Spaces:
Sleeping
Sleeping
File size: 3,007 Bytes
85038b5 0319d49 f2e9fda 85038b5 6eea86b b48ee26 85038b5 4b12318 addd4ac 05de07f 85038b5 971fc58 85038b5 05de07f 85038b5 34d4635 07b7ab2 482ed46 fcc64aa 00e6e5e 2ca71d8 84536d7 85038b5 |
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 |
import streamlit as st
from PIL import Image
from dotenv import load_dotenv
from streamlit_extras.add_vertical_space import add_vertical_space
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings
from langchain.vectorstores import chroma
from langchain.chains.retrieval_qa.base import RetrievalQA
from langchain.chains.question_answering import load_qa_chain
from langchain_community.llms import huggingface_hub
from langchain.document_loaders.pdf import PyMuPDFLoader
from transformers import AutoTokenizer, AutoModelForCausalLM
from langchain_core.vectorstores import VectorStoreRetriever
#from langchain.llms import huggingface_endpoint
import os
#import fitz
#import tempfile
from langchain.chains.summarize import load_summarize_chain
img = Image.open('image/nexio_logo1.png')
st.set_page_config(page_title="PDF Chatbot App",page_icon=img,layout="centered")
with st.sidebar:
st.title('🤖 AI PDF Chatbot 💬')
st.markdown('''
## About
This app is an AI chatbot for the PDF files
''')
add_vertical_space(12)
st.write('Powered by ')
st.image(image='image/nexio_logo2.png',width=150)
# load huggingface API key .env file
load_dotenv()
def main():
st.header("Chat with PDF 💬")
# upload pdf file
pdf = st.file_uploader("Upload your PDF file",type='pdf')
if pdf is not None:
pdf_reader = PdfReader(pdf)
text = ""
for page in pdf_reader.pages:
text += page.extract_text()
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=1000,
chunk_overlap=200,
length_function=len
)
chunks = text_splitter.split_text(text=text)
chunks_doc = text_splitter.create_documents(text)
# embeddings
embeddings = HuggingFaceEmbeddings()
vector_store = chroma.Chroma.from_texts(chunks,embeddings)
# Accept user question
query = st.text_input("Ask questions about your PDF file:")
if query:
#PATH = 'model/'
#llm = AutoModelForCausalLM.from_pretrained("openai-community/gpt2-medium")
llm = huggingface_hub.HuggingFaceHub(repo_id="openai-community/gpt2-medium",model_kwargs={"temperature":1.0, "max_length":500})
#docs = vector_store.similarity_search(query=query, k=1)
#st.write(docs)
#chain = load_qa_chain(llm=llm, chain_type="stuff")
#response = chain.run(input_documents=docs, question=query)
retriever=vector_store.similarity_search(query)
st.write(retriever[0].page_content)
#chain = RetrievalQA.from_chain_type(llm=llm,chain_type="stuff",retriever=retriever[0].page_content)
#response = chain.run(query)
#st.write(response)
if __name__ == '__main__':
main()
|