File size: 3,916 Bytes
2507f18 15b3a93 2507f18 fa906b4 2507f18 15b3a93 9f54505 2507f18 699a81e 2507f18 027f572 2507f18 027f572 11cc708 027f572 c7b5eb9 15b3a93 027f572 15b3a93 027f572 2507f18 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 |
import tempfile
import streamlit as st
from streamlit_chat import message
import torch
import torch.nn
import transformers
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
HfArgumentParser,
TrainingArguments,
pipeline,
logging,
)
import pandas as pd
import numpy as np
import os
import io
from langchain.document_loaders import TextLoader
from langchain import PromptTemplate
from langchain.text_splitter import CharacterTextSplitter
from langchain.document_loaders import PyPDFLoader
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.chains.question_answering import load_qa_chain
from langchain.chains import RetrievalQA
from langchain import HuggingFacePipeline
from langchain.chains import ConversationalRetrievalChain
from helper import pdf_loader,splitDoc,makeEmbeddings,create_flan_t5_base
def conversational_chat(chain,query):
result = chain({"question": query,
"chat_history": st.session_state['history']})
st.session_state['history'].append((query, result["answer"]))
return result["answer"]
def ui():
st.title('PDF Question Answer Bot')
# hugging_face_key = os.environ["HUGGINGFACE_HUB_TOKEN"]
llm = create_flan_t5_base(load_in_8bit=False)
hf_llm = HuggingFacePipeline(pipeline=llm)
uploaded_file = st.file_uploader("Choose a PDF file", type=["pdf"])
#saving the uploaded pdf file
if uploaded_file is not None:
save_path = "./uploaded_file.pdf"
with open(save_path, "wb") as f:
f.write(uploaded_file.read())
#loading the pdf file
pdf_doc=pdf_loader('./uploaded_file.pdf')
pdf_doc=splitDoc(pdf_doc)
vector_database = makeEmbeddings(pdf_doc)
#making the retriever of the vector database
retriever = vector_database.as_retriever(search_kwargs={"k":10})
qa_chain = ConversationalRetrievalChain.from_llm(llm = hf_llm,
retriever=vector_database.as_retriever())
# Create an empty container to hold the PDF loader section
pdf_loader_container = st.empty()
# Check if the PDF file is uploaded or not
if uploaded_file is not None:
st.text("The file has been uploaded successfully")
# Hide the PDF loader interface when the file is uploaded
pdf_loader_container.empty()
# Show the chat interface
show_chat_interface(qa_chain)
def show_chat_interface(qa_chain):
if 'history' not in st.session_state:
st.session_state['history'] = []
if 'generated' not in st.session_state:
st.session_state['generated'] = ["Hello ! Ask me anything about the Uploaded PDF " + " 🤗"]
if 'past' not in st.session_state:
st.session_state['past'] = ["Hey ! 👋"]
response_container = st.container()
#container for the user's text input
container = st.container()
with container:
with st.form(key='my_form', clear_on_submit=True):
user_input = st.text_input("Query:", placeholder="Talk about your PDF data here (:", key='input')
submit_button = st.form_submit_button(label='Send')
if submit_button and user_input:
output = conversational_chat(qa_chain,user_input)
st.session_state['past'].append(user_input)
st.session_state['generated'].append(output)
if st.session_state['generated']:
with response_container:
for i in range(len(st.session_state['generated'])):
message(st.session_state["past"][i], is_user=True, key=str(i) + '_user', avatar_style="big-smile")
message(st.session_state["generated"][i], key=str(i), avatar_style="thumbs")
if __name__=='__main__':
ui() |