Spaces:
No application file
No application file
File size: 2,510 Bytes
6cc785b |
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 |
import streamlit as st
from langchain.text_splitter import CharacterTextSplitter
from langchain.docstore.document import Document
from langchain.chains.summarize import load_summarize_chain
from langchain_community.llms import CTransformers
from langchain.callbacks.manager import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from pypdf import PdfReader
# Page title
st.set_page_config(page_title='🦜🔗 Text Summarization App')
st.title('🦜🔗 Text Summarization App')
# Function to read all PDF files and return text
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
# Function to split the text into smaller chunks and convert it into document format
def chunks_and_document(txt):
text_splitter = CharacterTextSplitter()
texts = text_splitter.split_text(txt)
docs = [Document(page_content=t) for t in texts]
return docs
# Loading the Llama 2's LLM
def load_llm():
# We instantiate the callback with a streaming stdout handler
callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
# Loading the LLM model
llm = CTransformers(
model="llama-2-7b-chat.ggmlv3.q2_K.bin",
model_type="llama",
config={'max_new_tokens': 600,
'temperature': 0.5,
'context_length': 700}
)
return llm
# Function to apply the LLM model with our document
def chains_and_response(docs):
llm = load_llm()
chain = load_summarize_chain(llm, chain_type='map_reduce')
return chain.invoke(docs)
def main():
# Initialize messages if not already present
if "messages" not in st.session_state.keys():
st.session_state.messages = []
# Sidebar for uploading PDF files
with st.sidebar:
st.title("Menu:")
pdf_docs = st.file_uploader(
"Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True
)
if st.button("Submit & Process"):
with st.spinner("Processing..."):
txt_input = get_pdf_text(pdf_docs)
docs = chunks_and_document(txt_input)
response = chains_and_response(docs)
st.title('📝✅ Summarization Result')
for res in response:
st.info(res)
main()
|