Skip to main content
Add these nodes with the pipeline builder: pipeline.add(name="...").<node>(...). Each entry lists the node’s configuration parameters. See the Pipeline reference for add, run, and lifecycle methods.

​
ai_fill_pdf — AI Fill PDF

Fill out a PDF with form fields using AI. The AI will understand and fill each field using provided context. To convert your PDF to have fillable input fields, use: https://www.sejda.com/pdf-forms 
pipeline.add(name="node").ai_fill_pdf(provider="anthropic", context="...", file=...)
Parameters
​
select_pages
bool
default:"False"
Whether to select specific pages to fill
​
provider
str
required
The model provider
​
model
str
default:"''"
The specific model for filling the PDF
​
context
str
required
Context used by LLM to fill PDF fields
​
file
AcceptsFile
required
The PDF with form fields to be filled
​
selected_pages
str
default:"''"
PDF page range

​
ai_filter_list — AI Filter List

Filter items in a list given a specific AI condition. Example, Filter (Red, White, Boat) by whether it is a color: (Red, White) 
pipeline.add(name="node").ai_filter_list(provider="anthropic", ai_condition="...", filter_by=..., list_to_filter=...)
Parameters
​
filter_mode
str
default:"'single'"
Choose whether to filter a single list or filter by another list One of: another, single
​
provider
str
required
The model provider
​
model
str
default:"''"
The specific model for filtering
​
ai_condition
str
required
Write in natural language the condition to filter each item in the list
​
filter_by
list[str]
required
The items to filter the list by
​
list_to_filter
list[str]
required
The list to filter
​
output_blank_value
bool
default:"False"
If true, output a blank value for values that do not meet the filter condition. If false, nothing will be outputted
​
sampling
SamplingConfig
​
max_tokens
Any
​
temperature
Any
​
top_p
Any

​
ai_operations — Leverage AI for various tasks

Leverage AI for various tasks 
pipeline.add(name="node").ai_operations()
Parameters
​
sub_type
str
default:"''"

​
append_files — Append Files

Append files together in successive fashion 
pipeline.add(name="node").append_files()
Parameters
​
file_type
str
default:"'PDF'"
One of: PDF, PPTX
​
selected_files
AcceptsFileList
default:"[]"

​
categorizer — Categorizer

Categorize text using AI into custom-defined buckets 
pipeline.add(name="node").categorizer(provider="anthropic", text="...")
Parameters
​
justification
bool
default:"False"
Include the AI’s justification for its score
​
provider
str
required
The model provider
​
model
str
default:"''"
The specific model for categorization
​
text
str
required
The text that will be categorized
​
additional_context
str
default:"''"
Provide any additional context or instructions
​
fields
ListType | list[List[Dict[str, Any]]] | list[NameDescription]
default:"[]"
The fields to be categorized
​
sampling
SamplingConfig
​
max_tokens
int
The maximum number of tokens to generate
​
temperature
float
The temperature of the model
​
top_p
float
The top-p value

​
combine_list — Combine List

Combine multiple lists into one list. Final list is ordered in the order of the input lists. 
pipeline.add(name="node").combine_list(list=...)
Parameters
​
type
str
default:"'string'"
The type of the list
​
list
ListType | list[List[Any]] | list[List[List[Any]]]
required
List to be combined

​
combine_text — Combine Text

Combine text inputs into a singular output. 
pipeline.add(name="node").combine_text(text=...)
Parameters
​
text
list[str]
required

​
create_list — Create List

Create a list from input texts. Final list is ordered in the order of the inputs. 
pipeline.add(name="node").create_list(list=...)
Parameters
​
type
str
default:"'string'"
The type of the list
​
list
ListType | list[Any] | list[List[Any]]
required
Value to be added to the list

​
csv_reader — CSV Reader

Read the contents from a CSV file and output a list of the data for each column. 
pipeline.add(name="node").csv_reader(selected_file=..., sheet="...")
Parameters
​
file_type
str
default:"'CSV'"
The type of file to read. One of: CSV, EXCEL
​
is_file_variable
bool
default:"True"
​
processed_outputs
dict
default:"{}"
​
selected_file
AcceptsFile
required
The file to read.
​
sheet
str
required
The Excel sheet to read from.
​
sheets
list[str]
default:"[]"
​
manual_columns
ListType | list[ColumnItem] | list[List[Dict[str, Any]]]
default:"[]"
Define the name(s) of the columns that you want to read
​
columns
ListType | list[ColumnItem]
default:"[]"
Define the name(s) of the columns that you want to read

