Update app.py

app.py

@@ -16,19 +16,17 @@ from langchain_core.prompts import PromptTemplate
 """
 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("Qwen/Qwen2-7B-Instruct")
-# llm = ChatOpenAI(
-#         model="Qwen/Qwen2-7B-Instruct",
-#         temperature=0.8,)
+import gradio as gr
+from openai import OpenAI
+import os
 
-# qa = RetrievalQA.from_chain_type(
-#         llm=client,
-#         chain_type="stuff",
-#         retriever=retriever,
-#         chain_type_kwargs=chain_type_kwargs,
-#         return_source_documents=True
-#     )
 
+TOKEN = os.getenv("HF_TOKEN")
+
+client = OpenAI(
+    base_url="https://api-inference.huggingface.co/v1/",
+    api_key=TOKEN,
+)
 
 def respond(
     message,
@@ -49,26 +47,29 @@ def respond(
     messages.append({"role": "user", "content": message})
 
     response = ""
-
-    for message in client.chat_completion(
-        messages,
+    
+    for message in  client.chat.completions.create(
+        model="meta-llama/Meta-Llama-3.1-8B-Instruct",
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
+        messages=messages,
     ):
         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
-"""
+
+chatbot = gr.Chatbot(height=600)
+
 demo = gr.ChatInterface(
     respond,
+    fill_height=True,
+    chatbot=chatbot,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(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(