File size: 4,418 Bytes
97bce8f 3916e88 97bce8f c171266 97bce8f c171266 97bce8f 3916e88 97bce8f c171266 97bce8f c171266 97bce8f 4669820 97bce8f 3916e88 97bce8f ec68d04 97bce8f d3f4592 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 |
import streamlit as st
import os
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import GooglePalmEmbeddings
from langchain.llms import GooglePalm
from langchain.vectorstores import FAISS
from langchain.chains import ConversationalRetrievalChain
from langchain.memory import ConversationBufferMemory
os.environ['GOOGLE_API_KEY'] = 'AIzaSyD8uzXToT4I2ABs7qo_XiuKh8-L2nuWCEM'
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(text):
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=20)
chunks = text_splitter.split_text(text)
return chunks
def get_vector_store(text_chunks):
embeddings = GooglePalmEmbeddings()
vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
return vector_store
def get_conversational_chain(vector_store):
llm = GooglePalm()
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=vector_store.as_retriever(), memory=memory)
return conversation_chain
def user_input(user_question):
with st.container():
response = st.session_state.conversation({'question': user_question})
st.session_state.chatHistory = response['chat_history']
file_contents = ""
left , right = st.columns((2,1))
with left:
for i, message in enumerate(st.session_state.chatHistory):
if i % 2 == 0:
st.write("Human:", message.content)
else:
st.write("Bot:", message.content)
st.success("Done !")
with right:
for message in st.session_state.chatHistory:
file_contents += f"{message.content}\n"
file_name = "Chat_History.txt"
st.download_button("Download chat history👈", file_contents, file_name=file_name, mime="text/plain")
def summary(summarization):
with st.container():
file_contents = ''
left , right = st.columns((2,1))
with left:
if summarization:
response1 = st.session_state.conversation({'question': 'Retrieve one-line topics and their descriptors; create detailed, bulleted summaries for each topic.'})
st.write("summary:\n", response1['answer'])
st.success("Done !")
else:
response1 = {}
with right:
file_contents = response1.get('answer', '')
file_name = "summarization_result.txt"
st.download_button("Download Summary", file_contents, file_name=file_name, mime="text/plain")
def main():
st.set_page_config("LOR ChatAI")
st.header("LOR ChatAI")
st.write("---")
with st.container():
with st.sidebar:
st.title("Settings")
st.subheader("Upload your Documents")
pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Process Button", accept_multiple_files=True)
if st.button("Process"):
with st.spinner("Processing"):
raw_text = get_pdf_text(pdf_docs)
text_chunks = get_text_chunks(raw_text)
vector_store = get_vector_store(text_chunks)
st.session_state.conversation = get_conversational_chain(vector_store)
st.success("Done")
with st.container():
# Summarisation Section
st.subheader("PDF Summarisation")
st.write('Click on summary button to get summary on given uploaded file.')
summarization = st.button("Summarise")
summary(summarization)
st.write("---")
with st.container():
# Question Section
st.subheader("PDF question-answer section")
user_question = st.text_input("Ask a Question from the PDF Files")
if "conversation" not in st.session_state:
st.session_state.conversation = None
if "chatHistory" not in st.session_state:
st.session_state.chatHistory = None
if user_question:
user_input(user_question)
st.write('##')
if __name__ == "__main__":
main() |