Message Part Extractor

This node extracts specific parts from messages in a table, allowing you to work with content types such as text, images, roles, names, and tool calls. The input table is processed row by row, extracting the specified parts from each message.

Extracted parts:

Role: Extracts the role of the message, such as User, AI, or Tool.
Name: Extracts the name associated with the message.
Text Content: Extracts text content from the message.
Image Content: Extracts image content from the message.
Tool Calls: Extracts tool calls, including tool names, IDs, and arguments.
Tool Call ID: Extracts the ID of the tool call associated with the message.

Options

Message column: The column containing messages to extract parts from.
Keep message column: Whether to keep the original message column in the output table.
Role column name: If enabled, a new column with the role will be added under the specified name.
Name column name: If enabled, a new column with the name will be added under the specified name.
Text parts column prefix: Prefix for the output columns for extracted text parts. There will be as many columns as there are text contents in a message, named 'prefix 1', 'prefix 2', etc.
Image parts column prefix: Prefix for the output columns for extracted image parts. There will be as many columns as there are image contents in a message, named 'prefix 1', 'prefix 2', etc.
Tool calls column prefix: Prefix for the output columns for extracted tool calls. There will be as many columns as there are tool calls in a message, named 'prefix 1', 'prefix 2', etc.
Tool call ID column name: Name of the output column for extracted tool call IDs.

Input Ports

: Table containing messages to extract parts from.

Output Ports

: Table with extracted message parts.

Popular Predecessors

No recommendations found

Popular Successors

No recommendations found

Views

This node has no views

Workflows

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.

Installation

To use this node in KNIME, install the extension KNIME AI Extension from the below update site following our NodePit Product and Node Installation Guide:

v5.9

A zipped version of the software site can be downloaded here.

Plugin provider: KNIME AG, Zurich, Switzerland

Plugin version: 5.9.0.v202512011244

On NodePit since: 2025-12-11

Last update: 2026-01-05

Tags: StreamableModern UI

KNIME versions: Since v5.5

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!