Collections

A collection is a searchable index. When a pipeline ingests documents, their content is split into passages, converted into semantic vectors, and stored in a collection — that’s what lets chat find relevant content by meaning rather than exact keywords.

Create a collection

1. Go to Collections and select Create Collection.
2. Enter a Collection Name — letters, numbers, and underscores only, and it must be unique. Examples: company_handbook, q3_reports.
3. Select Create Collection.

The new collection starts empty. Documents arrive by running a pipeline that targets it.

Best practices

• One collection per pipeline. Each ingestion run rebuilds its target collection from scratch, so if two pipelines share a collection, running one erases the other’s documents. Give every pipeline its own collection.
• Name by content, not by source. hr_policies will make more sense in six months than smb_share_2.
• Collections are workspace-wide. Everyone’s chat questions search every collection, and any signed-in user can manage them — treat creation and deletion as shared, coordinated actions.

Review a collection

Click a collection in the list to see its Details — ID, name, and created/updated timestamps. (The Analytics tab is a placeholder for upcoming metrics.)

The Last Updated column on the list page is a quick way to see when each index last changed.

Delete a collection

Open the collection and select Delete Collection. This permanently removes the index and all its ingested content — chat will no longer find those documents. The original files on your file share are never touched.

If a pipeline targeted the deleted collection, it will fail on its next run; delete or recreate the pipeline accordingly.