@first-cloudugba

[dianecloud]

from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.llms import OpenAI
from langchain.chains import RetrievalQA

Load PDFs

loader = PyPDFLoader("docs/my_doc.pdf")
docs = loader.load()

Chunkify

splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
chunks = splitter.split_documents(docs)

Embed & index

vectorstore = FAISS.from_documents(chunks, OpenAIEmbeddings())
retriever = vectorstore.as_retriever()

QA chain

qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=retriever)