Update app.py (#2)

- Update app.py (97048a68d6668d7e8d1b3e8e76a7642ce905a50b)


Co-authored-by: nadia elghouti <[email protected]>

app.py

@@ -1,9 +1,14 @@
+this is what i have in the app 
+
 import gradio as gr
 from huggingface_hub import InferenceClient
-from fastapi.middleware.cors import CORSMiddleware
 
+"""
+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]],
@@ -13,9 +18,33 @@ def respond(
     top_p,
 ):
     messages = [{"role": "system", "content": system_message}]
-    
-    # ... (rest of your respond function remains the same)
 
+    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
+"""
 # Create Gradio app with queue enabled
 app = gr.ChatInterface(
     respond,