Update app.py

app.py

@@ -1,10 +1,12 @@
+import os
 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")
+import json
+import types
+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
 
 
 def respond(
@@ -15,50 +17,58 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    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]:
-            messages.append({"role": "user", "content": val[0]})
+            messages.append({"Role": "user", "Content": val[0]})
         if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+            messages.append({"Role": "assistant", "Content": val[1]})
 
-    messages.append({"role": "user", "content": message})
+    messages.append({"Role": "user", "Content": message})
+
+    params = {
+        "Model": "hunyuan-large",
+        "Messages": messages,
+        "Stream": True,
+        "StreamModeration": True,
+        "EnableEnhancement": False,
+    }
+    req.from_json_string(json.dumps(params))
+
+    resp = client.ChatCompletions(req)
 
     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
+    for event in resp:
+        data = json.loads(event['data'])
+        token = data['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)",
-        ),
-    ],
+    title="Hunyuan-Large"
 )
 
 
 if __name__ == "__main__":
     demo.launch()
+