Resume

Summarizes a long text using a language model. Preserves key points while significantly reducing the length.

Parameters

Parameter	Type	Required	Variable	Description
input	dynamic value	Yes	Yes	Text to summarize. Accepts a variable or free text.
maxLength	number	No	No	Maximum length of the summary in characters. (min 1)
style	choice (bullet, paragraph, key_points, abstract, llm_optimized)	No	No	Summary style: bullet points, paragraph, key points, abstract, or LLM-optimized. (Default: "paragraph")
language	text	No	No	Summary language (ISO 639-1 code, e.g. fr, en). 'auto' for automatic detection.
customInstructions	text	No	Yes	Custom instructions for the LLM when generating the summary.
includeEntities	boolean	No	No	Include extracted entities in the summary output. (Default: false)
model.provider	text	No	No	Language model provider (e.g. openai, anthropic).
model.model	text	No	No	Model identifier to use (e.g. gpt-4o-mini).
parameters.temperature	number	No	No	Model creativity. 0 = deterministic, 1 = more creative. (Default: 0.7, min 0, max 2)
parameters.maxTokens	number	No	No	Maximum number of tokens in the generated response. (Default: 2048, min 1, max 128000)
outputVariable	text	No	No	Output variable name containing the generated summary.

Parameters marked Variable = Yes accept the {{blockName.field}} syntax.

Output

Output variable : summary

{
  "content": "..."
}

Example

Summarize a 10-page report.

Input :

{"text": "Le rapport annuel 2025 presente les resultats financiers..."}

Output :

{"content": "Resume : Les resultats 2025 montrent une croissance de 12%..."}

Tip

{{summary.content}} contains the summary. Adjust maxTokens in model settings to control the summary length.