Update app.py

app.py

@@ -1,69 +1,56 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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.ChatInterface(
-    respond,
-    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)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+from flask import Flask, jsonify
+import time
+import os
+
+app = Flask(__name__)
+
+# Global memory store
+data_blob = None
+data_size_bytes = 0
+created_at = None
+
+
+def generate_data(size_mb=1024):
+    """Generate ~size_mb MB random data"""
+    global data_blob, data_size_bytes, created_at
+
+    print(f"[+] Generating ~{size_mb} MB random data in memory...")
+
+    start = time.time()
+
+    # Generate random bytes (~1GB)
+    data_blob = os.urandom(size_mb * 1024 * 1024)
+
+    data_size_bytes = len(data_blob)
+    created_at = time.time()
+
+    end = time.time()
+
+    print(f"[✓] Data generated in {round(end - start, 2)} sec")
+    print(f"[✓] Size: {round(data_size_bytes / (1024**3), 2)} GB")
+
+
+@app.route("/")
+def home():
+    return "Server is running 🚀"
+
+
+@app.route("/get")
+def get_info():
+    if data_blob is None:
+        return jsonify({
+            "status": "no data in memory"
+        })
+
+    return jsonify({
+        "size_bytes": data_size_bytes,
+        "size_mb": round(data_size_bytes / (1024 * 1024), 2),
+        "size_gb": round(data_size_bytes / (1024**3), 2),
+        "created_at_epoch": created_at,
+        "created_at_readable": time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(created_at))
+    })
 
 
 if __name__ == "__main__":
-    demo.launch()
+    generate_data(1024)  # ~1GB
+    app.run(host="0.0.0.0", port=7860)