Update app.py

app.py

@@ -12,6 +12,8 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter ,CharacterTex
 from langchain.chains import RetrievalQA
 from langchain.document_loaders import TextLoader ,PyPDFLoader ,DirectoryLoader
 from langchain.document_loaders import GoogleDriveLoader
+from datasets import load_dataset
+dataset = load_dataset("heyal/carbon_data")
 
 def create_vecotrstore(embedding , texts, db_name = 'chromadb' ) -> None:
   "Extract vector embeddings from text and store to persistance directory and return vector object."
@@ -28,8 +30,9 @@ def create_vecotrstore(embedding , texts, db_name = 'chromadb' ) -> None:
 def load_chunk(data_dir):
   
   #loader = DirectoryLoader(data_dir , glob="./*.pdf", loader_cls=PyPDFLoader)
-  loader = GoogleDriveLoader(folder_id = data_dir, glob="./*.pdf", loader_cls=PyPDFLoader, credentials_path='googlecreds.json')
-  documents = loader.load()
+  #loader = GoogleDriveLoader(folder_id = data_dir, glob="./*.pdf", loader_cls=PyPDFLoader, credentials_path='googlecreds.json')
+  #documents = loader.load()
+  documents = dataset
   print(f"{len(documents)} documents are loaded.")
 
   text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000,