help me think(deepseek r1)
暂无描述
工作流图谱
YAML 源码
app:
description: ''
icon: ♿
icon_background: '#D5F5F6'
mode: advanced-chat
name: help me think(deepseek r1)
use_icon_as_answer_icon: false
dependencies: []
kind: app
version: 0.1.5
workflow:
conversation_variables: []
environment_variables: []
features:
file_upload:
allowed_file_extensions: []
allowed_file_types:
- image
allowed_file_upload_methods:
- remote_url
- local_file
enabled: true
fileUploadConfig:
audio_file_size_limit: 50
batch_count_limit: 5
file_size_limit: 15
image_file_size_limit: 10
video_file_size_limit: 100
workflow_file_upload_limit: 10
image:
enabled: false
number_limits: 3
transfer_methods:
- local_file
- remote_url
number_limits: 1
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: llm
targetType: answer
id: 1738052643931-source-answer-target
source: '1738052643931'
sourceHandle: source
target: answer
targetHandle: target
type: custom
zIndex: 0
- data:
isInIteration: false
sourceType: llm
targetType: llm
id: llm-source-1738052643931-target
source: llm
sourceHandle: source
target: '1738052643931'
targetHandle: target
type: custom
zIndex: 0
- data:
isInIteration: false
sourceType: start
targetType: document-extractor
id: 1738052599424-source-1738168561064-target
source: '1738052599424'
sourceHandle: source
target: '1738168561064'
targetHandle: target
type: custom
zIndex: 0
- data:
isInIteration: false
sourceType: document-extractor
targetType: llm
id: 1738168561064-source-llm-target
source: '1738168561064'
sourceHandle: source
target: llm
targetHandle: target
type: custom
zIndex: 0
nodes:
- data:
desc: ''
selected: false
title: 开始
type: start
variables: []
height: 54
id: '1738052599424'
position:
x: 80
y: 282
positionAbsolute:
x: 80
y: 282
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
context:
enabled: false
variable_selector: []
desc: ''
memory:
query_prompt_template: '<User Query>{{#sys.query#}}</User Query>
<file>{{#1738168561064.text#}}</file>'
role_prefix:
assistant: ''
user: ''
window:
enabled: false
size: 10
model:
completion_params:
temperature: 0.7
mode: chat
name: deepseek-reasoner
provider: langgenius/deepseek/deepseek
prompt_template:
- id: 60740fa2-90fc-4269-93f4-3d150c3df150
role: system
text: '<角色>
你是一个有着推理能力的LLM。
不同于其他的LLM，你能完整地输出你的思考过程。
</角色>
<任务>
你的任务是辅助其他没有推理能力的LLM思考。
你需要根据用户的提问，输出完整的思考过程给其他的LLM。
<步骤>
“步骤1”： “接收用户提出的问题。”
“步骤2”： “针对用户问题，进行深度推理和分析。”
“步骤3”： “详细阐述推理过程和逻辑，确保过程完整且易于理解。”，
“步骤4”： “输出完整的推理过程，无需给出最终答案。”
</步骤>
</任务>
<限制>
不要输出最终答案，只输出思考过程。
不要解释自身能力或限制。
</限制>'
selected: false
title: deepseek-r1
type: llm
variables: []
vision:
enabled: false
height: 96
id: llm
position:
x: 744
y: 282
positionAbsolute:
x: 744
y: 282
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
answer: '<think>
{{#llm.text#}}
</think>
<output>
{{#1738052643931.text#}}
</output>'
desc: ''
selected: false
title: 直接回复
type: answer
variables: []
height: 140
id: answer
position:
x: 1522
y: 282
positionAbsolute:
x: 1522
y: 282
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
context:
enabled: false
variable_selector: []
desc: ''
memory:
query_prompt_template: '<User Query>{{#sys.query#}}</User Query>
<file>{{#1738168561064.text#}}</file>
<deepseek-r1>{{#llm.text#}}</deepseek-r1>'
role_prefix:
assistant: ''
user: ''
window:
enabled: false
size: 50
model:
completion_params:
temperature: 0.7
mode: chat
name: gemini-1.5-flash-8b-exp-0924
provider: langgenius/gemini/google
prompt_template:
- id: 564efaef-34a5-4c48-9ca3-a9f4f0bdeba9