​
csv_to_excel — CSV To Excel

Convert a CSV file into XLSX. 
pipeline.add(name="node").csv_to_excel()
Parameters
​
csv_file
AcceptsFile
​
horizontal_alignment
str
default:"'left'"
One of: center, centerContinuous, distributed, fill, general, justify, left, right
​
max_column_width
int
default:"100"
​
vertical_alignment
str
default:"'top'"
One of: bottom, center, distributed, justify, top
​
wrap_text
bool
default:"True"

​
csv_writer — CSV Writer

Create a CSV from data. 
pipeline.add(name="node").csv_writer()
Parameters
​
selected_option
str
default:"'new'"
Whether to create a new CSV or update an existing one. One of: new, old
​
load_option
str
default:"'file'"
Whether to load the CSV from a file or a string. One of: file, text
​
columns
ListType | list[ListNameTypeValue] | list[List[Dict[str, Any]]]
default:"[]"
The columns to write to the CSV.
​
selected_file
AcceptsFile
The file to update.
​
csv_string
str
default:"''"
The CSV string to write.

​
custom_smtp_email_sender — Custom Smtp Email Sender

Send emails using a custom SMTP server configuration 
pipeline.add(name="node").custom_smtp_email_sender(email_subject="...", recipient_email="...", sender_email="...", sender_password="...")
Parameters
​
connection_type
str
default:"'SSL'"
One of: SSL, STARTTLS, TLS
​
email_body
str
default:"''"
​
email_subject
str
required
​
recipient_email
str
required
​
send_as_html
bool
default:"''"
​
sender_email
str
required
​
sender_name
str
default:"''"
​
sender_password
str
required
​
smtp_server
str
required
​
smtp_server_port
int
default:"465"

​
dataframe_aggregate — Dataframe Aggregate

Aggregate data from a dataframe. 
pipeline.add(name="node").dataframe_aggregate(aggregation_column="...", aggregation_type="AVG", dataframe=..., group_by_columns=...)
Parameters
​
dataframe_type
str
default:"'table'"
The type of dataframe to be used One of: table
​
aggregation_column
str
required
Select a numeric column (integer or decimal) to perform aggregation
​
aggregation_type
str
required
The aggregation to perform One of: AVG, COUNT, MAX, MIN, SUM
​
dataframe
AcceptsDataframe
required
The dataframe to aggregate
​
group_by_columns
list[str]
required
The columns to group by

​
dataframe_get_schema — Dataframe Get Schema

Get the schema of a dataframe including columns, types, and constraints. 
pipeline.add(name="node").dataframe_get_schema(dataframe=...)
Parameters
​
dataframe_type
str
default:"'table'"
The type of dataframe to be used One of: table
​
dataframe
AcceptsDataframe
required
The dataframe to get schema from

​
dataframe_nl_query — Dataframe NL Query

Execute natural language queries on dataframes. 
pipeline.add(name="node").dataframe_nl_query(dataframe=..., nlquery="...")
Parameters
​
dataframe_type
str
default:"'table'"
The type of dataframe to be used One of: table
​
dataframe
AcceptsDataframe
required
The dataframe to query using natural language
​
nlquery
str
required
Ask a question about your data in natural language. Example: What are the top 10 rows?

​
dataframe_operations — Dataframe Operations

Dataframe Operations 
pipeline.add(name="node").dataframe_operations()
Parameters
​
sub_type
str
default:"''"

​
dataframe_raw_query — Dataframe Raw Query

Execute custom queries on dataframes. 
pipeline.add(name="node").dataframe_raw_query(query="...", dataframe=..., preload=True)
Parameters
​
dataframe_type
str
default:"'table'"
The type of dataframe to be used One of: table
​
query
str
required
SQL query to execute on the dataframe. Use {df} as the table name placeholder. Example: SELECT * FROM {df} limit 10;
​
dataframe
AcceptsDataframe
required
The dataframe to query
​
preload
bool
required
Whether to preload dataframe instead of lazy load

