上文《Dify工作流实战（一）智能文档助手》介绍了智能文档助手，本文介绍下通过dify读取excel的数据，并生成对应的统计图表。
工作流类型：chatflow
制作的excel文件：
| 文章日阅读量 | Dify安装部署 | RAGFlow安装部署 | Dify联网查询 | Dify翻译小助手 | Dify创建知识库 |
| 2025/3/27 | 100 | 101 | 102 | 103 | 104 |
| 2025/3/28 | 105 | 106 | 107 | 108 | 109 |
工作流dsl：
app:
description: ''
icon: 🤖
icon_background: '#FFEAD5'
mode: advanced-chat
name: Excel解析生成图表
use_icon_as_answer_icon: false
dependencies:
- current_identifier: null
type: marketplace
value:
marketplace_plugin_unique_identifier: langgenius/volcengine_maas:0.0.7@f8e44422cfa5b9a6ac1f2d3b43ef1069868efdad1e5cec2590de3f53ceac37b0
kind: app
version: 0.1.5
workflow:
conversation_variables: []
environment_variables: []
features:
file_upload:
allowed_file_extensions:
- .JPG
- .JPEG
- .PNG
- .GIF
- .WEBP
- .SVG
allowed_file_types:
- image
allowed_file_upload_methods:
- local_file
- remote_url
enabled: false
fileUploadConfig:
audio_file_size_limit: 500
batch_count_limit: 50
file_size_limit: 1024
image_file_size_limit: 1000
video_file_size_limit: 10000
workflow_file_upload_limit: 10
image:
enabled: false
number_limits: 3
transfer_methods:
- local_file
- remote_url
number_limits: 3
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
isInLoop: false
sourceType: document-extractor
targetType: llm
id: 1741962070164-source-llm-target
source: '1741962070164'
sourceHandle: source
target: llm
targetHandle: target
type: custom
zIndex: 0
- data:
isInIteration: false
isInLoop: false
sourceType: start
targetType: if-else
id: 1741961981530-source-1741962638469-target
source: '1741961981530'
sourceHandle: source
target: '1741962638469'
targetHandle: target
type: custom
zIndex: 0
- data:
isInLoop: false
sourceType: if-else
targetType: document-extractor
id: 1741962638469-true-1741962070164-target
source: '1741962638469'
sourceHandle: 'true'
target: '1741962070164'
targetHandle: target
type: custom
zIndex: 0
- data:
isInIteration: false
isInLoop: false
sourceType: if-else
targetType: answer
id: 1741962638469-false-1741962945275-target
source: '1741962638469'
sourceHandle: 'false'
target: '1741962945275'
targetHandle: target
type: custom
zIndex: 0
- data:
isInIteration: false
isInLoop: false
sourceType: code
targetType: answer
id: 1741965295287-source-answer-target
source: '1741965295287'
sourceHandle: source
target: answer
targetHandle: target
type: custom
zIndex: 0
- data:
isInLoop: false
sourceType: llm
targetType: code
id: llm-source-1741965295287-target
source: llm
sourceHandle: source
target: '1741965295287'
targetHandle: target
type: custom
zIndex: 0
nodes:
- data:
desc: ''
selected: false
title: 开始
type: start
variables:
- allowed_file_extensions: []
allowed_file_types:
- document
allowed_file_upload_methods:
- local_file
label: 请提供excel
max_length: 1
options: []
required: true
type: file-list
variable: excel
height: 90
id: '1741961981530'
position:
x: 30
y: 275
positionAbsolute:
x: 30
y: 275
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