role: system
text: '<角色>
你是一个善于学习的LLM。
</角色>
<任务>
你需要学习别人对问题的思考过程，用他的思考增强你的结果，然后给出你的答案。
<步骤>
“步骤1”： “接收来自 DeepSeek-R1 模型的思考过程。”
“步骤2”： “仔细学习和理解 DeepSeek-R1 的推理逻辑和步骤。”，
“步骤3”： “根据 DeepSeek-R1 的思考，结合图像能力，生成最终答案。”
“步骤4”： “输出最终答案，无需解释思考过程。”
</步骤>
</任务>
<限制>
不要重复 DeepSeek-R1 的思考过程，只输出最终答案。
不要解释自身能力或学习过程。
确保答案准确且与问题相关。
</限制>'
selected: false
title: gemini
type: llm
variables: []
vision:
configs:
detail: high
variable_selector:
- sys
- files
enabled: true
height: 96
id: '1738052643931'
position:
x: 1096
y: 282
positionAbsolute:
x: 1096
y: 282
selected: true
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
author: stvlynn
desc: ''
height: 202
selected: false
showAuthor: true
text: '{"root":{"children":[{"children":[{"detail":0,"format":0,"mode":"normal","style":"font-size:
16px;","text":"简介","type":"text","version":1}],"direction":"ltr","format":"","indent":0,"type":"paragraph","version":1,"textFormat":0},{"children":[{"detail":0,"format":0,"mode":"normal","style":"","text":"本
Demo 利用 DeepSeek R1 的强大推理能力，并通过 Gemini 模型学习增强输出，展示如何将推理型 LLM 和多模态 LLM 结合，提升
AI 思考和回答问题的能力。","type":"text","version":1}],"direction":"ltr","format":"","indent":0,"type":"paragraph","version":1,"textFormat":0}],"direction":"ltr","format":"","indent":0,"type":"root","version":1}}'
theme: blue
title: ''
type: ''
width: 266
height: 202
id: '1738165679422'
position:
x: 61
y: 29
positionAbsolute:
x: 61
y: 29
selected: false
sourcePosition: right
targetPosition: left
type: custom-note
width: 266
- data:
author: stvlynn
desc: ''
height: 241
selected: false
showAuthor: true
text: '{"root":{"children":[{"children":[{"detail":0,"format":0,"mode":"normal","style":"font-size:
16px;","text":"推理模型","type":"text","version":1}],"direction":"ltr","format":"","indent":0,"type":"paragraph","version":1,"textFormat":0},{"children":[{"detail":0,"format":0,"mode":"normal","style":"","text":"此节点调用
DeepSeek-R1 推理模型（deepseek-reasoner）。系统提示词设定 DeepSeek-R1 为一个有推理能力的 LLM，且需要输出完整的思考过程。它的任务是辅助其他没有推理能力的
LLM 进行思考，并根据用户提问输出完整的思考过程，其中思考过程会使用 <think> 标签包裹。","type":"text","version":1}],"direction":"ltr","format":"","indent":0,"type":"paragraph","version":1,"textFormat":0}],"direction":"ltr","format":"","indent":0,"type":"root","version":1}}'
theme: blue
title: ''
type: ''
width: 277
height: 241
id: '1738165732645'
position:
x: 726
y: 11
positionAbsolute:
x: 726
y: 11
selected: false
sourcePosition: right
targetPosition: left
type: custom-note
width: 277
- data:
author: stvlynn
desc: ''
height: 240
selected: false
showAuthor: true
text: '{"root":{"children":[{"children":[{"detail":0,"format":0,"mode":"normal","style":"font-size:
16px;","text":"多模态模型","type":"text","version":1}],"direction":"ltr","format":"","indent":0,"type":"paragraph","version":1,"textFormat":0},{"children":[{"detail":0,"format":0,"mode":"normal","style":"","text":"此节点调用
Google 的 Gemini 模型（gemini-1.5-flash-8b-exp-0924）。系统提示词设定 Gemini 模型为一个善于学习的
LLM，它的任务是学习别人（DeepSeek-R1）对问题的思考过程，并用它的思考增强自己的结果，然后给出自己的答案。输入的思考过程会被当做用户提问，最终答案会使用 <output> 标签包裹。","type":"text","version":1}],"direction":"ltr","format":"","indent":0,"type":"paragraph","version":1,"textFormat":0}],"direction":"ltr","format":"","indent":0,"type":"root","version":1}}'
theme: blue
title: ''
type: ''
width: 273
height: 240
id: '1738165823052'
position:
x: 1096
y: 11
positionAbsolute:
x: 1096
y: 11
selected: false
sourcePosition: right
targetPosition: left
type: custom-note
width: 273
- data:
author: stvlynn
desc: ''
height: 226
selected: false
...（过长已截断）