Update app.py

app.py

@@ -1,11 +1,19 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+import json
+from tencentcloud.common import credential
+from tencentcloud.common.profile.client_profile import ClientProfile
+from tencentcloud.common.profile.http_profile import HttpProfile
+from tencentcloud.common.exception.tencent_cloud_sdk_exception import TencentCloudSDKException
+from tencentcloud.hunyuan.v20230901 import hunyuan_client, models
 
-"""
-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")
+from datetime import datetime
 
+def print_now(msg):
+    now = datetime.now()
+    formatted_time = now.strftime("%Y-%m-%d %H:%M:%S.%f")
+    print(f"{msg}:{formatted_time}")
+    return formatted_time
 
 def respond(
     message,
@@ -15,50 +23,74 @@ def respond(
     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)",
-        ),
-    ],
-)
+    try:
+        default_system ='You are a helpful assistant.'
+
+        messages = [{"Role": "system", "Content": default_system}]
+
+        secret_id = os.getenv('SECRET_ID')
+        secret_key = os.getenv('SECRET_KEY')
+
+        cred = credential.Credential(secret_id, secret_key)
+        httpProfile = HttpProfile()
+        httpProfile.endpoint = "hunyuan.tencentcloudapi.com"
+        clientProfile= ClientProfile()
+        clientProfile.httpProfile = httpProfile
+        client = hunyuan_client.HunyuanClient(cred, "", clientProfile)
+        req = models.ChatCompletionsRequest()
+
+        for val in history:
+            if val[0] and val[1]:
+                messages.append({"Role": "user", "Content": val[0]})
+                messages.append({"Role": "assistant", "Content": val[1]})
+        
+        messages.append({"Role": "user", "Content": message})
+        params = {
+            "Model": "hunyuan-turbos-latest",
+            "Messages": messages,
+            "Stream": True,
+            "StreamModeration": True,
+            "EnableEnhancement": False,
+        }
+        req.from_json_string(json.dumps(params))
+
+        resp= client.ChatCompletions(req)
+
+        response = ""
 
+        for event in resp:
+            data = json.loads(event['data'])
+            token = data['Choices'][0]['Delta']['Content']
+
+            response += token
+            yield response
+
+    except TencentCloudSDKException as err:
+        raise gr.Error(f"腾讯云SDK异常: {err}")
+    except Exception as e:
+        raise gr.Error(f"发生错误: {str(e)}")
+
+example_prompts = [
+    ["How to cook Kung Pao chicken the tastiest?"],
+    ["Help me create an email expressing my greetings to an old friend."],
+    ["写一篇关于青春的五言绝句"],
+    ["一枚反面朝上的硬币，被翻转了15下后，它的上面是正面，这个说法正确吗?"]
+]
+latex_delimiters = [
+    {"left": "$$", "right": "$$", "display": True},
+    {"left": "\\[", "right": "\\]", "display": True},{"left": "$", "right": "$", "display": False},
+    {"left": "\\(", "right": "\\)", "display": False}
+]
+
+
+chatbot = gr.Chatbot(latex_delimiters=latex_delimiters, scale=9)
+
+demo = gr.ChatInterface(respond,
+    title="Hunyuan-Large",
+    examples=example_prompts,
+    chatbot=chatbot
+)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.queue(default_concurrency_limit=40)
+    demo.launch(max_threads=40)