Tools
Run a single pipeline step on demand. Tool requests authenticate with a Bearer token and do not need a workspace.Convert
Normalize a source document into clean text.
Split
Break converted text into smaller chunks.
Shape
Infer the schema of your data.
Extract
Pull specific fields and values out of the text.
Pipeline
Run a full ingestion
Chain
convert → split → shape → extract into one managed job and load the result into a workspace.Query your data
Run natural-language queries over the data you have ingested into a workspace.