Update app.py

app.py

@@ -1,64 +1,105 @@
+import os
+os.system('pip install dashscope')
 import gradio as gr
-from huggingface_hub import InferenceClient
+from http import HTTPStatus
+import dashscope
+from dashscope import Generation
+from dashscope.api_entities.dashscope_response import Role
+from typing import List, Optional, Tuple, Dict
+from urllib.error import HTTPError
+default_system = 'You are a helpful assistant.'
 
-"""
-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")
+YOUR_API_TOKEN = os.getenv('YOUR_API_TOKEN')
+dashscope.api_key = YOUR_API_TOKEN
 
+History = List[Tuple[str, str]]
+Messages = List[Dict[str, str]]
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+def clear_session() -> History:
+    return '', []
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def modify_system_session(system: str) -> str:
+    if system is None or len(system) == 0:
+        system = default_system
+    return system, system, []
 
-    messages.append({"role": "user", "content": message})
+def history_to_messages(history: History, system: str) -> Messages:
+    messages = [{'role': Role.SYSTEM, 'content': system}]
+    for h in history:
+        messages.append({'role': Role.USER, 'content': h[0]})
+        messages.append({'role': Role.ASSISTANT, 'content': h[1]})
+    return messages
 
-    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
+def messages_to_history(messages: Messages) -> Tuple[str, History]:
+    assert messages[0]['role'] == Role.SYSTEM
+    system = messages[0]['content']
+    history = []
+    for q, r in zip(messages[1::2], messages[2::2]):
+        history.append([q['content'], r['content']])
+    return system, history
 
-        response += token
-        yield response
 
+def model_chat(query: Optional[str], history: Optional[History], system: str
+) -> Tuple[str, str, History]:
+    if query is None:
+        query = ''
+    if history is None:
+        history = []
+    messages = history_to_messages(history, system)
+    messages.append({'role': Role.USER, 'content': query})
+    gen = Generation.call(
+        model='qwen-max-0125',
+        messages=messages,
+        result_format='message',
+        stream=True
+    )
+    for response in gen:
+        if response.status_code == HTTPStatus.OK:
+            role = response.output.choices[0].message.role
+            response = response.output.choices[0].message.content
+            system, history = messages_to_history(messages + [{'role': role, 'content': response}])
+            yield '', history, system
+        else:
+            raise ValueError('Request id: %s, Status code: %s, error code: %s, error message: %s' % (
+                response.request_id, response.status_code,
+                response.code, response.message
+            ))
 
-"""
-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)",
-        ),
-    ],
-)
 
+with gr.Blocks() as demo:
+    gr.Markdown("""<center><font size=8>Qwen2.5-Max👾</center>""")
 
-if __name__ == "__main__":
-    demo.launch()
+    with gr.Row():
+        with gr.Column(scale=3):
+            system_input = gr.Textbox(value=default_system, lines=1, label='System')
+        with gr.Column(scale=1):
+            modify_system = gr.Button("🛠️ Set system prompt and clear history", scale=2)
+        system_state = gr.Textbox(value=default_system, visible=False)
+    chatbot = gr.Chatbot(label='qwen2.5-max')
+    textbox = gr.Textbox(lines=1, label='Input')
+
+    with gr.Row():
+        clear_history = gr.Button("🧹 Clear history")
+        sumbit = gr.Button("🚀 Send")
+
+    textbox.submit(model_chat,
+                 inputs=[textbox, chatbot, system_state],
+                 outputs=[textbox, chatbot, system_input],
+                 concurrency_limit = 40)
+    
+    sumbit.click(model_chat,
+                 inputs=[textbox, chatbot, system_state],
+                 outputs=[textbox, chatbot, system_input],
+                 concurrency_limit = 40)
+    clear_history.click(fn=clear_session,
+                        inputs=[],
+                        outputs=[textbox, chatbot],
+                        concurrency_limit = 40)
+    modify_system.click(fn=modify_system_session,
+                        inputs=[system_input],
+                        outputs=[system_state, system_input, chatbot],
+                        concurrency_limit = 40)
+
+demo.queue(api_open=False)
+demo.launch(max_threads=40)