Spaces:
Sleeping
Sleeping
File size: 2,282 Bytes
cbc6f35 c8862b8 405d7a9 8ec4279 b9c3d84 cbc6f35 c8862b8 cbc6f35 405d7a9 cbc6f35 405d7a9 8ec4279 405d7a9 8ec4279 405d7a9 519d51e 405d7a9 cbc6f35 405d7a9 cbc6f35 |
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 |
import streamlit as st
import os
from tempfile import NamedTemporaryFile
from langchain.document_loaders import PyPDFLoader
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import Chroma
from langchain import PromptTemplate, LLMChain
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
# Function to save the uploaded PDF to a temporary file
def save_uploaded_file(uploaded_file):
with NamedTemporaryFile(delete=False, suffix=".pdf") as temp_file:
temp_file.write(uploaded_file.read())
return temp_file.name
# Streamlit UI
st.title("PDF Question Answering App")
uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
if uploaded_file is not None:
# Save the uploaded file to a temporary location
temp_file_path = save_uploaded_file(uploaded_file)
# Load the PDF document using PyPDFLoader
loader = PyPDFLoader(temp_file_path)
pages = loader.load_and_split()
# Initialize embeddings and Chroma
embed = HuggingFaceEmbeddings()
db = Chroma.from_documents(pages, embed)
# Define a function to get answers
def get_answer(question):
doc = db.similarity_search(question, k=4)
context = doc[0].page_content + doc[1].page_content + doc[2].page_content + doc[3].page_content
#max_seq_length = 512 # You may define this based on your model
#context = context[:max_seq_length]
# Load the model & tokenizer for question-answering
model_name = "deepset/roberta-base-squad2"
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Create a question-answering pipeline
nlp = pipeline("question-answering", model=model, tokenizer=tokenizer)
# Prepare the input
QA_input = {
"question": question,
"context": context,
}
# Get the answer
result = nlp(**QA_input)
return result["answer"]
question = st.text_input("Enter your question:")
if st.button("Get Answer"):
answer = get_answer(question)
st.write("Answer:")
st.write(answer)
# Cleanup: Delete the temporary file
os.remove(temp_file_path)
|