> ## Documentation Index
> Fetch the complete documentation index at: https://unstructured-53-docs-245-multimodal.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Generative OCR optimization

After partitioning, you can have a vision language model (VLM) optimize the fidelity of text blocks that Unstructured
initially processed during its partitioning phase.

Here are a few examples of Unstructured's output of text blocks that were initially processed, and the more accurate
version of these text blocks that were optimized by using Claude Sonnet 4. Irrelevant lines of output have been omitted here for brevity.

Example 1: Vertical watermarked text

<img src="https://mintcdn.com/unstructured-53-docs-245-multimodal/4ajZsC8pNRoLboLt/img/ui/enriching/generative-ocr-watermark.png?fit=max&auto=format&n=4ajZsC8pNRoLboLt&q=85&s=11b78b9997a659eef3fa188a0975731d" alt="Vertical watermarked text example" width="143" height="626" data-path="img/ui/enriching/generative-ocr-watermark.png" />

Before (vertical watermarked text, represented incorrectly):

```json theme={null}
{
    "...": "...",
    "text": "3 2 0 2 t c O 9 2 ] V C . s c [ 2 v 9 0 8 6 1 . 0 1 3 2 : v i X r",
    "...": "..."
}
```

After (vertical watermarked text, now represented correctly from the original content):

```json theme={null}
{
    "...": "...",
    "text": "arXiv:2310.16809v2 [cs.CV] 29 Oct 2023",
    "...": "..."
}
```

Example 2: Hyperlink

<img src="https://mintcdn.com/unstructured-53-docs-245-multimodal/4ajZsC8pNRoLboLt/img/ui/enriching/generative-ocr-hyperlink.png?fit=max&auto=format&n=4ajZsC8pNRoLboLt&q=85&s=46d0bde46994d60f5825b6c66242368f" alt="Hyperlinked text example" width="507" height="188" data-path="img/ui/enriching/generative-ocr-hyperlink.png" />

Before (hyperlink, represented incorrectly):

```json theme={null}
{
    "...": "...",
    "text": "con/Yuliang-Liu/MultinodalOCR|",
    "...": "..."
}
```

After (hyperlink, now represented correctly from the original content):

```json theme={null}
{
    "...": "...",
    "text": "https://github.com/Yuliang-Liu/MultimodalOCR",
    "...": "..."
}
```

Example 3: Chinese characters

<img src="https://mintcdn.com/unstructured-53-docs-245-multimodal/4ajZsC8pNRoLboLt/img/ui/enriching/generative-ocr-image.png?fit=max&auto=format&n=4ajZsC8pNRoLboLt&q=85&s=af528b59c87161d122bdc6a17e566512" alt="Chinese characters example" width="269" height="200" data-path="img/ui/enriching/generative-ocr-image.png" />

Before (Chinese characters, represented incorrectly):

```json theme={null}
{
    "...": "...",
    "text": "GT SHE GPT4-V: EHES",
    "...": "..."
}
```

After (Chinese characters, now represented correctly from the original content, expressed as Unicode):

```json theme={null}
{
    "...": "...",
    "text": "GT : \u91d1\u724c\u70e7\u814a GPT4-V: \u6587\u9759\u5019\u9e1f",
    "...": "..."
}
```

## Improve text fidelity with generative OCR

To produce generative OCR optimizations, in an **Enrichment** node in a workflow, click the following
in the node's settings pane's **Details** tab:

* **Image** under **Input Type**.

* One of the following providers and models:

  * **Anthropic** under **Provider** and any choice under **Model**
  * **OpenAI** under **Provider** and any choice under **Model**

* **Generative OCR** under **Task**.

<Warning>
  Generative OCR does not process any text blocks by default. You must also explicitly specify which document element
  types containing text that you want generative OCR to process. To do this, in the workflow editor for your workflow:

  1. Click the **Partitioner** node.
  2. In the node's settings pane, scroll down to and then click a blank area inside of the **Extract Image Block Types** list.
  3. Select each [document element types](/ui/document-elements#element-type) that you want generative OCR to process. For this
     walkthrough, select only **NarrativeText**.

  Generative OCR does not process the text of any `Image` or `Table` elements if they have already been processed by
  [image description](#image-description-task) or [table description](#table-description-task) enrichments, respectively. Do
  not remove the **Image** or **Table** document elements types from this **Extract Image Block Types** list, or else
  the image description and table description enrichments in your workflow might produce unexepcted results or might not work at all.
</Warning>

<Note>
  The **Generative OCR** enrichment appears under the **Input Type** of **Image**, even though this is not an image-related enrichment.
  This is a known issue and will be addressed in a future release.
</Note>

<Note>
  You can change a workflow's image description settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.

  For workflows that use [chunking](/ui/chunking), the **Chunker** node should be placed after all **Enrichment** nodes. Placing the
  **Chunker** node before an image descriptions **Enrichment** node could cause incomplete or no image descriptions to be generated.
</Note>

<Warning>
  Unstructured can produce generative OCR optimizations for workflows that are configured as follows:

  * With a **Partitioner** node set to use the **Auto** or **High Res** partitioning strategy, and a generative OCR optimizations node is added.
  * With a **Partitioner** node set to use the **VLM** partitioning strategy. No generative OCR optimization node is needed (or allowed).

  Unstructured never produces generative OCR optimizations for workflows with a **Partitioner** node set to use the **Fast** partitioning strategy.
</Warning>