Starter LLM Inference Call

app.py

@@ -3,10 +3,14 @@ import gradio as gr
 from openai import OpenAI
 
 # Initialize HF Router client using OpenAI SDK
+'''
 client = OpenAI(
     base_url="https://router.huggingface.co/v1",
     api_key=os.environ["HF_TOKEN"],   # ensure HF_TOKEN is set
 )
+'''
+
+client = InferenceClient(api_key=os.environ["HF_TOKEN"])
 
 # LLM function
 def ask_llm(prompt):
@@ -16,7 +20,8 @@ def ask_llm(prompt):
             messages=[
                 {"role": "user", "content": prompt}
             ],
-            max_tokens=200
+            max_tokens=200,
+            temperature=0.7
         )
         #return completion.choices[0].message["content"]
         return completion.choices[0].message.content
@@ -29,8 +34,8 @@ demo = gr.Interface(
     fn=ask_llm,
     inputs=gr.Textbox(lines=3, label="Ask the AI"),
     outputs=gr.Textbox(label="Response"),
-    title="HF Router LLM Demo",
-    description="Powered by HuggingFace Router + OpenAI SDK client."
+    title="HF Inference Client LLM Demo",
+    description="Powered by HuggingFace InferenceClient SDK."
 )
 
 demo.launch()