Starter LLM Inference Call

app.py

@@ -0,0 +1,35 @@
+import os
+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
+)
+
+# LLM function
+def ask_llm(prompt):
+    try:
+        completion = client.chat.completions.create(
+            model="meta-llama/Llama-3.1-8B-Instruct",
+            messages=[
+                {"role": "user", "content": prompt}
+            ],
+            max_tokens=200
+        )
+        return completion.choices[0].message["content"]
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+
+# Build Gradio UI
+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."
+)
+
+demo.launch()

requirements.txt

@@ -0,0 +1 @@
+openai>=1.51.0