Create app.py

app.py

@@ -0,0 +1,38 @@
+import gradio as gr
+import openai
+import pandas as pd
+import numpy as np
+
+# Example API key setup (for testing)
+openai.api_key = "YOUR_API_KEY"
+
+def evaluate_prompt(model_name, prompt_text):
+    """
+    Runs a single evaluation against OpenAI or Anthropic API
+    Returns text output and token count
+    """
+    if model_name.lower() == "gpt-4":
+        response = openai.ChatCompletion.create(
+            model="gpt-4",
+            messages=[{"role":"user","content":prompt_text}],
+            temperature=0.5
+        )
+        output_text = response['choices'][0]['message']['content']
+        tokens = response['usage']['total_tokens']
+        return f"Output:\n{output_text}\n\nTokens used: {tokens}"
+    else:
+        return "Model not supported yet"
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## MotionEval: AI Model Evaluation MVP")
+    
+    model_name = gr.Textbox(label="Model Name (e.g. GPT-4)")
+    prompt_text = gr.Textbox(label="Prompt", lines=5)
+    
+    run_button = gr.Button("Run Evaluation")
+    output = gr.Textbox(label="Result", lines=15)
+    
+    run_button.click(fn=evaluate_prompt, inputs=[model_name, prompt_text], outputs=output)
+
+demo.launch()