Summarization
Summarization
Section titled “Summarization”Summarize a text using a LLM
What it does
Section titled “What it does”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”).
When to use it
Section titled “When to use it”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.
Inputs and settings
Section titled “Inputs and settings”| Setting | Notes |
|---|---|
| Text | The text to summarize. Rendered as a text area. |
| Options → Max words | The approximate maximum number of words the summary should contain. |
| Options → Style | The style of the summary, e.g. “bullet points”, “one paragraph”, “formal”. |
| Options → System message | Optional additional system message appended to the summarization instructions. Rendered as a text area. |
Outputs
Section titled “Outputs”Returns { summary }, the model’s generated summary of the input text.
Dependencies and credentials
Section titled “Dependencies and credentials”- Model (required) — connect a language model dependency (e.g. Chat OpenAI). Used to generate the summary.
Example workflow
Section titled “Example workflow”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.
Troubleshooting
Section titled “Troubleshooting”- 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.