context:
enabled: false
variable_selector: []
desc: ''
model:
completion_params:
temperature: 0.7
mode: chat
name: DeepSeek-V3
provider: langgenius/volcengine_maas/volcengine_maas
prompt_template:
- id: 5146b7a9-3769-4493-831d-a75bc903a1f7
role: system
text: "你是一个文档提取专家，请根据用户上传文档内容{{#1741962070164.text#}}提取该表格里面的数据返回json格式数据。\n\
其中内容格式‘文章日阅读量’、‘Dify安装部署’、‘RAGFlow安装部署’、‘Dify联网查询’、‘Dify翻译小助手’、‘Dify创建知识库’字段返回信息，返回的结果信息以json格式返回\n\
\n 返回数据格式如下：\n{\n\"文章日阅读量\": [\n{\n\"date\": \"2025-3-1\",\n\"Dify安装部署\"\
: 200,\n\"RAGFlow安装部署\": 300,\n\"Dify联网查询\": 125,\n\"Dify翻译小助手\": 351，\n\
“Dify创建知识库”: 123\n},\n{\n\"date\": \"2025-3-2\",\n\"Dify安装部署\": 323,\n\
\"RAGFlow安装部署\": 335,\n\"Dify联网查询\": 1321,\n\"Dify翻译小助手\": 514,\n“Dify创建知识库”:\
\ 153\n},\n]\n}\n"
selected: false
title: 文档处理LLM
type: llm
variables: []
vision:
enabled: false
height: 90
id: llm
position:
x: 944.6224968394765
y: 275
positionAbsolute:
x: 944.6224968394765
y: 275
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
answer: '{{#1741965295287.result#}}
'
desc: ''
selected: false
title: 直接回复
type: answer
variables: []
height: 105
id: answer
position:
x: 1215.100652446408
y: 414.8319557205739
positionAbsolute:
x: 1215.100652446408
y: 414.8319557205739
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
desc: ''
is_array_file: true
selected: false
title: 文档提取器
type: document-extractor
variable_selector:
- '1741961981530'
- excel
height: 92
id: '1741962070164'
position:
x: 638
y: 275
positionAbsolute:
x: 638
y: 275
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
cases:
- case_id: 'true'
conditions:
- comparison_operator: contains
id: 3b2c44f2-2090-4fa6-a66f-d6e99cb90481
sub_variable_condition:
case_id: 24fd5e4a-804e-4a45-914f-d86ad7711a68
conditions:
- comparison_operator: contains
id: ecf0b999-0b72-49ab-8c37-c5487ca2bf47
key: extension
value: xls
varType: string
logical_operator: and
value: ''
varType: array[file]
variable_selector:
- '1741961981530'
- excel
id: 'true'
logical_operator: or
desc: ''
selected: false
title: 条件分支
type: if-else
height: 150
id: '1741962638469'
position:
x: 334
y: 275
positionAbsolute:
x: 334
y: 275
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
answer: 当前文档不是excel
desc: ''
selected: true
title: 直接回复 2
type: answer
variables: []
height: 102
id: '1741962945275'
position:
x: 638
y: 407
positionAbsolute:
x: 638
y: 407
selected: true
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
code: "import json\nimport os\nimport re\n\ndef main(json_str: str) -> dict:\n\
\ try:\n # 预处理：清理非 JSON 部分\n json_match = re.search(r'\\\
{.*\\}', json_str, re.DOTALL)\n if not json_match:\n return\
\ {\"result\": \"Error: Invalid JSON format\"}\n \n # 提取合法的\
\ JSON 部分\n cleaned_json_str = json_match.group(0)\n \n \
\ # 解析JSON数据\n data = json.loads(cleaned_json_str)\n \
\ filename = data.get(\"filename\", \"stock_chart.html\")\n stock_data\
\ = data.get(\"文章日阅读量\", [])\n \n # 准备数据格式\n dates\
