Update app.py

app.py

@@ -1,6 +1,5 @@
-!pip install streamlit transformers PyPDF2 faiss-cpu
 import streamlit as st
-import PyPDF2 # Now PyPDF2 should be found 
+import PyPDF2
 from transformers import RagTokenizer, RagRetriever, RagSequenceForGeneration
 
 # Load PDF and extract text
@@ -22,8 +21,11 @@ def initialize_rag_model():
 
 # Process user query
 def generate_answer(query, context, tokenizer, retriever, model):
+    # Retrieve the relevant documents
     inputs = tokenizer(query, return_tensors="pt")
-    inputs["context_input_ids"] = retriever(context, return_tensors="pt")["input_ids"]
+    # Get the context input IDs from the retriever
+    context_input_ids = retriever(context, return_tensors="pt")["input_ids"]
+    inputs["context_input_ids"] = context_input_ids
     outputs = model.generate(**inputs)
     answer = tokenizer.batch_decode(outputs, skip_special_tokens=True)
     return answer[0]
@@ -31,7 +33,7 @@ def generate_answer(query, context, tokenizer, retriever, model):
 # Streamlit UI
 st.title("PDF Question-Answer Chatbot")
 
-uploaded_file = st.file_uploader("/content/Rag Comprehensive notes with example.pdf", type=["pdf"])
+uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
 if uploaded_file is not None:
     text = load_pdf(uploaded_file)
     st.write("PDF loaded successfully. You can now ask questions.")