Update app.py

app.py

@@ -1,64 +1,94 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import json
 
-"""
-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("davnas/lora_model")
-
-
-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})
+# Initialize the client with the token
+client = InferenceClient(
+    model="davnas/Italian_Cousine_2.1",
+    headers={"Content-Type": "application/json"}
+)
 
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    # Format the prompt including history and system message
+    conversation = []
+    
+    # Add system message if provided
+    if system_message:
+        conversation.append({"role": "system", "content": system_message})
+    
+    # Add conversation history
+    for user_msg, assistant_msg in history:
+        conversation.append({"role": "user", "content": user_msg})
+        conversation.append({"role": "assistant", "content": assistant_msg})
+    
+    # Add current message
+    conversation.append({"role": "user", "content": message})
+    
+    # Convert conversation to prompt format
+    prompt = ""
+    for msg in conversation:
+        if msg["role"] == "system":
+            prompt += f"{msg['content']}\n"
+        elif msg["role"] == "user":
+            prompt += f"User: {msg['content']}\n"
+        elif msg["role"] == "assistant":
+            prompt += f"Assistant: {msg['content']}\n"
+    
+    prompt += "Assistant:"
+    
+    # Prepare parameters for text generation
+    parameters = {
+        "max_new_tokens": max_tokens,
+        "temperature": temperature,
+        "top_p": top_p,
+        "return_full_text": False
+    }
+    
     response = ""
+    try:
+        # Use generate_text with proper parameters
+        for token in client.text_generation(
+            prompt,
+            stream=True,
+            **parameters
+        ):
+            response += token
+            yield response
+    except Exception as e:
+        yield f"Error: {str(e)}"
 
-    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 the interface with message type
 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.Textbox(
+            value="You are a helpful assistant knowledgeable about Italian cuisine.",
+            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)",
+            label="Top-p (nucleus sampling)"
         ),
     ],
+    chatbot=gr.Chatbot(type="messages")  # Use messages format instead of tuples
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(server_name="0.0.0.0", server_port=7860)