File size: 5,330 Bytes
e77241a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 |
import gradio as gr
import modelscope_studio as mgr
from http import HTTPStatus
import os
from dashscope import MultiModalConversation
import dashscope
YOUR_API_TOKEN = os.getenv('YOUR_API_TOKEN')
dashscope.api_key = YOUR_API_TOKEN
def add_text(chatbot, task_history, input):
"""Add text to the chat history."""
task_history.append({"role": "user", "content": [{"text": input.text}]})
task_history.append({"role": "user", "content": [{"audio": input.files[0].path}]})
chatbot.append([{
"text": input.text,
"files": input.files,
}, None])
return chatbot, task_history, None
# def add_mic(chatbot, task_history, mic):
# """Add audio to the chat history."""
# task_history.append({"role": "user", "content": [{"audio": mic}]})
# chatbot.append((f"[Audio input: {mic}]", None))
# return chatbot, task_history
def add_file(chatbot, task_history, audio_file):
"""Add audio file to the chat history."""
task_history.append({"role": "user", "content": [{"audio": audio_file.name}]})
chatbot.append((f"[Audio file: {audio_file.name}]", None))
return chatbot, task_history
def reset_user_input():
"""Reset the user input field."""
return gr.Textbox.update(value='')
def reset_state(task_history):
"""Reset the chat history."""
return [], []
def regenerate(chatbot, task_history):
"""Regenerate the last bot response."""
if task_history and task_history[-1]['role'] == 'assistant':
task_history.pop()
chatbot.pop()
if task_history:
chatbot, task_history = predict(chatbot, task_history)
return chatbot, task_history
def predict(chatbot, task_history):
"""Generate a response from the model."""
response = MultiModalConversation.call(model='qwen2-audio-instruct',
messages=task_history)
if response.status_code == HTTPStatus.OK:
output_text = response.output.choices[0].message.content
if isinstance(output_text, list):
output_text = next((item.get('text') for item in output_text if 'text' in item), '')
elif isinstance(output_text, dict):
output_text = output_text.get('text', '')
task_history.append({'role': response.output.choices[0].message.role,
'content': [{'text': output_text}]})
chatbot.append((None, output_text)) # Add the response to chatbot
return chatbot, task_history
else:
error_message = f"Failed to get a response: {response.code} - {response.message}"
chatbot.append((None, error_message)) # Add the error message to chatbot
return chatbot, task_history
with gr.Blocks() as demo:
gr.Markdown("""<p align="center"><img src="https://modelscope.oss-cn-beijing.aliyuncs.com/resource/qwen.png" style="height: 80px"/><p>""") ## todo
gr.Markdown("""<center><font size=8>Qwen2-Audio-Instruct Bot</center>""")
gr.Markdown(
"""\
<center><font size=3>This WebUI is based on Qwen2-Audio-Instruct, developed by Alibaba Cloud. \
(本WebUI基于Qwen2-Audio-Instruct打造，实现聊天机器人功能。)</center>""")
gr.Markdown("""\
<center><font size=4>Qwen2-Audio <a href="https://modelscope.cn/models/qwen/Qwen2-Audio-7B">🤖 </a>
| <a href="https://huggingface.co/Qwen/Qwen2-Audio-7B">🤗</a>  ｜
Qwen2-Audio-Instruct <a href="https://modelscope.cn/models/qwen/Qwen2-Audio-7B-Instruct">🤖 </a> |
<a href="https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct">🤗</a>  ｜
 <a href="https://github.com/QwenLM/Qwen2-Audio">Github</a></center>""")
chatbot = mgr.Chatbot(label='Qwen2-Audio-7B-Instruct', elem_classes="control-height", height=750)
# query = gr.Textbox(lines=2, label='Input')
# mic = gr.Audio(source="microphone", type="filepath")
user_input = mgr.MultimodalInput(
interactive=True,
sources=['microphone'],
submit_button_props=dict(value="🚀 Submit (发送)")
)
task_history = gr.State([])
with gr.Row():
empty_bin = gr.Button("🧹 Clear History (清除历史)")
# submit_btn = gr.Button("🚀 Submit (发送)")
regen_btn = gr.Button("🤔️ Regenerate (重试)")
addfile_btn = gr.UploadButton("📁 Upload (上传文件)", file_types=["audio"])
# mic.change(add_mic, [chatbot, task_history, mic], [chatbot, task_history])
# submit_btn.click(add_text, [chatbot, task_history, query], [chatbot, task_history]).then(
# predict, [chatbot, task_history], [chatbot, task_history], show_progress=True
# )
# submit_btn.click(reset_user_input, [], [query])
user_input.submit(fn=add_text,
inputs=[chatbot, task_history, user_input],
outputs=[chatbot, task_history, user_input]).then(
predict, [chatbot, task_history], [chatbot, task_history], show_progress=True
)
empty_bin.click(reset_state, outputs=[chatbot, task_history], show_progress=True)
regen_btn.click(regenerate, [chatbot, task_history], [chatbot, task_history], show_progress=True)
addfile_btn.upload(add_file, [chatbot, task_history, addfile_btn], [chatbot, task_history], show_progress=True)
demo.queue().launch(
share=False,
inbrowser=True,
server_port=7860,
server_name="0.0.0.0",
)
|