Update app.py

app.py

@@ -1,26 +1,46 @@
+from huggingface_hub import InferenceClient
 import gradio as gr
-import random
-import time
+
+client = InferenceClient()
+
+def respond(
+    prompt: str,
+    history,
+):
+    if not history:
+        history = [{"role": "system", "content": "You are a friendly chatbot"}]
+    history.append({"role": "user", "content": prompt})
+
+    yield history
+
+    response = {"role": "assistant", "content": ""}
+    for message in client.chat_completion(
+        history,
+        temperature=0.95,
+        top_p=0.9,
+        max_tokens=512,
+        stream=True,
+        model="HuggingFaceH4/zephyr-7b-beta"
+    ):
+        response["content"] += message.choices[0].delta.content or ""
+
+        yield history + [response]
+
 
 with gr.Blocks() as demo:
-    chatbot = gr.Chatbot(type="messages")
-    msg = gr.Textbox()
-    clear = gr.Button("Clear")
-
-    def user(user_message, history: list):
-        return "", history + [{"role": "user", "content": user_message}]
-
-    def bot(history: list):
-        bot_message = random.choice(["How are you?", "I love you", "I'm very hungry"])
-        history.append({"role": "assistant", "content": ""})
-        for character in bot_message:
-            history[-1]['content'] += character
-            time.sleep(0.05)
-            yield history
-
-    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
-        bot, chatbot, chatbot
+    gr.Markdown("# Chat with Hugging Face Zephyr 7b 🤗")
+    chatbot = gr.Chatbot(
+        label="Agent",
+        type="messages",
+        avatar_images=(
+            None,
+            "https://em-content.zobj.net/source/twitter/376/hugging-face_1f917.png",
+        ),
     )
-    clear.click(lambda: None, None, chatbot, queue=False)
+    prompt = gr.Textbox(max_lines=1, label="Chat Message")
+    prompt.submit(respond, [prompt, chatbot], [chatbot])
+    prompt.submit(lambda: "", None, [prompt])
+
 
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()