Skip to content

Summarization

Summarize a text using a LLM

Sends the input text to a language model with instructions to summarize it concisely while preserving the key points. You can optionally cap the approximate length and set a style (e.g. “bullet points”, “one paragraph”, “formal”).

Use this node to condense long text — articles, transcripts, documents, chat threads — into a shorter summary for display, storage, or as compact context for a downstream agent.

SettingNotes
TextThe text to summarize. Rendered as a text area.
Options → Max wordsThe approximate maximum number of words the summary should contain.
Options → StyleThe style of the summary, e.g. “bullet points”, “one paragraph”, “formal”.
Options → System messageOptional additional system message appended to the summarization instructions. Rendered as a text area.

Returns { summary }, the model’s generated summary of the input text.

  • Model (required) — connect a language model dependency (e.g. Chat OpenAI). Used to generate the summary.

Connect a Chat OpenAI node to the Model dependency, feed long text from an upstream node (e.g. a scraped page or transcript) into Text, optionally set Max words and Style, then pass the summary output to a display node or as context for another agent.

  • If summaries run longer than expected, set Max words explicitly — it is an approximate instruction to the model, not a hard truncation.
  • Verify the Model dependency is connected — the node throws if no model is found.
  • For very long input text, check the connected model’s context window; excessively long text may need to be chunked upstream.