> ## Documentation Index
> Fetch the complete documentation index at: https://docs.unstructured.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Transform nodes

> Configure Transform nodes to extract content from raw files and split it into optimally sized elements, using a Partitioner to detect document structure and a Chunker to prepare elements for downstream processing.

## 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](/concepts/partitioning).

| Node                                                                     | Description                                                                      |
| ------------------------------------------------------------------------ | -------------------------------------------------------------------------------- |
| [Auto](/api-reference/workflow/nodes/transform/partitioner-auto)         | Routes each page to the optimal strategy at runtime, balancing quality and cost. |
| [VLM](/api-reference/workflow/nodes/transform/partitioner-vlm)           | Delivers highest-quality results for PDFs, images, and scanned documents.        |
| [High Res](/api-reference/workflow/nodes/transform/partitioner-high-res) | Processes all supported file types with advanced image-to-text extraction.       |
| [Fast](/api-reference/workflow/nodes/transform/partitioner-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](/api-reference/workflow/sources/) node.
* There can only be one partitioning node per workflow.

## Chunker

[Learn about the available chunking strategies](/concepts/chunking).

| Node                                                                                       | Description                                                                                        |
| ------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------- |
| [Chunk by Character](/api-reference/workflow/nodes/transform/chunker-chunk-by-character)   | Combines elements within hard and soft character limits, without using section or page boundaries. |
| [Chunk by Title](/api-reference/workflow/nodes/transform/chunker-chunk-by-title)           | Preserves section boundaries by starting a new chunk at each Title element.                        |
| [Chunk by Page](/api-reference/workflow/nodes/transform/chunker-chunk-by-page)             | Preserves page boundaries, ensuring no chunk spans more than one page.                             |
| [Chunk by Similarity](/api-reference/workflow/nodes/transform/chunker-chunk-by-similarity) | Groups topically similar consecutive elements into chunks using an embedding model.                |

### Workflow placement

* Always place Chunker nodes after a [Partitioner](#partitioner) node.

* Chunker nodes are usually placed after any [Enrichment](/api-reference/workflow/nodes/enhancement/enhancement#prompter) nodes present in the workflow.

  An exception is the [Named Entity Recognition (NER) enrichment node](/api-reference/workflow/nodes/enhancement/prompter-named-entity-recognition-ner), which should be placed *after* any Chunker nodes.

* For post-chunk enrichment nodes such as [Contextual chunking](/api-reference/workflow/nodes/enhancement/chunker-chunk-by-contextual) and [Chunk by Table Merging](/api-reference/workflow/nodes/enhancement/chunker-chunk-by-table-merging), see [Enrich](/api-reference/workflow/nodes/enhancement/enhancement#chunker).