d hel

app.py

@@ -1,6 +1,5 @@
 import streamlit as st
-# from dotenv import load_dotenv
-from langchain_community.document_loaders.pdf import PyPDFDirectoryLoader, PyPDFLoader
+from langchain_community.document_loaders.pdf import PyPDFDirectoryLoader
 from langchain.text_splitter import CharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceInstructEmbeddings
 from langchain_community.vectorstores import FAISS
@@ -8,8 +7,6 @@ from langchain.chains import ConversationalRetrievalChain
 from langchain.llms import HuggingFaceHub
 from langchain.memory import ConversationBufferMemory
 
-# load_dotenv()
-
 def make_vectorstore(embeddings):
     # use glob to find all the pdf files in the data folder in the base directory
     loader = PyPDFDirectoryLoader("data")   
@@ -33,9 +30,8 @@ def get_conversation(vectorstore):
     # create a memory object to store the conversation history
     memory = ConversationBufferMemory(memory_key="chat_history",return_messages=True,)
 
-    # create a conversational retrieval chain
     conversation_chain = ConversationalRetrievalChain.from_chain_type(
-        llm=HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512}), 
+        llm=HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512}),
         chain_type="stuff", 
         retriever=vectorstore.as_retriever(),
         memory=memory)