import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from [Link] import OpenAIEmbeddings
from langchain_community.vectorstores import FAISS
from [Link].question_answering import load_qa_chain
from langchain_community.chat_models import ChatOpenAI
OPENAI_API_KEY = "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" #Pass your
key here
#Upload PDF files
[Link]("My first Chatbot")
with [Link]:
[Link]("Your Documents")
file = st.file_uploader(" Upload a PDf file and start asking questions",
type="pdf")
#Extract the text
if file is not None:
pdf_reader = PdfReader(file)
text = ""
for page in pdf_reader.pages:
text += page.extract_text()
#[Link](text)
#Break it into chunks
text_splitter = RecursiveCharacterTextSplitter(
separators="\n",
chunk_size=1000,
chunk_overlap=150,
length_function=len
)
chunks = text_splitter.split_text(text)
#[Link](chunks)
# generating embedding
embeddings = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)
# creating vector store - FAISS
vector_store = FAISS.from_texts(chunks, embeddings)
# get user question
user_question = st.text_input("Type Your question here")
# do similarity search
if user_question:
match = vector_store.similarity_search(user_question)
#[Link](match)
#define the LLM
llm = ChatOpenAI(
openai_api_key = OPENAI_API_KEY,
temperature = 0,
max_tokens = 1000,
model_name = "gpt-3.5-turbo"
)
#output results
#chain -> take the question, get relevant document, pass it to the LLM,
generate the output
chain = load_qa_chain(llm, chain_type="stuff")
response = [Link](input_documents = match, question = user_question)
[Link](response)
