Create app.py

app.py

@@ -0,0 +1,57 @@
+import os
+import PyPDF2
+from typing import Dict
+from transformers import BertTokenizerFast, BertForQuestionAnswering
+import torch
+import streamlit as st
+
+# Load the pre-trained model and tokenizer
+tokenizer = BertTokenizerFast.from_pretrained("bert-base-uncased")
+model = BertForQuestionAnswering.from_pretrained("bert-base-uncased")
+
+def extract_text_from_pdf(pdf_path):
+    with open(pdf_path, "rb") as file:
+        reader = PyPDF2.PdfFileReader(file)
+        text = ""
+        for page_num in range(reader.getNumPages()):
+            text += reader.getPage(page_num).extractText()
+    return text
+
+def preprocess_text(question, context):
+    inputs = tokenizer(question, context, return_tensors="pt")
+    return inputs
+
+def question_answering_system(question, pdf_path):
+    context = extract_text_from_pdf(pdf_path)
+    inputs = preprocess_text(question, context)
+    start_scores, end_scores = model(**inputs)
+    
+    start_index = torch.argmax(start_scores)
+    end_index = torch.argmax(end_scores) + 1
+    answer_tokens = inputs["input_ids"][0][start_index:end_index]
+    
+    answer = tokenizer.convert_ids_to_tokens(answer_tokens)
+    return " ".join(answer)
+
+# Set up Streamlit app
+st.set_page_config(page_title="PDF Question Answering", layout="wide")
+
+st.title("PDF Question Answering System")
+st.write("Upload a PDF file and enter a question related to its content.")
+
+pdf_file = st.file_uploader("Upload PDF File", type=["pdf"])
+if pdf_file:
+    uploaded_file_name = pdf_file.name
+else:
+    uploaded_file_name = ""
+
+question = st.text_input("Enter your question:", key="question")
+
+if pdf_file and question:
+    try:
+        answer = question_answering_system(question, uploaded_file_name)
+        st.success(f"Answer: {answer}")
+    except Exception as e:
+        st.error(f"Error: {str(e)}")
+
+st.markdown("Made with ❤️ by [Streamlit](https://streamlit.io/) and [Hugging Face Transformers](https://huggingface.co/transformers/)")