process_query(query):
     query_embedding = model.encode(query)
 
     # Filter DataFrame by location
-    # filtered_data = filter_by_loc(query)
+    filtered_data = filter_by_loc(query)
 
     # Convert query_embedding to a tensor if it is not already
     query_embedding_tensor = torch.tensor(query_embedding)
 
     # Apply the similarity function to the filtered DataFrame
-    # filtered_data['similarity_score'] = filtered_data.apply(lambda row: get_similarity_score(row, query_embedding_tensor), axis=1)
+    filtered_data['similarity_score'] = filtered_data.apply(lambda row: get_similarity_score(row, query_embedding_tensor), axis=1)
 
-    df_new['similarity_score'] = df_new.apply(lambda row: get_similarity_score(row, query_embedding_tensor), axis=1)
+    # df_new['similarity_score'] = df_new.apply(lambda row: get_similarity_score(row, query_embedding_tensor), axis=1)
 
 
-    top_similar = df_new.sort_values('similarity_score', ascending=False).head(1)
+    top_similar = filtered_data.sort_values('similarity_score', ascending=False).head(1)
 
 
     hotel_name = top_similar['hotel_name'].values[0]