Spaces:
Runtime error
Runtime error
File size: 2,448 Bytes
e778d13 |
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 |
import streamlit as st
from transformers import BertForQuestionAnswering, BertTokenizer
import torch
from io import BytesIO
import PyPDF2
import pandas as pd
# Initialize session state to store the log of QA pairs and satisfaction responses
if 'qa_log' not in st.session_state:
st.session_state.qa_log = []
def extract_text_from_pdf(pdf_file):
pdf_reader = PyPDF2.PdfReader(BytesIO(pdf_file.read()))
text = ""
for page in pdf_reader.pages:
text += page.extract_text()
return text
def answer_question(question, context, model, tokenizer):
inputs = tokenizer.encode_plus(
question,
context,
add_special_tokens=True,
return_tensors="pt",
truncation="only_second",
max_length=512,
)
outputs = model(**inputs, return_dict=True)
answer_start_scores = outputs.start_logits
answer_end_scores = outputs.end_logits
answer_start = torch.argmax(answer_start_scores)
answer_end = torch.argmax(answer_end_scores) + 1
input_ids = inputs["input_ids"].tolist()[0]
answer = tokenizer.convert_tokens_to_string(
tokenizer.convert_ids_to_tokens(input_ids[answer_start:answer_end])
)
return answer
st.title("Resume Question Answering")
uploaded_file = st.file_uploader("Upload your resume (PDF format only)", type=["pdf"])
if uploaded_file is not None:
resume_text = extract_text_from_pdf(uploaded_file)
st.write("Resume Text:")
st.write(resume_text)
user_question = st.text_input("Ask a question based on your resume:")
if user_question:
model = BertForQuestionAnswering.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
tokenizer = BertTokenizer.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
answer = answer_question(user_question, resume_text, model, tokenizer)
st.write("Answer:")
st.write(answer)
# Ask for user feedback on satisfaction
satisfaction = st.radio('Are you satisfied with the answer?', ('Yes', 'No'), key='satisfaction')
# Log the interaction
st.session_state.qa_log.append({
'Question': user_question,
'Answer': answer,
'Satisfaction': satisfaction
})
# Display the log in a table format
st.write("Interaction Log:")
log_df = pd.DataFrame(st.session_state.qa_log)
st.dataframe(log_df)
|