Update app.py

app.py

@@ -3,7 +3,7 @@ import bs4
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.document_loaders import WebBaseLoader
 from langchain_community.vectorstores import Chroma
-from langchain_community.embeddings import HuggingFaceHubEmbeddings  # Updated import
+from langchain_huggingface import HuggingFaceEndpointEmbeddings  # Updated import
 from dotenv import load_dotenv
 import os
 
@@ -47,7 +47,10 @@ def load_and_retrieve_docs(url, max_retries=3):
             docs = loader.load()
             text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
             splits = text_splitter.split_documents(docs)
-            embeddings = HuggingFaceHubEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")  # Updated embeddings
+            embeddings = HuggingFaceEndpointEmbeddings(
+                endpoint_url="https://api-inference.huggingface.co/models/sentence-transformers/all-mpnet-base-v2",
+                api_key=os.environ["HUGGINGFACE_API_KEY"]
+            )  # Updated embeddings
             vectorstore = Chroma.from_documents(documents=splits, embedding=embeddings)
             return vectorstore.as_retriever()
         except ReadTimeout: