Basic steps

app.py

@@ -1,64 +1,30 @@
 import gradio as gr
+import random
 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")
+client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
 
+def echo(message, history):
+    choices = ["yes", "no", "silly ahh question", "not likely", "ask again", "absolutely", "YASSS"]
+    yes_or_no = random.choice(choices)
+    return yes_or_no
 
-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]})
-
+def respond(message, history):
+    messages = [{"role": "system", "content": "You are a sassy chatbot from the 1800s."}]
+    if history:
+        messages.extend(history)
     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,
+        max_tokens = 100,
+        stream = True,
     ):
         token = message.choices[0].delta.content
-
         response += token
         yield response
+    
+chatbot = gr.ChatInterface(respond, type = "messages")
 
-
-"""
-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()
+chatbot.launch()