Update

app.py

@@ -62,15 +62,32 @@
 
 
 
-import requests
+import gradio as gr
+from huggingface_hub import InferenceClient
 
-API_URL = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3.1-405B"
-headers = {"Authorization": "Bearer hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"}
+# Initialize the Hugging Face Inference Client
+client = InferenceClient(
+    "meta-llama/Meta-Llama-3.1-8B-Instruct",
+    # token=  # Replace with your actual token
+)
 
-def query(payload):
-	response = requests.post(API_URL, headers=headers, json=payload)
-	return response.json()
-	
-output = query({
-	"inputs": "Can you please let us know more details about your ",
-})
+# Define a function to handle the chat input and get a response from the model
+def chat_with_model(user_input):
+    # Call the client to get the model's response
+    response = ""
+    for message in client.chat_completion(
+        messages=[{"role": "user", "content": user_input}],
+        max_tokens=500,
+        stream=True,
+    ):
+        response += message.choices[0].delta.content
+    return response
+
+# Create a Gradio interface with a chat component
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot()
+    with gr.Row():
+        txt = gr.Textbox(show_label=False, placeholder="Type your message here...")
+        txt.submit(chat_with_model, inputs=txt, outputs=chatbot)
+
+demo.launch()