Spaces:
Runtime error
Runtime error
File size: 3,944 Bytes
31df2d1 9306c69 31df2d1 9306c69 6aaa040 31df2d1 b110556 6aaa040 008e424 31df2d1 6aaa040 31df2d1 b110556 31df2d1 6aaa040 a23cb40 6aaa040 31df2d1 6aaa040 |
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 streamlit as st
# from dotenv import load_dotenv
import pickle
from PyPDF2 import PdfReader
from streamlit_extras.add_vertical_space import add_vertical_space
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.llms import OpenAI
from langchain.chains.question_answering import load_qa_chain
from langchain.callbacks import get_openai_callback
import os
from langchain.vectorstores import Chroma
from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings
from langchain.embeddings import HuggingFaceHubEmbeddings
# Sidebar contents
from langchain.llms import HuggingFaceHub
if 'HuggingFace_API_Key' not in st.session_state:
st.session_state['HuggingFace_API_Key'] = ''
with st.sidebar:
st.title('🤗💬 LLM Chat App')
st.markdown('''
## About
This app is an LLM-powered chatbot
PDF:Chatbot AI-powered chat assistant for PDFs
''')
add_vertical_space(5)
st.session_state['HuggingFace_API_Key'] = st.sidebar.text_input(
"What's your HuggingFace API key?", type="password")
# load_dotenv()
load_button = st.sidebar.button("Submit API Key", key="load_button")
def main():
st.header("Chat with PDF 💬")
pdf = st.file_uploader("Upload your PDF", type='pdf')
if st.session_state['HuggingFace_API_Key'] != "":
# upload a PDF file
# st.write(pdf)
if pdf is not None:
pdf_reader = PdfReader(pdf)
text = ""
for page in pdf_reader.pages:
text += page.extract_text()
# st.write(text)
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=1000,
chunk_overlap=200,
length_function=len
)
chunks = text_splitter.split_text(text=text)
# # embeddings
store_name = pdf.name[:-4]
# st.write(f'{store_name}')
# st.write(chunks)
if os.path.exists(f"{store_name}.pkl"):
with open(f"{store_name}.pkl", "rb") as f:
VectorStore = pickle.load(f)
# st.write('Embeddings Loaded from the Disk')s
else:
# embeddings = OpenAIEmbeddings(
# openai_api_key='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')
# embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
embeddings = HuggingFaceHubEmbeddings(
huggingfacehub_api_token=st.session_state['HuggingFace_API_Key'])
VectorStore = FAISS.from_texts(
chunks, embedding=embeddings)
# VectorStore=Chroma.from_documents(chunks, embeddings)
with open(f"{store_name}.pkl", "wb") as f:
pickle.dump(VectorStore, f)
# embeddings = OpenAIEmbeddings()
# VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
# Accept user questions/query
query = st.text_input("Ask questions about your PDF file:")
# st.write(query)
if query:
docs = VectorStore.similarity_search(query=query, k=3)
llm = HuggingFaceHub(repo_id='google/flan-ul2',
huggingfacehub_api_token=st.session_state['HuggingFace_API_Key'], model_kwargs={"temperature": 0.1, "max_new_tokens": 500})
# llm = OpenAI()
chain = load_qa_chain(llm=llm, chain_type="stuff")
response = chain.run(input_documents=docs, question=query)
# with get_openai_callback() as cb:
# response = chain.run(input_documents=docs, question=query)
# print(cb)
st.write(response)
if __name__ == '__main__':
main() |