​
dataframe_read_columns — Dataframe Read Columns

Read columns from a dataframe. 
pipeline.add(name="node").dataframe_read_columns(column_name="...", dataframe=...)
Parameters
​
column_type
str
default:"'any'"
The expected type of the column values
​
dataframe_type
str
default:"'table'"
The type of dataframe to be used One of: table
​
column_name
str
required
The name of the column to read
​
dataframe
AcceptsDataframe
required

​
duplicate_list — Duplicate List

Create a new list by duplicating a single item with the size of the new list either matching the size of another list, or a specified size. 
pipeline.add(name="node").duplicate_list(input_field=..., list_size_to_match=..., list_size=0)
Parameters
​
specify_list_size
bool
default:"False"
Check this box if you want to manually specify the list size. In this case ‘Match List Size’ will not be used.
​
type
str
default:"'string'"
The type of the list
​
input_field
Any | ListType | list[Any]
required
Item to duplicate
​
list_size_to_match
list[str]
required
The size of the list you want to match
​
list_size
int
required
The size of the new list

​
email_notification — Send email notifications from no-reply@vectorshiftmail.com

Send email notifications from no-reply@vectorshiftmail.com 
pipeline.add(name="node").email_notification(email_subject="...", recipient_email="...")
Parameters
​
email_body
str
default:"''"
​
email_subject
str
required
​
recipient_email
str
required
​
send_as_html
bool
default:"''"

​
email_validator — Validate an email address

Validate an email address 
pipeline.add(name="node").email_validator(api_key="...", email_to_validate="...")
Parameters
​
model
str
default:"'regex'"
The validation model to use One of: custom-validator, regex
​
api_key
str
required
The API key to use
​
email_to_validate
str
required
The email you want to validate
​
provider
str
default:"'hunter'"
The validation provider to use One of: debounce, hunter

​
excel_cell_reader — Excel Cell Reader

Read data from an Excel cell. 
pipeline.add(name="node").excel_cell_reader(cell_index="...", selected_file=..., sheet="...")
Parameters
​
cell_index
str
required
​
read_formatting
bool
default:"False"
​
selected_file
AcceptsFile
required
​
sheet
str
required

​
excel_cell_writer — Excel Cell Writer

Write data to an Excel cell. 
pipeline.add(name="node").excel_cell_writer(cell_index="...", cell_value="...", selected_file=..., sheet="...")
Parameters
​
set_vertical_alignment
bool
default:"False"
Whether to set the vertical alignment of the cell.
​
set_horizontal_alignment
bool
default:"False"
Whether to set the horizontal alignment of the cell.
​
set_fill_color
bool
default:"False"
Whether to set the fill color of the cell.
​
cell_index
str
required
The cell to read from.
​
cell_value
str
required
The value to write to the cell.
​
fill_color
str
default:"'FFFFFF'"
The fill color of the cell.
​
horizontal_alignment
str
default:"'left'"
The horizontal alignment of the cell. One of: center, centerContinuous, distributed, fill, general, justify, left, right
​
selected_file
AcceptsFile
required
The file to read from.
​
sheet
str
required
The sheet to read from.
​
vertical_alignment
str
default:"'bottom'"
The vertical alignment of the cell. One of: bottom, center, distributed, justify, top

​
excel_file_reader — Excel File Reader

Read data from an Excel file. 
pipeline.add(name="node").excel_file_reader(selected_file=...)
Parameters
​
read_single_sheet
bool
default:"True"
Whether to read a single sheet from the Excel file.
​
read_formatting
bool
default:"False"
Whether to read the formatting of the cell.
​
read_formula
bool
default:"False"
Whether to read the formula of the cell.
​
selected_file
AcceptsFile
required
The file to read from.
​
sheet
str
default:"''"
The sheet to read from.

