Update app.py

app.py

@@ -1,11 +1,8 @@
 import gradio as gr
-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")
+import requests
 
+# Replace with your actual ngrok URL from Colab
+COLAB_BACKEND_URL = "https://215d-34-124-237-140.ngrok-free.app/"
 
 def respond(
     message,
@@ -15,50 +12,38 @@ def respond(
     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
-"""
+    # Construct the prompt with chat history and system prompt
+    full_prompt = system_message.strip() + "\n\n"
+    for user_msg, bot_msg in history:
+        if user_msg:
+            full_prompt += f"User: {user_msg.strip()}\n"
+        if bot_msg:
+            full_prompt += f"AI: {bot_msg.strip()}\n"
+    full_prompt += f"User: {message.strip()}\nAI:"
+
+    try:
+        # Send the prompt and generation parameters to the Colab backend
+        response = requests.post(COLAB_BACKEND_URL, json={
+            "prompt": full_prompt,
+            "max_tokens": max_tokens,
+            "temperature": temperature,
+            "top_p": top_p,
+        })
+        reply = response.json().get("response", "")
+        yield reply.strip()
+    except Exception as e:
+        yield f"[Error contacting backend: {str(e)}]"
+
+# Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a flirty, romantic AI girlfriend.", 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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.95, 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()