DuckDuckGo翻译+LLM二次翻译
中译英,分2步进行翻译。1、传统的翻译引擎翻译;2、LLM模型指出错误、3、意译。即节省了token,也提高翻译准确性。
工作流图谱
YAML 源码
app:
description: 中译英,分2步进行翻译。1、传统的翻译引擎翻译;2、LLM模型指出错误、3、意译。即节省了token,也提高翻译准确性。
icon: 🤖
icon_background: '#FFEAD5'
mode: workflow
name: DuckDuckGo翻译+LLM二次翻译
kind: app
version: 0.1.0
workflow:
features:
file_upload:
image:
enabled: false
number_limits: 3
transfer_methods:
- local_file
- remote_url
opening_statement: ''
retriever_resource:
enabled: true
sensitive_word_avoidance:
enabled: false
speech_to_text:
enabled: false
suggested_questions: []
suggested_questions_after_answer:
enabled: false
text_to_speech:
enabled: false
language: ''
voice: ''
graph:
edges:
- data:
isInIteration: false
sourceType: start
targetType: tool
id: 1721107953425-source-1721107972339-target
source: '1721107953425'
sourceHandle: source
target: '1721107972339'
targetHandle: target
type: custom
zIndex: 0
- data:
isInIteration: false
sourceType: tool
targetType: llm
id: 1721107972339-source-1721107989661-target
source: '1721107972339'
sourceHandle: source
target: '1721107989661'
targetHandle: target
type: custom
zIndex: 0
- data:
isInIteration: false
sourceType: llm
targetType: end
id: 1721107989661-source-1721108151465-target
source: '1721107989661'
sourceHandle: source
target: '1721108151465'
targetHandle: target
type: custom
zIndex: 0
nodes:
- data:
desc: ''
selected: false
title: 开始
type: start
variables:
- label: content
max_length: 50000
options: []
required: true
type: paragraph
variable: content
height: 90
id: '1721107953425'
position:
x: 80
y: 282
positionAbsolute:
x: 80
y: 282
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
desc: ''
provider_id: duckduckgo
provider_name: duckduckgo
provider_type: builtin
selected: true
title: DuckDuckGo 翻译
tool_configurations:
translate_to: en
tool_label: DuckDuckGo 翻译
tool_name: ddgo_translate
tool_parameters:
query:
type: mixed
value: '{{#1721107953425.content#}}'
type: tool
height: 90
id: '1721107972339'
position:
x: 384
y: 282
positionAbsolute:
x: 384
y: 282
selected: true
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
context:
enabled: false
variable_selector: []
desc: ''
model:
completion_params:
temperature: 1.1
mode: chat
name: deepseek-chat
provider: deepseek
prompt_template:
- id: 3b488a37-c31c-4537-86df-3bfa8da1ab70
role: system
text: '## 角色
你是一位科研论文审稿员,擅长写作高质量的英文科研论文。请你帮我准确且学术性地将以下中文翻译成英文,风格与英文科研论文保持一致。
## 规则:
- 输入格式为 Markdown 格式,输出格式也必须保留原始 Markdown 格式
- 以下是常见的相关术语词汇对应表(中文 -> English):
* 零样本 -> Zero-shot
* 少样本 -> Few-shot
## 策略:
分两步进行翻译工作,并打印每步的结果:
1. 根据直译的结果,指出其中存在的具体问题,要准确描述,不宜笼统的表示,也不需要增加原文不存在的内容或格式,包括不仅限于:
- 不符合英文表达习惯,明确指出不符合的地方
- 语句不通顺,指出位置,不需要给出修改意见,意译时修复
- 晦涩难懂,模棱两可,不易理解,可以尝试给出解释
2. 根据直译的结果和第二步指出的问题,重新进行意译,保证内容的原意的基础上,使其更易于理解,更符合英文科研论文的表达习惯,同时保持原有的格式不变
## 格式
返回格式如下,"{xxx}"表示占位符:
###问题
{直译的具体问题列表}
***
###意译'
- id: e7ce339a-e1b2-4554-86ac-c66d95bc669e
role: user
text: '这是需要翻译的原文
{{#1721107953425.content#}}
这是直译的结果
{{#1721107972339.text#}}'
selected: false
title: LLM
type: llm
variables: []
vision:
enabled: false
height: 98
id: '1721107989661'
position:
x: 688
y: 282
positionAbsolute:
x: 688
y: 282
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
desc: ''
outputs:
- value_selector:
- '1721107989661'
- text
variable: output
selected: false
title: 结束
type: end
height: 90
id: '1721108151465'
position:
x: 992
y: 282
positionAbsolute:
x: 992
y: 282
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
viewport:
x: -2
y: 34
zoom: 1