Aggregate
🤖 AI Drafted (Not reviewed)
Combine upstream fan-out results into a single payload.
|
|
| Tool id |
aggregate |
| Category |
transform |
| Uses a language model |
no |
| Needs a generative model |
no |
| Runs over many items |
no |
| Item handling |
reducing |
| Structured output |
no |
| Human-verified |
not yet |
What it reads
| Port |
Type |
Required |
What it is |
Text (text) |
text |
no |
Text records from upstream (string or list). |
Documents (documents) |
json |
no |
Optional document metadata aligned with text records. |
What it emits
| Port |
Type |
Required |
What it is |
Text (text) |
text |
— |
Combined text payload. |
Records (records) |
array |
— |
Full structured record list. |
Count (count) |
number |
— |
Number of records aggregated. |
Options
| Option |
Type |
Default |
What it does |
mode |
string |
concat |
How to combine upstream records. concat = text with separator; list = keep as array; json_array = JSON-encoded array; group_by_document = dict keyed by doc id/name. One of: concat, list, json_array, group_by_document. |
pretty_json |
boolean |
yes |
Indent JSON output (mode=json_array / group_by_document). |
separator |
string |
— |
Separator used when mode=concat. |
The prompt it sends
This tool does not send a prompt — it does its work in code.