Update app.py

app.py

@@ -1,30 +1,74 @@
-import os
+
 import gradio as gr
-from transformers import pipeline
+import requests
+import os
 
-# Get the Hugging Face API token from environment variables
-api_token = os.getenv("HUGGINGFACE_API_TOKEN_V")
+TOKEN = os.getenv("HUGGINGFACE_API_TOKEN_V")
 print('----------------',api_token,'-----------------')
 # Check if the API token is set
 if not api_token:
     raise ValueError("API token is not set. Please set the HUGGINGFACE_API_TOKEN environment variable.")
+import gradio as gr
+import requests
+import os
+
+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})
+
+    headers = {
+        "Authorization": f"Bearer {TOKEN}",
+        "Content-Type": "application/json"
+    }
+
+    payload = {
+        "model": "meta-llama/Meta-Llama-3.1-405B-Instruct-FP8",
+        "max_tokens": max_tokens,
+        "temperature": temperature,
+        "top_p": top_p,
+        "messages": messages
+    }
+
+    response = requests.post("https://api-inference.huggingface.co/v1/chat/completions", headers=headers, json=payload, stream=True)
+    
+    response_text = ""
+    for chunk in response.iter_content(chunk_size=None):
+        if chunk:
+            response_text += chunk.decode('utf-8')
+            yield response_text
+
+theme="Nymbo/Nymbo_Theme"
 
-# Initialize the text generation pipeline with authentication
-pipe = pipeline("text-generation", model="meta-llama/Meta-Llama-3.1-405B", use_auth_token=True)
-
-# Define the function to generate text
-def generate_text(prompt):
-    result = pipe(prompt, max_length=50, num_return_sequences=1)
-    return result[0]['generated_text']
-
-# Create a Gradio interface
-iface = gr.Interface(
-    fn=generate_text,
-    inputs=gr.inputs.Textbox(lines=2, placeholder="Enter your prompt here..."),
-    outputs="text",
-    title="Meta-Llama Text Generation",
-    description="Generate text using the Meta-Llama 3.1 405B model."
+demo = gr.ChatInterface(
+    respond,
+    theme=theme,
+    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.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
 )
 
-# Launch the interface
-iface.launch()
+if __name__ == "__main__":
+    demo.launch()