Files
urbanLifeline/dify/api/services/rag_pipeline/transform/website-crawl-general-economy.yml
2025-12-01 17:21:38 +08:00

675 lines
20 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

dependencies:
- current_identifier: null
type: marketplace
value:
plugin_unique_identifier: langgenius/general_chunker:0.0.1@e3da408b7277866404c3f884d599261f9d0b9003ea4ef7eb3b64489bdf39d18b
- current_identifier: null
type: marketplace
value:
plugin_unique_identifier: langgenius/firecrawl_datasource:0.0.1@f7aed0a26df0e5f4b9555371b5c9fa6db3c7dcf6a46dd1583245697bd90a539a
- current_identifier: null
type: marketplace
value:
plugin_unique_identifier: langgenius/jina_datasource:0.0.1@cf23afb2c3eeccc5a187763a1947f583f0bb10aa56461e512ac4141bf930d608
kind: rag_pipeline
rag_pipeline:
description: ''
icon: 📙
icon_background: ''
icon_type: emoji
name: website-crawl-general-economy
version: 0.1.0
workflow:
conversation_variables: []
environment_variables: []
features: {}
graph:
edges:
- data:
isInIteration: false
isInLoop: false
sourceType: datasource
targetType: variable-aggregator
id: 1752491761974-source-1752565435219-target
source: '1752491761974'
sourceHandle: source
target: '1752565435219'
targetHandle: target
type: custom
zIndex: 0
- data:
isInLoop: false
sourceType: datasource
targetType: variable-aggregator
id: 1752565402678-source-1752565435219-target
source: '1752565402678'
sourceHandle: source
target: '1752565435219'
targetHandle: target
type: custom
zIndex: 0
- data:
isInIteration: false
isInLoop: false
sourceType: variable-aggregator
targetType: tool
id: 1752565435219-source-1752569675978-target
source: '1752565435219'
sourceHandle: source
target: '1752569675978'
targetHandle: target
type: custom
zIndex: 0
- data:
isInLoop: false
sourceType: tool
targetType: knowledge-index
id: 1752569675978-source-1752477924228-target
source: '1752569675978'
sourceHandle: source
target: '1752477924228'
targetHandle: target
type: custom
zIndex: 0
nodes:
- data:
chunk_structure: text_model
embedding_model: text-embedding-ada-002
embedding_model_provider: langgenius/openai/openai
index_chunk_variable_selector:
- '1752569675978'
- result
indexing_technique: economy
keyword_number: 10
retrieval_model:
score_threshold: 0.5
score_threshold_enabled: false
search_method: keyword_search
top_k: 3
vector_setting:
embedding_model_name: text-embedding-ada-002
embedding_provider_name: langgenius/openai/openai
selected: true
title: Knowledge Base
type: knowledge-index
height: 114
id: '1752477924228'
position:
x: 2140.4053851189346
y: 281.3910724383104
positionAbsolute:
x: 2140.4053851189346
y: 281.3910724383104
selected: true
sourcePosition: right
targetPosition: left
type: custom
width: 242
- data:
datasource_configurations: {}
datasource_label: Jina Reader
datasource_name: jina_reader
datasource_parameters:
crawl_sub_pages:
type: mixed
value: '{{#rag.1752491761974.jina_crawl_sub_pages#}}'
limit:
type: variable
value:
- rag
- '1752491761974'
- jina_limit
url:
type: mixed
value: '{{#rag.1752491761974.jina_url#}}'
use_sitemap:
type: mixed
value: '{{#rag.1752491761974.jina_use_sitemap#}}'
plugin_id: langgenius/jina_datasource
provider_name: jinareader
provider_type: website_crawl
selected: false
title: Jina Reader
type: datasource
height: 52
id: '1752491761974'
position:
x: 1067.7526055798794
y: 281.3910724383104
positionAbsolute:
x: 1067.7526055798794
y: 281.3910724383104
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 242
- data:
datasource_configurations: {}
datasource_label: Firecrawl
datasource_name: crawl
datasource_parameters:
crawl_subpages:
type: mixed
value: '{{#rag.1752565402678.firecrawl_crawl_sub_pages#}}'
exclude_paths:
type: mixed
value: '{{#rag.1752565402678.firecrawl_exclude_paths#}}'
include_paths:
type: mixed
value: '{{#rag.1752565402678.firecrawl_include_only_paths#}}'
limit:
type: variable
value:
- rag
- '1752565402678'
- firecrawl_limit
max_depth:
type: variable
value:
- rag
- '1752565402678'
- firecrawl_max_depth
only_main_content:
type: mixed
value: '{{#rag.1752565402678.firecrawl_extract_main_content#}}'
url:
type: mixed
value: '{{#rag.1752565402678.firecrawl_url#}}'
plugin_id: langgenius/firecrawl_datasource
provider_name: firecrawl
provider_type: website_crawl
selected: false
title: Firecrawl
type: datasource
height: 52
id: '1752565402678'
position:
x: 1067.7526055798794
y: 417.32608398342404
positionAbsolute:
x: 1067.7526055798794
y: 417.32608398342404
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 242
- data:
output_type: string
selected: false
title: Variable Aggregator
type: variable-aggregator
variables:
- - '1752491761974'
- content
- - '1752565402678'
- content
height: 129
id: '1752565435219'
position:
x: 1505.4306671642219
y: 281.3910724383104
positionAbsolute:
x: 1505.4306671642219
y: 281.3910724383104
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 242
- data:
is_team_authorization: true
output_schema:
properties:
result:
description: The result of the general chunk tool.
