Spaces:
Runtime error
Runtime error
import os | |
import streamlit as st | |
from dotenv import load_dotenv | |
from PyPDF2 import PdfReader | |
from langchain.text_splitter import CharacterTextSplitter | |
from langchain.embeddings import OpenAIEmbeddings | |
from langchain.vectorstores import FAISS | |
from langchain.chat_models import ChatOpenAI | |
from langchain.memory import ConversationBufferMemory | |
from langchain.chains import ConversationalRetrievalChain | |
from htmlTemplates import css, bot_template, user_template | |
def extract_text_from_pdfs(pdf_docs): | |
text = "" | |
for pdf in pdf_docs: | |
pdf_reader = PdfReader(pdf) | |
for page in pdf_reader.pages: | |
text += page.extract_text() | |
return text | |
def split_text_into_chunks(text): | |
text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len) | |
return text_splitter.split_text(text) | |
def create_vector_store_from_text_chunks(text_chunks): | |
key = os.getenv('OPENAI_KEY') | |
embeddings = OpenAIEmbeddings(openai_api_key=key) | |
return FAISS.from_texts(texts=text_chunks, embedding=embeddings) | |
def create_conversation_chain(vectorstore): | |
llm = ChatOpenAI() | |
memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True) | |
return ConversationalRetrievalChain.from_llm(llm=llm, retriever=vectorstore.as_retriever(), memory=memory) | |
def process_user_input(user_question): | |
response = st.session_state.conversation({'question': user_question}) | |
st.session_state.chat_history = response['chat_history'] | |
for i, message in enumerate(st.session_state.chat_history): | |
template = user_template if i % 2 == 0 else bot_template | |
st.write(template.replace("{{MSG}}", message.content), unsafe_allow_html=True) | |
def main(): | |
load_dotenv() | |
st.set_page_config(page_title="Chat with multiple PDFs", page_icon=":books:") | |
st.write(css, unsafe_allow_html=True) | |
st.header("Chat with multiple PDFs :books:") | |
user_question = st.text_input("Ask a question about your documents:") | |
if user_question: | |
process_user_input(user_question) | |
with st.sidebar: | |
st.subheader("Your documents") | |
pdf_docs = st.file_uploader("Upload your PDFs here and click on 'Process'", accept_multiple_files=True) | |
if st.button("Process"): | |
with st.spinner("Processing"): | |
raw_text = extract_text_from_pdfs(pdf_docs) | |
text_chunks = split_text_into_chunks(raw_text) | |
vectorstore = create_vector_store_from_text_chunks(text_chunks) | |
st.session_state.conversation = create_conversation_chain(vectorstore) | |
if __name__ == '__main__': | |
main() | |