Spaces:
Running
Running
File size: 1,773 Bytes
09321b6 |
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 |
from modelscope.utils.constant import Tasks
from .pipeline_tool import ModelscopePipelineTool
class ImageChatTool(ModelscopePipelineTool):
default_model = 'damo/multi-modal_mplug_owl_multimodal-dialogue_7b'
description = '图文对话和图像描述服务，针对输入的图片和用户的文本输入，给出文本回复'
name = 'modelscope_image-chat'
parameters: list = [{
'name': 'image',
'description': '用户输入的图片',
'required': True
}, {
'name': 'text',
'description': '用户输入的文本',
'required': True
}]
task = Tasks.multimodal_dialogue
def construct_image_chat_input(self, **kwargs):
image = kwargs.pop('image', '')
text = kwargs.pop('text', '')
system_prompt_1 = 'The following is a conversation between a curious human and AI assistant.'
system_prompt_2 = "The assistant gives helpful, detailed, and polite answers to the user's questions."
messages = {
'messages': [
{
'role': 'system',
'content': system_prompt_1 + ' ' + system_prompt_2
},
{
'role': 'user',
'content': [{
'image': image
}]
},
{
'role': 'user',
'content': text
},
]
}
return messages
def _remote_parse_input(self, *args, **kwargs):
messages = self.construct_image_chat_input(**kwargs)
return {'input': messages}
def _local_parse_input(self, *args, **kwargs):
return (self.construct_image_chat_input(**kwargs)), {}
|