Update app.py

app.py

@@ -1,128 +1,98 @@
-#!/usr/bin/env python
-
 import os
-from threading import Thread
-from typing import Iterator
+os.system('pip install dashscope')
 
 import gradio as gr
-import spaces
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
-
-DESCRIPTION = "# Arcee Model Testing - current test: arcee-ai/SEC-Calme-7B-Instruct"
-
-if not torch.cuda.is_available():
-    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
-
-MAX_MAX_NEW_TOKENS = 4096
-DEFAULT_MAX_NEW_TOKENS = 4096
-MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
-
-if torch.cuda.is_available():
-    model_id = "arcee-ai/SEC-Calme-7B-Instruct"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
-
-
-@spaces.GPU
-def generate(
-    message: str,
-    chat_history: list[tuple[str, str]],
-    max_new_tokens: int = 4096,
-    temperature: float = 0.6,
-    top_p: float = 0.9,
-    top_k: int = 50,
-    repetition_penalty: float = 1.2,
-) -> Iterator[str]:
-    conversation = []
-    for user, assistant in chat_history:
-        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
-    conversation.append({"role": "user", "content": message})
-
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
-    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
-        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
-        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
-    input_ids = input_ids.to(model.device)
-
-    streamer = TextIteratorStreamer(tokenizer, timeout=20.0, skip_prompt=True, skip_special_tokens=True)
-    generate_kwargs = dict(
-        {"input_ids": input_ids},
-        streamer=streamer,
-        max_new_tokens=max_new_tokens,
-        do_sample=True,
-        top_p=top_p,
-        top_k=top_k,
-        temperature=temperature,
-        num_beams=1,
-        repetition_penalty=repetition_penalty,
-    )
-    t = Thread(target=model.generate, kwargs=generate_kwargs)
-    t.start()
-
-    outputs = []
-    for text in streamer:
-        outputs.append(text)
-        yield "".join(outputs)
-
-
-chat_interface = gr.ChatInterface(
-    fn=generate,
-    additional_inputs=[
-        gr.Slider(
-            label="Max new tokens",
-            minimum=1,
-            maximum=MAX_MAX_NEW_TOKENS,
-            step=1,
-            value=DEFAULT_MAX_NEW_TOKENS,
-        ),
-        gr.Slider(
-            label="Temperature",
-            minimum=0.1,
-            maximum=4.0,
-            step=0.1,
-            value=0.6,
-        ),
-        gr.Slider(
-            label="Top-p (nucleus sampling)",
-            minimum=0.05,
-            maximum=1.0,
-            step=0.05,
-            value=0.9,
-        ),
-        gr.Slider(
-            label="Top-k",
-            minimum=1,
-            maximum=1000,
-            step=1,
-            value=50,
-        ),
-        gr.Slider(
-            label="Repetition penalty",
-            minimum=1.0,
-            maximum=2.0,
-            step=0.05,
-            value=1.2,
-        ),
-    ],
-    stop_btn=None,
-    examples=[
-        ["Hello there! How are you doing?"],
-        ["Can you explain briefly to me what is the Python programming language?"],
-        ["Explain the plot of Cinderella in a sentence."],
-        ["How many hours does it take a man to eat a Helicopter?"],
-        ["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
-    ],
-)
-
-with gr.Blocks(css="style.css") as demo:
-    gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(
-        value="Duplicate Space for private use",
-        elem_id="duplicate-button",
-        visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1",
+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.'
+
+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 clear_session() -> History:
+    return '', []
+
+def modify_system_session(system: str) -> str:
+    if system is None or len(system) == 0:
+        system = default_system
+    return system, system, []
+
+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
+
+
+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
+
+
+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 = "arcee-ai/Saul-Base-Calme-7B-Instruct-slerp",
+        messages=messages,
+        result_format='message',
+        stream=True
     )
-    chat_interface.render()
+    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 HTTPError('Request id: %s, Status code: %s, error code: %s, error message: %s' % (
+                response.request_id, response.status_code,
+                response.code, response.message
+            ))
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("""<center><font size=8>Qarcee-ai/Saul-Base-Calme-7B-Instruct-slerp</center>""")
+    gr.Markdown("""<center><font size=4>arcee-ai/Saul-Base-Calme-7B-Instruct-slerp.</center>""")
+
+    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='arcee-ai/Saul-Base-Calme-7B-Instruct-slerp')
+    textbox = gr.Textbox(lines=2, label='Input')
+
+    with gr.Row():
+        clear_history = gr.Button("🧹 Clear history")
+        sumbit = gr.Button("🚀 Send")
+
+    sumbit.click(model_chat,
+                 inputs=[textbox, chatbot, system_state],
+                 outputs=[textbox, chatbot, system_input])
+    clear_history.click(fn=clear_session,
+                        inputs=[],
+                        outputs=[textbox, chatbot])
+    modify_system.click(fn=modify_system_session,
+                        inputs=[system_input],
+                        outputs=[system_state, system_input, chatbot])
 
-if __name__ == "__main__":
-    demo.queue(max_size=20).launch()
+demo.queue(api_open=False).launch(max_threads=10,height=800, share=False)