Update app.py

app.py

@@ -1,55 +1,67 @@
 import gradio as gr
 from openai import OpenAI
 import os
-import nest_asyncio
-
-nest_asyncio.apply()
 
 ACCESS_TOKEN = os.getenv("HF_TOKEN")
 
-# Fixed client initialization without proxies
 client = OpenAI(
-    base_url="https://api-inference.huggingface.co/models/NousResearch/Hermes-3-Llama-3.1-8B/",
+    base_url="https://api-inference.huggingface.co/v1/",
     api_key=ACCESS_TOKEN,
 )
 
 def respond(
     message,
+    history: list[tuple[str, str]],
     system_message,
     max_tokens,
     temperature,
     top_p,
 ):
-    messages = [
-        {"role": "system", "content": system_message},
-        {"role": "user", "content": message}
-    ]
+    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 = ""
     
-    try:
-        response = client.chat.completions.create(
-            model="NousResearch/Hermes-3-Llama-3.1-8B",
-            messages=messages,
-            max_tokens=max_tokens,
-            temperature=temperature,
-            top_p=top_p
-        )
-        return response.choices[0].message.content
-    except Exception as e:
-        return f"Error: {str(e)}"
+    for message in  client.chat.completions.create(
+        model="NousResearch/Hermes-3-Llama-3.1-8B",
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+        messages=messages,
+    ):
+        token = message.choices[0].delta.content
+        
+        response += token
+        yield response
+        
+chatbot = gr.Chatbot(height=600)
 
-# Gradio interface
-iface = gr.Interface(
-    fn=respond,
-    inputs=[
-        gr.Textbox(label="Message", lines=4),
-        gr.Textbox(label="System Message", value="You are a helpful assistant."),
-        gr.Slider(minimum=1, maximum=2048, value=512, label="Max Tokens"),
-        gr.Slider(minimum=0, maximum=1, value=0.7, label="Temperature"),
-        gr.Slider(minimum=0, maximum=1, value=0.9, label="Top P")
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="", 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",
+        ),
+        
     ],
-    outputs="text",
-    title="Hermes-3-Llama Chat"
+    fill_height=True,
+    chatbot=chatbot,
+    theme="Nymbo/Alyx_Theme",
 )
-
 if __name__ == "__main__":
-    iface.launch()
+    demo.launch()