​
excel_operations — Process and manipulate Excel files

Process and manipulate Excel files 
pipeline.add(name="node").excel_operations()
Parameters
​
sub_type
str
default:"''"

​
excel_sheets_reader — Excel Sheets Reader

Get list of all sheet names from an Excel file. 
pipeline.add(name="node").excel_sheets_reader(selected_file=...)
Parameters
​
selected_file
AcceptsFile
required

​
excel_writer — Excel Writer

Write data to an Excel sheet. 
pipeline.add(name="node").excel_writer(cell_start_index="...", cell_values=..., selected_file=..., sheet="...")
Parameters
​
set_vertical_alignment
bool
default:"False"
Whether to set the vertical alignment of the cells.
​
set_horizontal_alignment
bool
default:"False"
Whether to set the horizontal alignment of the cells.
​
set_fill_color
bool
default:"False"
Whether to set the fill color of the cells.
​
cell_start_index
str
required
The cell to start writing from.
​
cell_values
list[str]
required
The values to write to the cells.
​
fill_color
str
default:"'FFFFFF'"
The fill color of the cells.
​
horizontal_alignment
str
default:"'left'"
The horizontal alignment of the cells. One of: center, centerContinuous, distributed, fill, general, justify, left, right
​
selected_file
AcceptsFile
required
The file to write to.
​
sheet
str
required
The sheet to write to.
​
vertical_alignment
str
default:"'bottom'"
The vertical alignment of the cells. One of: bottom, center, distributed, justify, top

​
extract_data — Extract Data

Extract key pieces of information or a list of information from a input text. 
pipeline.add(name="node").extract_data(text="...", fields=..., processed_outputs=...)
Parameters
​
model
str
default:"'gpt-4o'"
​
text
str
required
​
additional_context
str
default:"''"
​
fields
ListType | list[List[Dict[str, Any]]] | list[NameTypeDescription]
required
​
processed_outputs
dict
required
​
provider
str
default:"'openai'"

​
extract_to_table — Extract To Table

Extract data to a CSV using AI 
pipeline.add(name="node").extract_to_table(file=..., text_for_extraction="...")
Parameters
​
model
str
default:"'gpt-4o'"
One of: gpt-4o, gpt-4o-2024-08-06, gpt-4o-mini
​
add_columns_manually
bool
default:"False"
​
additional_context
str
default:"''"
​
extract_multiple_rows
bool
default:"True"
​
file
AcceptsFile
required
​
manual_columns
ListType | list[ColumnEntry] | list[List[Dict[str, Any]]]
default:"[]"
​
provider
str
default:"'openai'"
One of: openai
​
text_for_extraction
str
required

​
file_operations — Process and manipulate files

Process and manipulate files 
pipeline.add(name="node").file_operations()
Parameters
​
sub_type
str
default:"''"

​
file_to_text — File To Text

Convert data from type File to type Text 
pipeline.add(name="node").file_to_text(file=...)
Parameters
​
chunk_text
bool
default:"False"
Whether to chunk the text into smaller pieces.
​
decrypt
bool
default:"False"
Use a password to decrypt the file.
​
file
AcceptsFile
required
The file to convert to text.
​
file_parser
str
default:"'default'"
The type of file parser to use. One of: contextual_ai, default, docling, llama_parse, mistral_ocr, reducto, textract
​
password
str
default:"''"
The password to decrypt the file.
​
chunk_overlap
int
default:"400"
The overlap of each chunk of text.
​
chunk_size
int
default:"1024"
The size of each chunk of text.

​
filter_list — Filter List

Filter items in a list given a specific condition. Example, Filter (Red, White, Blue) by (100, 95, 80)>90 is (Red, White) 
pipeline.add(name="node").filter_list(condition_type="Equal", filter_by=..., list_to_filter=..., output_blank_value=True)
Parameters
​
filter_mode
str
default:"'single'"
Choose whether to filter a single list or filter by another list One of: another, single
​
type
str
default:"'string'"
The type of the list
​
condition_type
str
required
The type of condition to apply
​
condition_value
str
default:"''"
The value to compare the list items against
​
filter_by
ListType | list[Any] | list[List[Any]]
required
The items to filter the list by
​
list_to_filter
ListType | list[Any] | list[List[Any]]
required
The list to filter
​
output_blank_value
bool
required
If true, output a blank value for values that do not meet the filter condition. If false, nothing will be outputted

​
find_and_replace — Find And Replace

Find and replace words in a given text 
pipeline.add(name="node").find_and_replace(text_to_manipulate="...")
Parameters
​
replacements
ListType | list[FindReplace] | list[List[Dict[str, Any]]]
default:"[]"
​
text_to_manipulate
str
required

