Creates a column that segments and sorts data values into bins. bins can be an integer or a list. When bins is an integer, the input data is split equally into that number of bins. When bins is a list, the input data is split based on the list boundaries.
Name or list of names of new columns or column_name: value pairs.
string, array
—
Yes
Options
value
(Optional) Value(s) to add in the new column(s). If using a dictionary in output, value can only be a string.
string, number, object, array, boolean, null
null
No
value_if_exists
Determines behaviour when the output column already exists. existing (default): leave the column unchanged. coalesce: fill empty/null cells with the new value, keeping non-null cells. new: overwrite the entire column with the new value.
string; one of:
existing
coalesce
new
"existing"
No
coalesce_value
Only used when value_if_exists is coalesce. Determines which side is preferred when both the existing and new values are non-empty. existing (default): keep the existing value, only fill empty/null cells with the new value. new: keep the new value, only fall back to the existing value where the new value is empty/null.
string; one of:
existing
new
"existing"
No
Conditions
if
Condition that determines whether the wrangle runs as a whole. Recipe variables may be referenced with ${variable}.
string
—
No
where
Filter rows before applying the wrangle using SQL-like criteria, such as column1 = 123 OR column2 = 'abc'.
string
—
No
where_params
Values used with where for parameterized criteria. Uses SQLite placeholder syntax such as ? or :name.
The output column the embeddings will be saved as.
string, null
null
No
Options
task
The task type for the embedding model. Only applicable for the Jina provider. Selects the appropriate task-specific adapter.
string, null; one of:
retrieval.query
retrieval.passage
text-matching
classification
separation
null
No
Formatting
output_type
Output the embeddings as a numpy array or a python list Default - python list.
string; one of:
numpy array
python list
"python list"
No
precision
The precision of the embeddings. Default is float32. This should be used with output_type numpy array.
string; one of:
float16
float32
"float32"
No
Execution
batch_size
The number of rows to submit per individual request.
integer
100
No
threads
The number of requests to submit in parallel. Each request contains the number of rows set as batch_size.
integer
10
No
Errors
retries
The number of times to retry if the request fails. This will apply exponential backoff to help with rate limiting.
integer
0
No
Details
api_key
The API key.
string
—
Yes
model
The specific model to use to generate the embeddings.
string
"text-embedding-3-small"
No
url
The endpoint to send embedding requests to. Defaults to the standard endpoint for the resolved provider. Setting a Jina URL without an explicit provider will automatically use Jina's request/response format.
string
"https://api.openai.com/v1/embeddings"
No
provider
Controls the request/response format for the embedding API. When omitted, inferred from url (jina.ai → jina, otherwise openai). Setting provider also sets the default url for that provider, so you only need one of provider or url for standard endpoints. Use both together only when pointing to a custom endpoint that uses a non-default provider's API format (e.g. a Jina-compatible proxy).
string, null; one of:
openai
jina
null
No
Conditions
if
Condition that determines whether the wrangle runs as a whole. Recipe variables may be referenced with ${variable}.
string
—
No
where
Filter rows before applying the wrangle using SQL-like criteria, such as column1 = 123 OR column2 = 'abc'.
string
—
No
where_params
Values used with where for parameterized criteria. Uses SQLite placeholder syntax such as ? or :name.
Makes use of a Jinja template to create a description, title, or summary based on your data.
info
Jinja templates do not allow variables with spaces. This wrangle automatically replaces spaces in column headers with underscores, so use underscores instead of spaces when referencing columns in the template.
Specify a name of column containing a dictionary of elements to be used in jinja template. Otherwise, the column headers will be used as keys.
string, null
null
No
Options
template
A dictionary which defines the template/location as well as the form which the template is input. If any keys use a space, they must be replaced with an underscore. Note: spaces within column names are replaced by underscores (_).
object
—
Yes
Conditions
if
Condition that determines whether the wrangle runs as a whole. Recipe variables may be referenced with ${variable}.
string
—
No
where
Filter rows before applying the wrangle using SQL-like criteria, such as column1 = 123 OR column2 = 'abc'.
string
—
No
where_params
Values used with where for parameterized criteria. Uses SQLite placeholder syntax such as ? or :name.