Transform nodes - Unstructured

Partitioner

Unstructured recommends that you choose the Auto partitioning strategy in most cases. With Auto, Unstructured does all the heavy lifting, optimizing at runtime for the highest quality at the lowest cost page-by-page. For a detailed discussion of the various partitioning strategies, see Partitioning.

Node	Description
Auto	Routes each page to the optimal strategy at runtime, balancing quality and cost.
VLM	Delivers highest-quality results for PDFs, images, and scanned documents.
High Res	Processes all supported file types with advanced image-to-text extraction.
Fast	Extracts text from text-only documents at the highest speed and lowest cost.

Workflow placement

A partitioning node must be the first processing node in the workflow, immediately following the source node.
There can only be one partitioning node per workflow.

Chunker

Learn about the available chunking strategies.

Node	Description
Chunk by Character	Combines elements within hard and soft character limits, without using section or page boundaries.
Chunk by Title	Preserves section boundaries by starting a new chunk at each Title element.
Chunk by Page	Preserves page boundaries, ensuring no chunk spans more than one page.
Chunk by Similarity	Groups topically similar consecutive elements into chunks using an embedding model.

Workflow placement

Always place Chunker nodes after a Partitioner node.
Chunker nodes are usually placed after any Enrichment nodes present in the workflow. An exception is the Named Entity Recognition (NER) enrichment node, which should be placed after any Chunker nodes.
For post-chunk enrichment nodes such as Contextual chunking and Chunk by Table Merging, see Enrich.

Custom workflow DAG Auto partition

​Partitioner

​Workflow placement

​Chunker

​Workflow placement

Partitioner

Workflow placement

Chunker

Workflow placement