Create app.py

app.py

@@ -0,0 +1,48 @@
+import streamlit as st
+from transformers import AutoModelForQuestionAnswering, AutoTokenizer
+import torch
+
+# Load the saved model and tokenizer
+@st.cache_resource
+def load_model():
+    model_path = "./bert_qa_model"
+    model = AutoModelForQuestionAnswering.from_pretrained(model_path)
+    tokenizer = AutoTokenizer.from_pretrained(model_path)
+    return model, tokenizer
+
+model, tokenizer = load_model()
+
+def answer_question(context, question):
+    # Tokenize input
+    inputs = tokenizer(question, context, return_tensors="pt")
+    
+    # Get model output
+    with torch.no_grad():
+        outputs = model(**inputs)
+    
+    # Get start and end logits
+    answer_start = torch.argmax(outputs.start_logits)
+    answer_end = torch.argmax(outputs.end_logits) + 1
+    
+    # Decode the answer
+    answer = tokenizer.decode(inputs["input_ids"][0][answer_start:answer_end])
+    
+    return answer
+
+# Streamlit app
+st.title("Question Answering System")
+
+st.write("Enter a context and a question, and the model will provide an answer based on the context.")
+
+context = st.text_area("Context", height=200)
+question = st.text_input("Question")
+
+if st.button("Get Answer"):
+    if context and question:
+        answer = answer_question(context, question)
+        st.success(f"Answer: {answer}")
+    else:
+        st.error("Please provide both context and question.")
+
+st.markdown("---")
+st.write("Powered by Hugging Face Transformers and Streamlit")