Chunker

Overview

You can use this Snap to chunk knowledge context in a customized manner as per the Snap configuration. You can use the output of this Snap to query the vector data.


Chunker Snap Overview

Prerequisites

None.

Limitations and Known Issues

None.

Snap Views

View Description Examples of Upstream and Downstream Snaps
Input This Snap supports a maximum of one binary or document input view.
  • Binary Input type: Requires a Binary file as an input.
  • Document Input type: Requires a Document input and provides an expression-enabled property (by default) - Content for input.
Output This Snap has at the most one document output view. There is an output document for each chunk generated (includes passing the original input document/header with every request). The resultant chunks can then be embedded and stored in the vector database. Pinecone Upsert
Error

Error handling is a generic way to handle errors without losing data or failing the Snap execution. You can handle the errors that the Snap might encounter when running the pipeline by choosing one of the following options from the When errors occur list under the Views tab. The available options are:

  • Stop Pipeline Execution Stops the current pipeline execution when the Snap encounters an error.
  • Discard Error Data and Continue Ignores the error, discards that record, and continues with the remaining records.
  • Route Error Data to Error View Routes the error data to an error view without stopping the Snap execution.

Learn more about Error handling in Pipelines.

Snap Settings

Note:
  • Suggestion icon (): Indicates a list that is dynamically populated based on the configuration.
  • Expression icon (): Indicates whether the value is an expression (if enabled) or a static value (if disabled). Learn more about Using Expressions in SnapLogic.
  • Add icon (): Indicates that you can add fields in the field set.
  • Remove icon (): Indicates that you can remove fields from the field set.
Field / Field Set Type Description
Label String

Required. Specify a unique name for the Snap. Modify this to be more appropriate, especially if there are more than one of the same Snap in the pipeline.

Default value: Chunker

Example: Create chunk of report
Content String/Expression

Appears when the Input type is Document in the Views tab.

Required. Specify the text content to be chunked.

Default value: N/A

Example: "test text"
Chunk unit Dropdown list/Expression
Required. Specify the unit of the chunk size and the chunk overlap. Available options include:
  • Char: Refers to character-based chunking. If you choose this option as the chunk unit, the text is divided into chunks based on the number of characters. Each chunk will have a specified length in terms of characters.
  • Token: Refers to token-based chunking. If you choose this option as the chunk unit, the text is divided into chunks based on linguistic tokens. This option supports only GPT-3.5 Turbo and GPT-4 models.

Default value: Char

Example: Token
Chunk size Integer/Expression

Required. Specify the maximum number of tokens each chunk must have. Chunk size is the total size of each chunk (if a header is specified, that contributes to the chunk size).

Default value: 1000

Example: 100
Chunk overlap Integer/Expression

Required. Specify the number of tokens that can overlap between consecutive chunks.

Default value: 0

Example: 1
Chunk header configuration Use this to define chunk header properties.
Header type Dropdown list/Expression
Specify the chunk header type. Available options include:
  • None
  • User-defined header
  • First characters of content

Default value: None

Example: User-defined header
Header length Integer/Expression

Appears when you select First characters of content in the Header type field.

Specify the number of characters in the beginning of the content to be added to the beginning of every chunk of the output.

Default value: N/A

Example: 10
Header content String/Expression

Appears when you select User-defined header in the Header type field.

Specify the user-defined chunk header to be added to the beginning of every chunk of the output.

Default value: N/A

Example: Long header
Snap execution Dropdown list
Select one of the three modes in which the Snap executes. Available options are:
  • Validate & Execute. Performs limited execution of the Snap and generates a data preview during pipeline validation. Subsequently, performs full execution of the Snap (unlimited records) during pipeline runtime.
  • Execute only. Performs full execution of the Snap during pipeline execution without generating preview data.
  • Disabled. Disables the Snap and all Snaps that are downstream from it.

Default value: Validate & Execute

Example: Execute only

Examples