from langchain.document_loaders import PyPDFLoader
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import ElasticVectorSearch, Pinecone, Weaviate, FAISS
from langchain.chains import RetrievalQA
from langchain.chat_models import ChatOpenAI
import os
os.environ["OPENAI_API_KEY"]

# loader = PyPDFLoader("cardinality.pdf")
# pages = loader.load_and_split()
# print(len(pages), pages)

embeddings = OpenAIEmbeddings()
# Create DB
# db = FAISS.from_documents(pages, embeddings)

# Save the DB in your local
# db.save_local("faiss_index")

# # load the DB 
new_db = FAISS.load_local("faiss_index", embeddings)

# # Init LLM
llm = ChatOpenAI()
qa_chain = RetrievalQA.from_chain_type(llm, retriever=new_db.as_retriever())

def ask(user_query):
    res=qa_chain({"query": user_query})
    return res["result"]