Update app.py

app.py

@@ -1,64 +1,40 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    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
-
-        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()
+from transformers import pipeline
+
+# Load Question Answering Pipelines
+qa_models = {
+    "🤖 DistilBERT (SQuAD)": pipeline("question-answering", model="distilbert-base-uncased-distilled-squad"),
+    "🌱 TinyRoBERTa (SQuAD2)": pipeline("question-answering", model="deepset/tinyroberta-squad2"),
+    "📘 BERT Base (SQuAD)": pipeline("question-answering", model="bert-base-uncased", tokenizer="bert-base-uncased")
+}
+
+# Inference Function
+def answer_question(question, context, model_name):
+    model = qa_models[model_name]
+    result = model(question=question, context=context)
+    return result["answer"]
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("<h1 style='text-align: center; color: darkorange; font-weight: bold;'>Question Answering with Lightweight LLMs</h1>")
+    gr.Markdown("<div style='text-align: center;'>Ask questions based on the provided context using free LLMs.</div>")
+    
+    with gr.Row():
+        with gr.Column():
+            context = gr.Textbox(label="📄 Context", lines=6, placeholder="Paste your paragraph here...")
+            question = gr.Textbox(label="❓ Question", placeholder="Type your question here...")
+            model_choice = gr.Radio(
+                ["🤖 DistilBERT (SQuAD)", "🌱 TinyRoBERTa (SQuAD2)", "📘 BERT Base (SQuAD)"],
+                label="Select a Model"
+            )
+            submit = gr.Button("Get Answer")
+
+        with gr.Column():
+            answer = gr.Textbox(label="✅ Answer", lines=2)
+
+    submit.click(fn=answer_question, inputs=[question, context, model_choice], outputs=answer)
+    
+    gr.Markdown("<div style='text-align: center; color: darkorange;'>Designed by Mehak Mazhar</div>")
+
+# Set background color via CSS
+demo.launch(css="body { background-color: #FFF3E0; }")