New Snap template

This Snap reads/fetches/writes/parses/executes/transforms/calls/creates ....

Supported Accounts

  • This is a Read-type Snap.

S3 Browser Snap dialog

Prerequisites

None.

Limitations

Known issues

None.

Snap views

Type 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 input to be used as the prompt. When you select the Binary input view, the Prompt field is hidden.
  • Document Input type: You must provide a field to specify the path to the input prompt. The Snap requires a prompt, which can be generated either by the Amazon Bedrock Prompt Generator Snap or any user-desired prompt intended for submission to the Amazon Bedrock Converse API.
Output This Snap has at the most one document output view. The Snap provides the result generated by the Amazon Bedrock Converse API.
Learn more about Error handling.

Examples

  1. Providing User-defined Object Metadata and Object Tags using the S3 File Writer Snap: This example demonstrates how to provide user-defined metadata.
  2. S3 File Writer - Typical Snap Configuration: This example demonstrates how to configure an S3 File Writer Snap.

Snap settings

Note: Learn about the common controls in the Snap settings dialog.
Field/Field set 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: S3 File Writer

Example: Write CSV file to S3 staging bucket
Name

String/Expression

Required. Specify the tool name, and the model calls that specific tool with the same name.

Important: Following are the supported characters for the function name: lowercase (a-z), uppercase (A-Z), numbers (0-9), underscores (_), and dashes (-).
Minimum value: 1 character

Maximum value: 64 characters

Default value: N/A

Example: weather_tool
Description

String/Expression

A description of what the function does.

Default value: N/A

Example: weather_tool
Strict Mode

Checkbox

For OpenAI LLMs only Select this checkbox to ensure that the Snap validates the input parameters strictly according to the defined schema or constraints. When enabled, the model will follow the exact schema defined in the Parameters field.

Default status: Deselected

Note: The Snap supports only a subset of JSON Schema when this checkbox is selected. A list of unsupported JSON schema can be found. here. If the checkbox is selected, all fields must be required. Otherwise, OpenAI will respond with an error.
Input Mode

Dropdown list

The mode in which the function generator operates.

  • JSON Schema Mode
  • Express Mode

Default value: Express Mode

Example: Express Mode
Parameters

Appears when Express Mode is selected.

The parameters the function accepts.

Default value: Example:
JSON Schema

Button

Appears when JSON Schema Mode is selected.

The JSON Schema for the function definition. Click JSON Schema to open the JSON Editor

Default value: Default JSON Schema editor contents:


JSON Schema default contents
Tool path

String/Expression

The pipeline that will be executed when this tool is called.

Default value: N/A

Example: weather_tool_pipe

Snap execution

Dropdown list
Choose 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: Execute only

Example: Validate & Execute

Temporary files

During execution, data processing on Snaplex nodes occurs principally in-memory as streaming and is unencrypted. When processing larger datasets that exceed the available compute memory, the Snap writes unencrypted pipeline data to local storage to optimize the performance. These temporary files are deleted when the pipeline execution completes. You can configure the temporary data's location in the Global properties table of the Snaplex node properties, which can also help avoid pipeline errors because of the unavailability of space. Learn more about Temporary Folder in Configuration Options.

Troubleshooting

Error Reason Resolution
The following function (s) does not have a corresponding tool pipeline or the schema is invalid: get_weather _api Tool pipeline path is incorrect. Include a pipeline path for the function defined and ensure the tool type is valid.
The Agent is not complete but the execution is completed. The iteration limit is reached, but the finish reason is not a stop condition. Consider providing a greater iteration limit.
Duplicate tool names found: get_weather_api The duplicated tool names will be automatically renamed to avoid conflicts. Rename the tools.