properties:
general_chunks:
items:
description: The chunk of the text.
type: string
type: array
type: object
type: object
paramSchemas:
- auto_generate: null
default: null
form: llm
human_description:
en_US: The text you want to chunk.
ja_JP: チャンク化したいテキスト。
pt_BR: O texto que você deseja dividir.
zh_Hans: 你想要分块的文本。
label:
en_US: Input Variable
ja_JP: 入力変数
pt_BR: Variável de entrada
zh_Hans: 输入变量
llm_description: The text you want to chunk.
max: null
min: null
name: input_variable
options: []
placeholder: null
precision: null
required: true
scope: null
template: null
type: string
- auto_generate: null
default: null
form: llm
human_description:
en_US: The delimiter of the chunks.
ja_JP: チャンクの区切り記号。
pt_BR: O delimitador dos pedaços.
zh_Hans: 块的分隔符。
label:
en_US: Delimiter
ja_JP: 区切り記号
pt_BR: Delimitador
zh_Hans: 分隔符
llm_description: The delimiter of the chunks, the format of the delimiter
must be a string.
max: null
min: null
name: delimiter
options: []
placeholder: null
precision: null
required: true
scope: null
template: null
type: string
- auto_generate: null
default: null
form: llm
human_description:
en_US: The maximum chunk length.
ja_JP: 最大長のチャンク。
pt_BR: O comprimento máximo do bloco
zh_Hans: 最大块的长度。
label:
en_US: Maximum Chunk Length
ja_JP: チャンク最大長
pt_BR: O comprimento máximo do bloco
zh_Hans: 最大块的长度
llm_description: The maximum chunk length, the format of the chunk size
must be an integer.
max: null
min: null
name: max_chunk_length
options: []
placeholder: null
precision: null
required: true
scope: null
template: null
type: number
- auto_generate: null
default: null
form: llm
human_description:
en_US: The chunk overlap length.
ja_JP: チャンクの重複長
pt_BR: The chunk overlap length.
zh_Hans: 块的重叠长度。
label:
en_US: Chunk Overlap Length
ja_JP: チャンク重複長
pt_BR: Chunk Overlap Length
zh_Hans: 块的重叠长度
llm_description: The chunk overlap length, the format of the chunk overlap
length must be an integer.
max: null
min: null
name: chunk_overlap_length
options: []
placeholder: null
precision: null
required: false
scope: null
template: null
type: number
- auto_generate: null
default: null
form: llm
human_description:
en_US: Replace consecutive spaces, newlines and tabs
ja_JP: 連続のスペース、改行、まだはタブを置換する
pt_BR: Replace consecutive spaces, newlines and tabs
zh_Hans: 替换连续的空格、换行符和制表符
label:
en_US: Replace Consecutive Spaces, Newlines and Tabs
ja_JP: 連続のスペース、改行、まだはタブを置換する
pt_BR: Replace Consecutive Spaces, Newlines and Tabs
zh_Hans: 替换连续的空格、换行符和制表符
llm_description: Replace consecutive spaces, newlines and tabs, the format
of the replace must be a boolean.
max: null
min: null
name: replace_consecutive_spaces_newlines_tabs
options: []
placeholder: null
precision: null
required: false
scope: null
template: null
type: boolean
- auto_generate: null
default: null
form: llm
human_description:
en_US: Delete all URLs and email addresses
ja_JP: すべてのURLとメールアドレスを削除する
pt_BR: Delete all URLs and email addresses
zh_Hans: 删除所有URL和电子邮件地址
label:
en_US: Delete All URLs and Email Addresses
ja_JP: すべてのURLとメールアドレスを削除する
pt_BR: Delete All URLs and Email Addresses
zh_Hans: 删除所有URL和电子邮件地址
llm_description: Delete all URLs and email addresses, the format of the
delete must be a boolean.
max: null
min: null
name: delete_all_urls_and_email_addresses
options: []
placeholder: null
precision: null
required: false
scope: null
template: null
type: boolean
params:
chunk_overlap_length: ''
delete_all_urls_and_email_addresses: ''
delimiter: ''
input_variable: ''
max_chunk_length: ''
replace_consecutive_spaces_newlines_tabs: ''
provider_id: langgenius/general_chunker/general_chunker
provider_name: langgenius/general_chunker/general_chunker
provider_type: builtin
selected: false
title: General Chunker
tool_configurations: {}
tool_description: A tool for general text chunking mode, the chunks retrieved and recalled are the same.
