Update app.py

app.py

@@ -1,43 +1,64 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-# Load the model from Hugging Face Hub
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")  # Replace with your model name if different
-
-def generate_real_world_connection(grade, topic):
-    """
-    Generates a real-world connection for a science lesson based on user input.
-
-    Args:
-        grade: The grade level of the student (str).
-        topic: The science topic (str).
-
-    Returns:
-        A string containing the generated real-world connection.
-    """
-
-    prompt = f"Create a real-world connection for a {grade} science lesson on topic {topic}."
-    response = client.text_generation(
-        text=prompt,  # Use 'text' instead of 'inputs'
-        max_length=1024,
-        do_sample=True,
-        temperature=0.7,
-        top_p=0.95,
-    )
-    generated_text = response["generated_text"][0]
-    return generated_text.strip()
-
-# Define the Gradio interface
-interface = gr.Interface(
-    fn=generate_real_world_connection,
-    inputs=[
-        gr.Textbox(label="Grade Level (e.g., 5th)"),
-        gr.Textbox(label="Science Topic"),
+"""
+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. You answer in a funny tone with a joke in each response", 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)",
+        ),
     ],
-    outputs="text",
-    title="Real-World Connection Generator",
-    description="Generate real-world connections for science lessons using a large language model."
 )
 
+
 if __name__ == "__main__":
-    interface.launch()
+    demo.launch()