Update app1.py

app1.py

@@ -1,3 +1,25 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+def respond(message, history, 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
+
+def clear_history():
+    return [], ""
+
 demo = gr.ChatInterface(
     respond,
     title="MediPro",