​
flatten_list — Flatten List

Flatten list of lists into a single list. For example, [[a, b], [c, d]] becomes [a,b,c,d]. 
pipeline.add(name="node").flatten_list(list_of_lists=...)
Parameters
​
type
str
default:"'string'"
The type of the list
​
list_of_lists
ListType | list[List[Any]] | list[List[List[Any]]]
required
List of lists to be flattened

​
generate_chart — Generate Chart

Use this to generate a chart from. Convert a tabular file, dataframe or table to a chart or graph visualization. Supports bar, line, pie, scatter, and donut charts/graphs. 
pipeline.add(name="node").generate_chart(dataframe=..., dataframe_column_names="...", dataframe_type="csv", title="...")
Parameters
​
chart_type
str
default:"'bar'"
The type of chart to generate (bar, line, pie, scatter, donut) One of: bar, donut, line, pie, scatter, time_series
​
aggregation
str
default:"'sum'"
How to aggregate values when there are multiple data points per category One of: average, count, max, min, sum
​
chart_description
str
default:"''"
A brief description or subtitle explaining what the chart shows
​
dataframe
AcceptsDataframe
required
The dataframe to visualize as a chart. In case of csv, the input should be a properly formatted valid csv string with appropriate headers. When chaining from a tool that returned a CSV file (e.g. fetch_ratios.table), set dataframe_type=“file” and pass $action.<id>.table — never paste the upstream formatted_text/XML here.
​
dataframe_column_names
str
required
Actual column names from the dataframe. It should be a string representing the comma separated list of column names.
​
dataframe_type
str
required
The type of dataframe to be used. Only available options are table, csv, md, json, file. One of: csv, file, json, md, table
​
legend_orientation
str
default:"'right'"
Where to display the chart legend One of: bottom, hidden, left, right, top
​
sort_order
str
default:"'ascending'"
The order to sort the data One of: ascending, descending
​
title
str
required
The title to display on the chart
​
x_axis_field
str
required
The column name to use for the X-axis (categories). Must EXACTLY match (case-sensitive) one of the column names from the CSV header.
​
x_axis_label
str
default:"''"
The label to display on the X-axis. Defaults to the field name if not provided.
​
y_axis_fields
str
required
Column name(s) for Y-axis values. Must EXACTLY match (case-sensitive) column name(s) from the CSV header. For multi-series charts (multiple lines/bars), use comma-separated names like ‘revenue,profit,cost’.
​
y_axis_label
str
default:"''"
The label to display on the Y-axis
​
currency_symbol
str
default:"''"
Currency symbol (only used with currency format) One of: “, eur, gbp, jpy, usd
​
default_time_period
str
default:"'max'"
Initial time period tab selection One of: 1m, 1y, 5y, 6m, max, ytd
​
number_format
str
default:"'number'"
How to format values One of: currency, number, percent, ratio
​
series_icon_urls
str
default:"''"
Comma-separated icon URLs for each series (company logos, game art, product images, etc.), in same order as y_axis_fields. Leave empty for no icons.
​
series_labels
str
default:"''"
Comma-separated display names for each Y-axis field, in same order as y_axis_fields (e.g. ‘MSFT,NVDA’ for tickers, ‘Halo,Fortnite’ for games, ‘US,EU,APAC’ for regions).
​
show_percent_change
str
default:"'false'"
Set to ‘true’ to show Original/% Change toggle
​
unit_suffix
str
default:"''"
Scale suffix for values One of: “, b, k, m, t

​
get_list_item — Get List Item

Get a value from a list given an index. The first item in the list is index 0. 
pipeline.add(name="node").get_list_item(index=0, list=...)
Parameters
​
type
str
default:"'string'"
The type of the list
​
index
int
required
The index of the item to retrieve
​
list
ListType | list[Any] | list[List[Any]]
required
The list to retrieve the item from

​
join_list_item — Join List Item

Join a list of items into a single piece of text. For example, with / as the separator, [‘a’, ‘b’, ‘c’] becomes ‘a/b/c’ 
pipeline.add(name="node").join_list_item(list=...)
Parameters
​
join_by_newline
bool
default:"False"
Separate each line in the final output with a new line
​
type
str
default:"'string'"
The type of the list
​
join_characters
str
default:"''"
Use a specified character to join list items into a single string
​
list
ListType | list[Any] | list[List[Any]]
required
List of items to be joined

