Create app.py

app.py

@@ -0,0 +1,44 @@
+import streamlit as st
+import torch
+from transformers import BartForConditionalGeneration, BartTokenizer
+
+# Load the model and tokenizer
+model_repo_path = 'AbdurRehman313/hotpotQA_BART_Finetuned_E5'
+model = BartForConditionalGeneration.from_pretrained(model_repo_path)
+tokenizer = BartTokenizer.from_pretrained(model_repo_path)
+
+# Ensure the model is in evaluation mode
+model.eval()
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+model.to(device)
+
+# Streamlit app layout
+st.title("Multi-Hop Question Answering Application")
+
+# User input for context and question
+context_input = st.text_area("Enter context", height=200)
+question_input = st.text_area("Enter question")
+
+# Generate the answer
+if st.button("Get Answer"):
+    if context_input and question_input:
+        with st.spinner("Generating answer..."):
+            try:
+                # Prepare the input for the model
+                input_text = f"context: {context_input} question: {question_input}"
+                inputs = tokenizer(input_text, return_tensors='pt')
+                inputs = {key: value.to(device) for key, value in inputs.items()}
+
+                # Perform inference
+                with torch.no_grad():
+                    outputs = model.generate(inputs['input_ids'], max_length=50)
+
+                # Decode the output
+                answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+                st.subheader("Answer")
+                st.write(answer)
+            except Exception as e:
+                st.error(f"Error during question answering: {e}")
+    else:
+        st.warning("Please enter both context and question.")