ChatPdf / app.py
Aabbhishekk's picture
Update app.py
cc58b68 verified
import streamlit as st
import os
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.chains.question_answering import load_qa_chain
from langchain.callbacks import get_openai_callback
from langchain import HuggingFaceHub, LLMChain
from langchain.embeddings import HuggingFaceHubEmbeddings,HuggingFaceInferenceAPIEmbeddings
token = os.environ['HF_TOKEN']
repo_id = "sentence-transformers/all-mpnet-base-v2"
hf = HuggingFaceHubEmbeddings(
repo_id=repo_id,
task="feature-extraction",
huggingfacehub_api_token= token,
)
# from langchain.embeddings import HuggingFaceInferenceAPIEmbeddings
# embeddings = HuggingFaceInferenceAPIEmbeddings(
# api_key=token, model_name="sentence-transformers/all-MiniLM-l6-v2"
# )
# hf = HuggingFaceHubEmbeddings(
# repo_id=repo_id,
# task="feature-extraction",
# huggingfacehub_api_token= HUGGINGFACEHUB_API_TOKEN,
# )
def main():
st.set_page_config(page_title="Ask your PDF")
st.header("Ask your PDF πŸ’¬")
# upload file
pdf = st.file_uploader("Upload your PDF", type="pdf")
# extract the text
if pdf is not None:
pdf_reader = PdfReader(pdf)
text = ""
for page in pdf_reader.pages:
text += page.extract_text()
# split into chunks
text_splitter = CharacterTextSplitter(
separator="\n",
chunk_size=1000,
chunk_overlap=200,
length_function=len
)
chunks = text_splitter.split_text(text)
# create embeddings
# embeddings = OpenAIEmbeddings()
# embeddings = query(chunks)
# embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
knowledge_base = FAISS.from_texts(chunks, hf)
# show user input
user_question = st.text_input("Ask a question about your PDF:")
if user_question:
docs = knowledge_base.similarity_search(user_question)
# llm = OpenAI()
hub_llm = HuggingFaceHub(
repo_id='mistralai/Mistral-7B-Instruct-v0.3',
model_kwargs={'temperature':0.01,"max_length": 2048,},
huggingfacehub_api_token=token)
llm = hub_llm
chain = load_qa_chain(llm, chain_type="map_reduce")
with get_openai_callback() as cb:
response = chain.run(input_documents=docs, question=[user_question])
# print(cb)
st.write(response)
if __name__ == '__main__':
main()