Update app.py

app.py

@@ -1,64 +1,65 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from openai import OpenAI
+import base64
 
-"""
-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})
+# 初始化腾讯混元客户端（替换为你的API Key）
+client = OpenAI(
+    api_key="HUNYUAN_API_KEY",
+    base_url="https://api.hunyuan.cloud.tencent.com/v1"
+)
 
-    response = ""
+def generate_caption(image_path, question):
+    # 将图片转换为Base64
+    with open(image_path, "rb") as image_file:
+        base64_image = base64.b64encode(image_file.read()).decode('utf-8')
+    
+    # 构建消息结构
+    messages = [{
+        "role": "user",
+        "content": [
+            {"type": "text", "text": question},
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": f"data:image/jpeg;base64,{base64_image}"
+                }
+            }
+        ]
+    }]
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+    # 调用混元视觉模型
+    response = client.chat.completions.create(
+        model="hunyuan-vision",
+        messages=messages,
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        extra_body={
+            "stream_moderation": True,
+            "enable_enhancement": False
+        }
+    )
 
+    # 流式处理响应
+    full_response = ""
+    for chunk in response:
+        token = chunk.choices[0].delta.content
+        if token:
+            full_response += token
+            yield full_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)",
-        ),
-    ],
-)
+# 创建Gradio界面
+with gr.Blocks(title="腾讯混元图生文Demo") as demo:
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Image(type="filepath", label="上传图片")
+            question_input = gr.Textbox(label="输入问题", value="请描述图片内容")
+            submit_btn = gr.Button("生成描述")
+        output = gr.Textbox(label="描述结果", interactive=False)
 
+    submit_btn.click(
+        fn=generate_caption,
+        inputs=[image_input, question_input],
+        outputs=output
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(share=True)