update system prompt

app.py

@@ -1,40 +1,49 @@
 import gradio as gr
-from transformers import pipeline
-import os
-
-# Retrieve the Hugging Face API token from environment variables
-hf_token = os.getenv("HF_TOKEN")
-
-if not hf_token:
-    raise ValueError("API token is not set. Please set the HF_TOKEN environment variable in Space Settings.")
-
-def authenticate_and_generate(message, history, system_message, max_tokens, temperature, top_p):
-    try:
-        # Initialize the text-generation pipeline without use_auth_token if not needed
-        text_generator = pipeline("text-generation", model="gpt2")
-        
-        # Ensure that system_message is a string
-        system_message = str(system_message)
-        
-        # Construct the prompt with system message, history, and user input
-        history_str = "\n".join([f"User: {str(msg[0])}\nAssistant: {str(msg[1])}" for msg in history if isinstance(msg, (tuple, list)) and len(msg) == 2])
-        prompt = system_message + "\n" + history_str
-        prompt += f"\nUser: {message}\nAssistant:"
-
-        # Generate a response using the model
-        response = text_generator(prompt, max_length=max_tokens, temperature=temperature, top_p=top_p, do_sample=True, truncation=True)
-
-        # Extract the generated text from the response list
-        assistant_response = response[0]['generated_text']
-        # Optionally trim the assistant response if it includes the prompt again
-        assistant_response = assistant_response.split("Assistant:", 1)[-1].strip()
-        return assistant_response
-
-    except Exception as e:
-        return str(e)  # Return the error message for debugging
-
-athena = gr.ChatInterface(
-    fn=authenticate_and_generate,
+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="""
@@ -52,11 +61,18 @@ athena = gr.ChatInterface(
             """,
             label="System message"
         ),
-        gr.Slider(minimum=1, maximum=4096, value=512, step=1, label="Max new tokens"),
+        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)"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
     ],
 )
 
+
 if __name__ == "__main__":
-    athena.launch()
+    demo.launch()