tool_label: General Chunker
tool_name: general_chunker
tool_parameters:
chunk_overlap_length:
type: variable
value:
- rag
- shared
- chunk_overlap
delete_all_urls_and_email_addresses:
type: mixed
value: '{{#rag.shared.delete_urls_email#}}'
delimiter:
type: mixed
value: '{{#rag.shared.delimiter#}}'
input_variable:
type: mixed
value: '{{#1752565435219.output#}}'
max_chunk_length:
type: variable
value:
- rag
- shared
- max_chunk_length
replace_consecutive_spaces_newlines_tabs:
type: mixed
value: '{{#rag.shared.replace_consecutive_spaces#}}'
type: tool
height: 52
id: '1752569675978'
position:
x: 1807.4306671642219
y: 281.3910724383104
positionAbsolute:
x: 1807.4306671642219
y: 281.3910724383104
sourcePosition: right
targetPosition: left
type: custom
width: 242
viewport:
x: -707.721097109337
y: -93.07807382100896
zoom: 0.9350632198875476
rag_pipeline_variables:
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: '1752491761974'
default_value: null
label: URL
max_length: 256
options: []
placeholder: https://docs.dify.ai/en/
required: true
tooltips: null
type: text-input
unit: null
variable: jina_url
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: '1752491761974'
default_value: 10
label: Limit
max_length: 48
options: []
placeholder: null
required: true
tooltips: null
type: number
unit: null
variable: jina_limit
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: '1752491761974'
default_value: null
label: Crawl sub-pages
max_length: 48
options: []
placeholder: null
required: false
tooltips: null
type: checkbox
unit: null
variable: jina_crawl_sub_pages
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: '1752491761974'
default_value: null
label: Use sitemap
max_length: 48
options: []
placeholder: null
required: false
tooltips: Follow the sitemap to crawl the site. If not, Jina Reader will crawl
iteratively based on page relevance, yielding fewer but higher-quality pages.
type: checkbox
unit: null
variable: jina_use_sitemap
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: '1752565402678'
default_value: null
label: URL
max_length: 256
options: []
placeholder: https://docs.dify.ai/en/
required: true
tooltips: null
type: text-input
unit: null
variable: firecrawl_url
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: '1752565402678'
default_value: true
label: Crawl sub-pages
max_length: 48
options: []
placeholder: null
required: false
tooltips: null
type: checkbox
unit: null
variable: firecrawl_crawl_sub_pages
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: '1752565402678'
default_value: 10
label: Limit
max_length: 48
options: []
placeholder: null
required: true
tooltips: null
type: number
unit: null
variable: firecrawl_limit
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: '1752565402678'
default_value: null
label: Max depth
max_length: 48
options: []
placeholder: ''
required: false
tooltips: Maximum depth to crawl relative to the entered URL. Depth 0 just scrapes
the page of the entered url, depth 1 scrapes the url and everything after enteredURL
+ one /, and so on.
type: number
unit: null
variable: firecrawl_max_depth
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: '1752565402678'
default_value: null
label: Exclude paths
max_length: 256
options: []
placeholder: blog/*, /about/*
required: false
tooltips: null
type: text-input
unit: null
variable: firecrawl_exclude_paths
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: '1752565402678'
default_value: null
label: Include only paths
max_length: 256
options: []
placeholder: articles/*
required: false
tooltips: null
type: text-input
unit: null
variable: firecrawl_include_only_paths
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: '1752565402678'
default_value: null
label: firecrawl_extract_main_content
max_length: 48
options: []
placeholder: null
required: false
tooltips: null
type: checkbox
unit: null
variable: firecrawl_extract_main_content
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: shared
default_value: \n\n
label: Delimiter
max_length: 100
options: []
placeholder: null
required: true
tooltips: A delimiter is the character used to separate text. \n\n is recommended
for splitting the original document into large parent chunks. You can also use
special delimiters defined by yourself.
type: text-input
unit: null
variable: delimiter
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: shared
default_value: 1024
label: Maximum chunk length
max_length: 48
options: []
placeholder: null
required: true
tooltips: null
type: number
unit: characters
variable: max_chunk_length
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: shared
default_value: 50
label: chunk_overlap
max_length: 48
options: []
placeholder: null
required: false
tooltips: Setting the chunk overlap can maintain the semantic relevance between
them, enhancing the retrieve effect. It is recommended to set 10%25% of the
maximum chunk size.
type: number
unit: characters
variable: chunk_overlap
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: shared
default_value: null
label: replace_consecutive_spaces
max_length: 48
options: []
placeholder: null
required: false
tooltips: null
type: checkbox
unit: null
variable: replace_consecutive_spaces
- allow_file_extension: null
allow_file_upload_methods: null
allowed_file_types: null
belong_to_node_id: shared
default_value: null
label: Delete all URLs and email addresses
max_length: 48
options: []
placeholder: null
required: false
tooltips: null
type: checkbox
unit: null
variable: delete_urls_email