Update app.py

app.py

@@ -1,10 +1,10 @@
 # Initialize a retriever using Qdrant and SentenceTransformer embeddings
 from langchain_community.vectorstores import Qdrant
-from langchain_community.retrievers.qdrant_sparse_vector_retriever import QdrantSparseVectorRetriever 
 from langchain_community.embeddings import SentenceTransformerEmbeddings
+from kaggle_secrets import UserSecretsClient
 from qdrant_client import QdrantClient
 import pandas as pd
-import gradio as gr
+import gradio as gd
 
 
 embeddings = SentenceTransformerEmbeddings(model_name='sentence-transformers/clip-ViT-B-32')
@@ -13,20 +13,23 @@ def get_results(search_results):
     filtered_img_ids = [doc.metadata.get("image_id") for doc in search_results]
     return filtered_img_ids
 
+user_secrets = UserSecretsClient()
+vector_db_key = user_secrets.get_secret("vector_db_key")
+
 client = QdrantClient(
     url="https://763bc1da-0673-4535-91ac-b5538ec0287f.us-east4-0.gcp.cloud.qdrant.io:6333", 
-    api_key='UOqiBgqhhu8BBWP98mwjGl7h4IhL2vMAqzO4EI9PEB66A50n9GoIiQ',
+    api_key=vector_db_key,
 ) # Persists changes to disk, fast prototyping
 
 COLLECTION_NAME="semantic_image_search"
 
 
 dense_vector_retriever = Qdrant(client, COLLECTION_NAME, embeddings)
-images_data = pd.read_csv("images.csv", on_bad_lines='skip')
+images_data = pd.read_csv("/kaggle/input/fashion-product-images-dataset/fashion-dataset/images.csv", on_bad_lines='skip')
 
 def get_link(query):
     Search_Query = query
-    neutral_retiever = QdrantSparseVectorRetriever(retrievers=[dense_vector_retriever.as_retriever()])
+    neutral_retiever = dense_vector_retriever.as_retriever()
     result = neutral_retiever.get_relevant_documents(Search_Query)
     filtered_images = get_results(result)
     filtered_img_ids = [doc.metadata.get("image_id") for doc in result]