​
json_operations — JSON Operations

Read, create, and update JSON data 
pipeline.add(name="node").json_operations()
Parameters
​
sub_type
str
default:"''"

​
list_deduplicator — List Deduplicator

Remove duplicate items from a list. Outputs a list of unique items. 
pipeline.add(name="node").list_deduplicator(list=...)
Parameters
​
type
str
default:"'string'"
The type of the list One of: bool, float, int32, string, timestamp
​
list
ListType | list[Any] | list[List[Any]]
required
The list to deduplicate

​
list_operations — Process and manipulate lists

Process and manipulate lists 
pipeline.add(name="node").list_operations()
Parameters
​
sub_type
str
default:"''"

​
list_trimmer — List Trimmer

Trim a list to just the sections you want. Enter enter the number of items or specify the section of the list that you want to keep. 
pipeline.add(name="node").list_trimmer(end_index=0, list=..., start_index=0, item_to_keep=0)
Parameters
​
specify_section
bool
default:"False"
Check this to specify a section of the list to keep. Leave unchecked to keep a specified number of items from the start.
​
type
str
default:"'string'"
The type of the list
​
end_index
int
required
The ending index of the section to keep (exclusive).
​
list
ListType | list[Any] | list[List[Any]]
required
The list to trim
​
start_index
int
required
The starting index of the section to keep (inclusive). The first item of the list is index 0.
​
item_to_keep
int
required
Check this to specify a section of the list to keep. Leave unchecked to keep a specified number of items.

​
notifications — Notifications

Send alerts and notifications via different channels 
pipeline.add(name="node").notifications()
Parameters
​
sub_type
str
default:"''"

​
read_json_values — Read JSON Values

Read values from a JSON object based on a provided key(s). 
pipeline.add(name="node").read_json_values(json_string="...", keys=..., processed_outputs=...)
Parameters
​
json_string
str
required
​
keys
ListType | list[KeyItem] | list[List[Dict[str, Any]]]
required
​
processed_outputs
dict
required

​
rename_file — Rename File

Rename an existing file, assigning a new name along with the file extension. 
pipeline.add(name="node").rename_file(file=..., new_name="...")
Parameters
​
file
AcceptsFile
required
​
new_name
str
required

​
sales_data_enrichment — Sales Data Enrichment

Enhance sales data with validation and enrichment processes 
pipeline.add(name="node").sales_data_enrichment()
Parameters
​
sub_type
str
default:"''"

​
scorer — Scorer

Assign a numerical score based on predefined criteria to quantitatively assess a given entity. 
pipeline.add(name="node").scorer(provider="anthropic", text="...", criteria="...")
Parameters
​
justification
bool
default:"False"
Include the AI’s justification for its score
​
provider
str
required
The model provider
​
model
str
default:"''"
The specific model for scoring
​
text
str
required
The text that will be scored
​
additional_context
str
default:"''"
Provide any additional context or instructions
​
criteria
str
required
The criteria that the text will be scored
​
sampling
SamplingConfig
​
max_tokens
Any
​
temperature
Any
​
top_p
Any

​
sms_notification — Send text message notifications

Send text message notifications 
pipeline.add(name="node").sms_notification(message="...", phone_number="...")
Parameters
​
message
str
required
​
phone_number
str
required

​
sort_csv — Sort CSV

Sort a CSV based on a column 
pipeline.add(name="node").sort_csv(file=...)
Parameters
​
is_file_variable
bool
default:"True"
Whether the file is a variable.
​
has_headers
bool
default:"True"
Whether the CSV has headers.
​
column_index
int
default:"0"
The index of the column to sort by.
​
file
AcceptsFile
required
The CSV file to sort.
​
reverse_sort
bool
default:"False"
Whether to reverse the sort.
​
column_to_sort_by
str
default:"''"
The column to sort by.

