Create app.py

app.py

@@ -0,0 +1,57 @@
+import streamlit as st
+from PyPDF2 import PdfReader
+from transformers import RagTokenizer, RagRetriever, RagSequenceForGeneration
+import torch
+
+# Load RAG model and tokenizer
+tokenizer = RagTokenizer.from_pretrained("facebook/rag-sequence")
+retriever = RagRetriever.from_pretrained("facebook/rag-sequence", use_dummy_dataset=True)
+model = RagSequenceForGeneration.from_pretrained("facebook/rag-sequence")
+
+# Function to process PDF
+def read_pdf(file):
+    text = ""
+    pdf_reader = PdfReader(file)
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+    return text
+
+# Function to answer the question
+def answer_question(question, context):
+    input_dict = tokenizer.prepare_seq2seq_batch(
+        src_texts=[question],
+        return_tensors="pt",
+        padding=True,
+        truncation=True
+    )
+    # Retrieve relevant documents
+    input_ids = input_dict["input_ids"]
+    context_ids = retriever(input_ids, return_tensors="pt")['input_ids']
+    
+    # Generate answer
+    outputs = model.generate(input_ids=input_ids, context_input_ids=context_ids)
+    answer = tokenizer.batch_decode(outputs, skip_special_tokens=True)
+    return answer[0]
+
+# Streamlit frontend
+st.title("PDF Question-Answering Chatbot")
+
+uploaded_file = st.file_uploader("Upload a PDF file", type="pdf")
+
+if uploaded_file is not None:
+    # Read PDF
+    pdf_text = read_pdf(uploaded_file)
+    st.success("PDF file processed successfully.")
+
+    # Text area for user input
+    question = st.text_input("Ask a question about the PDF content:")
+    
+    if question:
+        # Get the answer
+        answer = answer_question(question, pdf_text)
+        st.subheader("Answer:")
+        st.write(answer)
+
+# Run the application
+if __name__ == "__main__":
+    st.run()