added to update

app.py

@@ -1,64 +1,33 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+import streamlit as st
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# Set page config FIRST — must be the first Streamlit command
+st.set_page_config(page_title="BERT QA", layout="wide")
 
+from transformers import pipeline
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Load QA pipeline with BERT model
+@st.cache_resource
+def load_qa_pipeline():
+    model_name = "deepset/bert-large-uncased-whole-word-masking-squad2"
+    return pipeline("question-answering", model=model_name, tokenizer=model_name)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+nlp = load_qa_pipeline()
 
-    messages.append({"role": "user", "content": message})
+# Streamlit UI
+st.title("🤖 BERT-based Q&A using HuggingFace")
 
-    response = ""
+context = st.text_area("📄 Enter Context", height=200, value="""
+Trainer: Jai Ganesh S;
+Session 1: Intro about Arenas & LLMs;
+Session 2: Hands-on on LLMs
+Session 3: LangChain - Intro
+""")
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+question = st.text_input("❓ Ask a Question", value="What's the session 1?")
 
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+if st.button("Get Answer"):
+    with st.spinner("Thinking..."):
+        QA_input = {"question": question, "context": context}
+        result = nlp(QA_input)
+        st.success(f"🧠 **Answer**: {result['answer']}")
+        st.caption(f"Score: {result['score']:.2f} | Start: {result['start']}, End: {result['end']}")