Add two-agent CV arena UI.

app.py

@@ -1,64 +1,121 @@
+# import gradio as gr
+# from huggingface_hub import InferenceClient
+
+# """
+# 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("HuggingFaceH4/zephyr-7b-beta")
+
+
+# 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})
+
+#     response = ""
+
+#     for message in client.chat_completion(
+#         messages,
+#         max_tokens=max_tokens,
+#         stream=True,
+#         temperature=temperature,
+#         top_p=top_p,
+#     ):
+#         token = message.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
+# """
+# demo = 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)",
+#         ),
+#     ],
+# )
+
+
+# if __name__ == "__main__":
+#     demo.launch()
+
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
-
-
-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})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.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
-"""
-demo = 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)",
-        ),
-    ],
-)
+from PIL import Image
+
+# —— 在这里根据你自己的 Agent 框架实现这个函数 ——  
+def run_agent_on_image(original_img: Image.Image, prompt: str, agent_name: str) -> Image.Image:
+    """
+    调用指定 agent（模型/工具）处理图片并返回结果
+    original_img: PIL Image
+    prompt: 用户输入的描述
+    agent_name: 在下拉框里选的模型名称
+    """
+    # 示例逻辑（请替换为真正的 agent 调用）
+    # if agent_name == "Model A":
+    #     return model_a.process(original_img, prompt)
+    # elif agent_name == "Model B":
+    #     return model_b.process(original_img, prompt)
+    return original_img  # TODO: 删除这行
+
+# 可选：把可用的 agent 列表写成一个文件或者直接在这里列出
+MODEL_CHOICES = ["Model A", "Model B", "Model C"]
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("## CV Agent Arena  🎨🤖\n上传一张图片，输入处理指令，然后选两个不同的 agent 比较结果。")
+
+    with gr.Row():
+        # 左侧：原图 + prompt
+        with gr.Column():
+            original = gr.Image(type="pil", label="Upload Original Image")
+            prompt = gr.Textbox(lines=2, placeholder="e.g. ‘Make it look like a sunny day’", label="Prompt")
+        # 右侧：选择两个 agent
+        with gr.Column():
+            agent1 = gr.Dropdown(choices=MODEL_CHOICES, label="Select Agent 1")
+            agent2 = gr.Dropdown(choices=MODEL_CHOICES, label="Select Agent 2")
+
+    # 处理按钮
+    run_btn = gr.Button("Run Agents")    
+
+    with gr.Row():
+        # 左侧输出：Agent1 结果
+        with gr.Column():
+            out1 = gr.Image(type="pil", label="Agent 1 Output")
+        # 右侧输出：Agent2 结果
+        with gr.Column():
+            out2 = gr.Image(type="pil", label="Agent 2 Output")
 
+    # 按钮绑定
+    run_btn.click(
+        fn=lambda img, p, a1, a2: (run_agent_on_image(img, p, a1), run_agent_on_image(img, p, a2)),
+        inputs=[original, prompt, agent1, agent2],
+        outputs=[out1, out2],
+    )
 
 if __name__ == "__main__":
+    demo.queue()   # 支持异步队列，提高并发
     demo.launch()