> ## 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. # Enhancement nodes > Configure Enhancement nodes to apply AI-powered transformations to partitioned document elements, including enrichments, structured data extraction, and vector embeddings. ## Chunker These chunker nodes apply AI-powered enhancements to existing chunks rather than splitting content by character or structure. | Node | Description | | -------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | | [Contextual chunking](/api-reference/workflow/nodes/enhancement/chunker-chunk-by-contextual) | Prepends LLM-generated context summaries to each chunk, improving retrieval quality for ambiguous content. | | [Chunk by Table Merging](/api-reference/workflow/nodes/enhancement/chunker-chunk-by-table-merging) | Detects and merges tables that span adjacent pages into a single coherent element using LLM assistance. | ### Workflow placement * Place the [Contextual chunking](/api-reference/workflow/nodes/enhancement/chunker-chunk-by-contextual) node after one of the standard text chunkers (such as `chunk_by_character`, `chunk_by_page`, `chunk_by_similarity`, or `chunk_by_title`), as it enriches existing chunks rather than creating them. * The [Chunk by Table Merging](/api-reference/workflow/nodes/enhancement/chunker-chunk-by-table-merging) node pairs well with a [Table to HTML](/api-reference/workflow/nodes/enhancement/prompter-table-to-html) enrichment earlier in the workflow. ## Embedder Configure an [Embedder](/api-reference/workflow/nodes/enhancement/embedder) node to convert chunked document elements into vector embeddings for similarity search in vector stores. ## Extract [Learn about the available extraction methods](/concepts/structured-data-extractor/data-extractor). | Node | Description | | ---------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------- | | [LLM](/api-reference/workflow/nodes/enhancement/extract-llm) | Extracts structured data using a language model with a JSON schema or plain-language guidance. | | [Regex](/api-reference/workflow/nodes/enhancement/extract-regex) | Extracts structured data using named regular-expression patterns, without requiring a language model. | ## Prompter Unstructured can potentially generate image summary descriptions, table summary descriptions, table-to-HTML output, and generative OCR optimizations, only for workflows that are configured as follows: * With a **Partitioner** node set to use the **Auto** or **High Res** partitioning strategy, and an image summary description node, table summary description node, table-to-HTML output node, or generative OCR optimization node is added. * With a **Partitioner** node set to use the **VLM** partitioning strategy. No image summary description node, table summary description node, table-to-HTML output node, or generative OCR optimization node is needed (or allowed). Even with these configurations, Unstructured actually generates image summary descriptions, table summary descriptions, and table-to-HTML output only for files that contain images or tables and are also eligible for processing with the following partitioning strategies: * **High Res**, when the workflow's **Partitioner** node is set to use **Auto** or **High Res**. * **VLM** or **High Res**, when the workflow's **Partitioner** node is set to use **VLM**. Unstructured never generates image summary descriptions, table summary descriptions, or table-to-HTML output for workflows that are configured as follows: * With a **Partitioner** node set to use the **Fast** partitioning strategy. * With a **Partitioner** node set to use the **Auto**, **High Res**, or **VLM** partitioning strategy, for all files that Unstructured encounters that do not contain images or tables. Unstructured never produces generative OCR optimizations for workflows with a **Partitioner** node set to use the **Fast** partitioning strategy. [Learn about the available enrichments](/concepts/enriching/overview). | Node | Description | | ----------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- | | [Image Description](/api-reference/workflow/nodes/enhancement/prompter-image-description) | Generates text summaries of detected images using a VLM. | | [Table Description](/api-reference/workflow/nodes/enhancement/prompter-table-description) | Generates text summaries of detected tables using a VLM. | | [Table to HTML](/api-reference/workflow/nodes/enhancement/prompter-table-to-html) | Converts detected tables to HTML markup using agentic AI or a VLM. | | [Named Entity Recognition (NER)](/api-reference/workflow/nodes/enhancement/prompter-named-entity-recognition-ner) | Identifies entities, their types, and relationships within text. | | [Generative OCR](/api-reference/workflow/nodes/enhancement/prompter-generative-ocr) | Improves the fidelity of initially partitioned text blocks using a VLM. | ### Workflow placement * Always place enrichment nodes after a [Partitioner](/api-reference/workflow/nodes/transform/transform#partitioner) node. * Place enrichment nodes before [Chunker](/api-reference/workflow/nodes/transform/transform#chunker) nodes, unless otherwise noted. * For example, a [`table2html` enrichment](/api-reference/workflow/nodes/enhancement/prompter-table-to-html) is often paired with a [`chunk_by_table_merging`](/api-reference/workflow/nodes/enhancement/chunker-chunk-by-table-merging) node later in the workflow. * An exception is the [NER enrichment](/api-reference/workflow/nodes/enhancement/prompter-named-entity-recognition-ner), which should be placed *after* any [Chunker](/api-reference/workflow/nodes/transform/transform#chunker) nodes. * Always place any [image description enrichment](/api-reference/workflow/nodes/enhancement/prompter-image-description) after any [OCR enrichment](/api-reference/workflow/nodes/enhancement/prompter-generative-ocr), if present, so that it overwrites the results from the OCR enrichment.