|
import streamlit as st |
|
from dotenv import load_dotenv |
|
from PyPDF2 import PdfReader |
|
from langchain.text_splitter import RecursiveCharacterTextSplitter |
|
from langchain.embeddings import HuggingFaceInstructEmbeddings, HuggingFaceBgeEmbeddings |
|
from langchain.vectorstores import FAISS |
|
from langchain.memory import ConversationBufferMemory |
|
from langchain.chains import ConversationalRetrievalChain |
|
from htmlTemplates import css, bot_template, user_template |
|
from langchain.llms import HuggingFaceHub |
|
|
|
def get_pdf_text(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 get_text_chunks(documents): |
|
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50) |
|
text_chunks = text_splitter.split_documents(documents) |
|
return text_chunks |
|
|
|
|
|
def get_vectorstore(text_chunks): |
|
|
|
embeddings = HuggingFaceBgeEmbeddings(model_name="hkunlp/instructor-large") |
|
vectorstore = FAISS.from_documents(texts=text_chunks, embedding=embeddings) |
|
return vectorstore |
|
|
|
|
|
def get_conversation_chain(vectorstore): |
|
|
|
llm = HuggingFaceHub(repo_id="deepset/roberta-base-squad2", model_kwargs={"temperature":0.5, "max_length":512}) |
|
|
|
memory = ConversationBufferMemory( |
|
memory_key='chat_history', return_messages=True) |
|
conversation_chain = ConversationalRetrievalChain.from_llm( |
|
llm=llm, |
|
retriever=vectorstore.as_retriever(), |
|
memory=memory |
|
) |
|
return conversation_chain |
|
|
|
|
|
def handle_userinput(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): |
|
if i % 2 == 0: |
|
st.write(user_template.replace( |
|
"{{MSG}}", message.content), unsafe_allow_html=True) |
|
else: |
|
st.write(bot_template.replace( |
|
"{{MSG}}", message.content), unsafe_allow_html=True) |
|
|
|
|
|
def main(): |
|
load_dotenv() |
|
st.set_page_config(page_title="Power GPT", |
|
page_icon=":books:") |
|
st.write(css, unsafe_allow_html=True) |
|
|
|
if "conversation" not in st.session_state: |
|
st.session_state.conversation = None |
|
if "chat_history" not in st.session_state: |
|
st.session_state.chat_history = None |
|
|
|
st.header("Power GPT :books:") |
|
user_question = st.text_input("Ask a question about your documents:") |
|
if user_question: |
|
handle_userinput(user_question) |
|
|
|
with st.sidebar: |
|
st.subheader("Your documents") |
|
pdf_docs = st.file_uploader( |
|
"Upload your Documents here", accept_multiple_files=True) |
|
if st.button("Submit"): |
|
with st.spinner("Processing"): |
|
|
|
raw_text = get_pdf_text(pdf_docs) |
|
|
|
|
|
text_chunks = get_text_chunks(raw_text) |
|
|
|
|
|
vectorstore = get_vectorstore(text_chunks) |
|
|
|
|
|
st.session_state.conversation = get_conversation_chain(vectorstore) |
|
|
|
|
|
if __name__ == '__main__': |
|
main() |