​
split_text — Split Text

Takes input text and separate it into a List of texts based on the delimiter. 
pipeline.add(name="node").split_text(text="...", character="...")
Parameters
​
delimiter
str
default:"'space'"
The delimiter to split the text on One of: character(s), newline, space
​
text
str
required
The text to split
​
character
str
required
The character(s) to split the text on

​
summarizer — Summarizer

Summarize large texts using AI. 
pipeline.add(name="node").summarizer(provider="anthropic", text="...")
Parameters
​
provider
str
required
The model provider
​
model
str
default:"''"
The specific model for summarization
​
text
str
required
The text to be summarized
​
sampling
SamplingConfig
​
max_tokens
Any
​
temperature
Any
​
top_p
Any

​
table — Table

Table 
pipeline.add(name="node").table()
Parameters
​
sub_type
str
default:"''"

​
table_add_columns — Table Add Columns

Add one or more columns to a table. 
pipeline.add(name="node").table_add_columns(table=..., columns=...)
Parameters
​
table
AcceptsTable
required
​
columns
dict
required

​
table_add_row — Table Add Row

Add New Row to Table. 
pipeline.add(name="node").table_add_row(table=...)
Parameters
​
table
AcceptsTable
required

​
table_aggregate — Table Aggregate

Aggregate data from a table. 
pipeline.add(name="node").table_aggregate(aggregation_column="...", aggregation_type="AVG", dataframe=..., group_by_columns=...)
Parameters
​
aggregation_column
str
required
​
aggregation_type
str
required
One of: AVG, COUNT, MAX, MIN, SUM
​
dataframe
AcceptsTable
required
​
group_by_columns
list[str]
required

​
table_delete_columns — Table Delete Columns

Delete one or more columns from a table. 
pipeline.add(name="node").table_delete_columns(table=..., columns=...)
Parameters
​
table
AcceptsTable
required
​
columns
list[str]
required

​
table_delete_values — Table Delete Values

Delete rows matching a filter. 
pipeline.add(name="node").table_delete_values(table=..., filters="...")
Parameters
​
table
AcceptsTable
required
​
filters
str
required

​
table_read_columns — Table Read Columns

Select column in table to read as list. 
pipeline.add(name="node").table_read_columns(column_name="...", dataframe=...)
Parameters
​
column_type
str
default:"'any'"
The expected type of the column values
​
column_name
str
required
The name of the column to read
​
dataframe
AcceptsTable
required
The table to read from

​
table_rename_column — Table Rename Column

Rename a column in a table. 
pipeline.add(name="node").table_rename_column(table=..., column="...", new_name="...")
Parameters
​
table
AcceptsTable
required
​
column
str
required
​
new_name
str
required

​
table_update_values — Table Update Values

Update the values in rows matching a filter. 
pipeline.add(name="node").table_update_values(table=..., filters="...", values=...)
Parameters
​
table
AcceptsTable
required
​
filters
str
required
​
values
dict
required

​
text_formatter — Text Formatter

Format text based off a specified formatter 
pipeline.add(name="node").text_formatter(text="...", max_num_token=0)
Parameters
​
formatter
str
default:"'To Uppercase'"
The formatter to apply to the text One of: To Lowercase, To Propercase, To Uppercase, Trim Spaces, Truncate
​
text
str
required
The text to format
​
max_num_token
int
required
The maximum number of tokens to truncate the text to

​
text_manipulation — Process and manipulate text

Process and manipulate text 
pipeline.add(name="node").text_manipulation()
Parameters
​
sub_type
str
default:"''"

​
text_to_file — Text To File

Convert data from type Text to type File. 
pipeline.add(name="node").text_to_file(text="...", file_name="...")
Parameters
​
text
str
required
​
file_name
str
required
​
file_type
str
default:"'PDF'"
One of: DOCX, PDF, TXT

​
translator — Translator

Translate text from one language to another. 
pipeline.add(name="node").translator(provider="anthropic", text="...")
Parameters
​
provider
str
required
The model provider
​
model
str
default:"''"
The specific model for translation
​
text
str
required
The text to be translated
​
source_language
str
default:"'Detect Language'"
The language of the input text
​
target_language
str
default:"'English'"
The language to translate to

​
write_json_value — Write JSON Value

Update a specific value in a JSON. 
pipeline.add(name="node").write_json_value(json_string="...")
Parameters
​
selected
str
default:"'new'"
Whether to update the JSON value or create a new JSON One of: new, old
​
fields
ListType | list[KeyValue] | list[List[Dict[str, Any]]]
default:"[]"
​
json_string
str
required
The JSON to update