\ = [item['date'].split(' ')[0] for item in stock_data] # 提取日期部分（去掉时间）\n\
\ articles_read_num1 = [item['Dify安装部署'] for item in stock_data]\n\
\ articles_read_num2 = [item['RAGFlow安装部署'] for item in stock_data]\n\
\ articles_read_num3 = [item['Dify联网查询'] for item in stock_data]\n\
\ articles_read_num4 = [item['Dify翻译小助手'] for item in stock_data]\n\
\ articles_read_num5 = [item['Dify创建知识库'] for item in stock_data]\n\
\ \n # 构建ECharts配置\n echarts_config = {\n \
\ \"title\": {\n \"text\": \"文章日阅读量\"\n },\n\
\ \"legend\": {\n \"data\": [\"Dify安装部署\", \"\
RAGFlow安装部署\", \"Dify联网查询\", \"Dify翻译小助手\", \"Dify创建知识库\"]\n \
\ },\n \"tooltip\": {},\n \"dataset\": {\n \
\ \"source\": [\n [\"日期\", \"Dify安装部署\", \"\
RAGFlow安装部署\", \"Dify联网查询\", \"Dify翻译小助手\", \"Dify创建知识库\"],\n \
\ *[[dates[i], articles_read_num1[i], articles_read_num2[i], articles_read_num3[i],\
\ articles_read_num4[i], articles_read_num5[i]] \n \
\ for i in range(len(dates))]\n ]\n },\n \
\ \"xAxis\": [\n {\"type\": \"category\", \"gridIndex\"\
: 0}\n \n ],\n \"yAxis\": [\n \
\ {\n \"gridIndex\": 0,\n \
\ \"name\": \"日阅读量（单位：次）\"\n }\n \n \
\ ],\n \"grid\": [\n {\"bottom\": \"55%\"\
},\n {\"top\": \"55%\"}\n ],\n \"series\"\
: [\n # 折线图系列\n # {\"type\": \"line\", \"\
seriesLayoutBy\": \"row\", \"name\": \"Dify安装部署\"},\n # {\"\
type\": \"line\", \"seriesLayoutBy\": \"row\", \"name\": \"RAGFlow安装部署\"\
},\n # {\"type\": \"line\", \"seriesLayoutBy\": \"row\",\
\ \"name\": \"Dify联网查询\"},\n # {\"type\": \"line\", \"seriesLayoutBy\"\
: \"row\", \"name\": \"Dify翻译小助手\"},\n # {\"type\": \"line\"\
, \"seriesLayoutBy\": \"row\", \"name\": \"Dify创建知识库\"}\n \n \
\ # 柱状图系列\n {\"type\": \"bar\", \"xAxisIndex\"\
: 0, \"yAxisIndex\": 0, \"name\": \"Dify安装部署\"},\n {\"type\"\
: \"bar\", \"xAxisIndex\": 0, \"yAxisIndex\": 0, \"name\": \"RAGFlow安装部署\"\
},\n {\"type\": \"bar\", \"xAxisIndex\": 0, \"yAxisIndex\"\
: 0, \"name\": \"Dify联网查询\"},\n {\"type\": \"bar\", \"xAxisIndex\"\
: 0, \"yAxisIndex\": 0, \"name\": \"Dify翻译小助手\"},\n {\"type\"\
: \"bar\", \"xAxisIndex\": 0, \"yAxisIndex\": 0, \"name\": \"Dify创建知识库\"\
}\n ]\n }\n \n # 生成输出文件\n output\
\ = \"```echarts\\n\" + json.dumps(echarts_config, indent=2, ensure_ascii=False)\
\ + \"\\n```\"\n \n # 返回结果\n return {\n \
\ \"result\": output\n }\n \n except Exception as e:\n \
\ return {\n \"result\": f\"Error: {str(e)}\"\n }"
code_language: python3
desc: ''
outputs:
result:
children: null
type: string
selected: false
title: 代码执行
type: code
variables:
- value_selector:
- llm
- text
variable: json_str
height: 54
id: '1741965295287'
position:
x: 1244.7895556070257
y: 275
positionAbsolute:
x: 1244.7895556070257
y: 275
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
viewport:
x: -231.4144266814012
y: -33.558973525201964
zoom: 0.8375732611651916点击运行，把excel上传上去，然后输入：解析这篇文档
最后工作流处理结果如下图：
备注：
1、这里excel是一个案例，里面对应的字段在llm节点的system里面有配置，如果想要修改excel的格式的话，llm节点的system也需要进行修改
发表评论