File size: 3,843 Bytes
407931b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
import os
import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain_openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
# from langchain_community.vectorstores import FAISS
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.chat_models import ChatOpenAI
from htmlTemplates import css, bot_template, user_template
from langchain.embeddings import HuggingFaceInstructEmbeddings
from langchain.llms import HuggingFaceHub
import os
def get_pdf_text(pdf_doc):
text = ""
for pdf in pdf_doc:
pdf_reader = PdfReader(pdf)
for page in pdf_reader.pages:
text += page.extract_text()
return text
def get_text_chunk(row_text):
text_splitter = CharacterTextSplitter(
separator="\n",
chunk_size = 1000,
chunk_overlap = 200,
length_function = len
)
chunk = text_splitter.split_text(row_text)
return chunk
def get_vectorstore(text_chunk):
embeddings = OpenAIEmbeddings(openai_api_key = os.getenv("OPENAI_API_KEY"))
# embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
vector = FAISS.from_texts(text_chunk,embeddings)
return vector
def get_conversation_chain(vectorstores):
llm = ChatOpenAI(openai_api_key = os.getenv("OPENAI_API_KEY"))
# llm = HuggingFaceHub(repo_id="google/flan-t5-base", 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=vectorstores.as_retriever(),
memory=memory)
return conversation_chain
def user_input(user_question):
response = st.session_state.conversation({"question":user_question})
st.session_state.chat_history = response["chat_history"]
for indx, msg in enumerate(st.session_state.chat_history):
if indx % 2==0:
st.write(user_template.replace("{{MSG}}",msg.content), unsafe_allow_html=True)
else:
st.write(bot_template.replace("{{MSG}}", msg.content), unsafe_allow_html=True)
def main():
# load secret key
load_dotenv()
# config the pg
st.set_page_config(page_title="Chat with multiple PDFs" ,page_icon=":books:")
st.write(css, unsafe_allow_html=True)
if "conversation" not in st.session_state:
st.session_state.conversation = None
st.header("Chat with multiple PDFs :books:")
user_question = st.text_input("Ask a question about your docs")
if user_question:
user_input(user_question)
# st.write(user_template.replace("{{MSG}}","Hello Robot"), unsafe_allow_html=True)
# st.write(bot_template.replace("{{MSG}}","Hello Human"), unsafe_allow_html=True)
# create side bar
with st.sidebar:
st.subheader("Your Documents")
pdf_doc = st.file_uploader(label="Upload your documents",accept_multiple_files=True)
if st.button("Process"):
with st.spinner(text="Processing"):
# get pdf text
row_text = get_pdf_text(pdf_doc)
# get the text chunk
text_chunk = get_text_chunk(row_text)
# st.write(text_chunk)
# create vecor store
vectorstores = get_vectorstore(text_chunk)
# st.write(vectorstores)
# create conversation chain
st.session_state.conversation = get_conversation_chain(vectorstores)
if __name__ == "__main__":
main() |