HumanSignal · caitlinwheeless · Oct 27, 2025 · Oct 27, 2025 · Oct 27, 2025
diff --git a/docs/netlify.toml b/docs/netlify.toml
@@ -58,6 +58,12 @@ to = "/plugins"
 status = 301
 force = true
 
+[[redirects]]
+from = "/tags/pdf-beta"
+to = "/tags/pdf"
+status = 301
+force = true
+
 [[redirects]]
 from = "/"
 to = "/guide"

diff --git a/docs/source/tags/pdf-beta.md b/docs/source/tags/pdf-beta.md
diff --git a/docs/source/tags/pdf.md b/docs/source/tags/pdf.md
@@ -6,34 +6,26 @@ meta_title: PDF tag for loading PDF documents
 meta_description: Label Studio PDF tag for loading PDF documents for machine learning and data science projects.
 ---
 
-The `Pdf` tag displays a PDF document in the labeling interface. Use this tag to perform document-level annotations, transcription, and summarization.
+The `Pdf` tag displays a PDF document in the labeling interface. You can use this tag to:
 
-Use with the following data types: PDF.
-
-{% insertmd includes/tags/pdf.md %}
-
-### Supported control tags
-
-The `<Pdf>` tag is intended for document-level classification tasks and does not support applying annotations to the actual content of the PDF. 
+- Perform document-level annotations such as classification, transcription, and summarization. 
+- Perform OCR validation on supported PDFs. <span class="badge"></span>
 
-For example, if you want to apply labels for OCR tasks, you will need to convert the PDF into images first. For more information, see [Multi-Page Document Annotation](/templates/multi-page-document-annotation). 
+Supports:
+* Zoom
+* Rotation
+* PDFs up to 100 pages
 
-You can use the following control tags:
-
-- [Choices](choices)
-- [DateTime](datetime)
-- [Number](number)
-- [Pairwise](pairwise)
-- [Rating](rating)
-- [Taxonomy](taxonomy)
-- [TextArea](textarea)
+Use with the following data types: PDF.
 
 !!! error Enterprise
     You can also use the PDF tag with [Prompts](https://docs.humansignal.com/guide/prompts_overview) to perform auto-labeling work such as PDF summarization, classification, information extraction, and document intelligence. 
 
-### Example
+{% insertmd includes/tags/pdf.md %}
+
+## Example: PDF classification
 
-Labeling configuration to label PDF documents:
+Labeling configuration apply document-level classification to PDF documents:
 
 ```html
 <View>
@@ -46,11 +38,72 @@ Labeling configuration to label PDF documents:
 </View>
 ```
 
-**Example Input data:**
+#### Example Input data:
+
+```json
+{
+  "pdf": "https://app.humansignal.com/static/samples/opossum-cuteness.pdf"
+}
+```
+
+## Example: OCR <span class="badge"></span>
+
+!!! error Enterprise
+    Label Studio Enterprise only. 
+
+    For Community and Starter Cloud users who want to apply labels for OCR tasks, you will need to convert the PDF into images first and then use a labeling configuration similar to the [Multi-Page Document Annotation](/templates/multi-page-document-annotation) template. 
+
+Labeling configuration for PDFs:
+
+```xml
+<View>
+  <OcrLabels name="ocr" toName="pdf">
+    <Label value="Typo"/>
+    <Label value="Incorrect amount"/>
+    <Label value="Incorrect name"/>
+  </OcrLabels>
+
+  <Pdf name="pdf" value="$pdf"/>
+</View>
+```
+
+#### Example Input data:
 
 ```json
 {
-  "pdf": "https://app.humansignal.com/static/samples/sample.pdf"
+  "pdf": "https://app.humansignal.com/static/samples/opossum-cuteness.pdf"
 }
 ```
+### OcrLabels 
+
+This tag adds bounding boxes to the PDF and allows you to assign labels to them. 
+
+
+This tag must have one or more `Label` tag children, and supports standard parameters such as `maxUsages` (see [RectangleLabels](rectanglelabels) as an example).
+
+#### Supported PDFs
+
+PDFs that work best with the new OCR labeling are those that already contain a selectable text layer (text overlay). 
+
+In these PDFs, when you draw a bounding box, the tool can read and highlight the underlying text from that layer (see the video below). 
+
+Image-only PDFs such as scans or phone photos without a text layer won’t return text. For those, you may need to use an external OCR tool to add a text layer first. If a PDF’s text layer is misaligned or low quality, captured text may be incomplete or incorrect, and this feature can help you audit and improve those overlays. 
+
+**Results:**
+
+| Result | Type | Description |
+| --- | --- | --- |
+| `x`, `y`, `width`, `height` | Number | Numbers from 0 to 1 that are relative to the page dimensions. | 
+| `rotation`| Number | Number in degrees clockwise from 0–360. Rotation is calculated with the origin at `(x, y)` (the top-left corner of the region). |
+| `pageIndex` | Number | Page number, 1-based. |
+| `ocrtext` | String | Captured text.  This can be edited by selecting the region and then editing the text from the **Info** panel. |
+
+!!! note
+    When you are rotating within the UI, it appears to originate from the center of the region. However, we store the origin as `(x, y)` - meaning in the top left corner of the region.
+
+<br/>
+<br/>
 
+<video style="max-width: 800px;" class="gif-border" autoplay loop muted>
+  <source src="/images/tags/pdf-ocr.mp4">
+</video>
diff --git a/docs/source/templates/multi-page-document-annotation.md b/docs/source/templates/multi-page-document-annotation.md
@@ -14,6 +14,9 @@ Multi-page document annotation allows you to annotate documents that consist of
 
 If you just need to classify a PDF document as a whole, you can also use the [PDF Classification template](pdf_classification).
 
+!!! error Enterprise
+    If you are performing OCR annotation and you are a Label Studio Enterprise users, see [OCR Labeling for PDFs](pdf_ocr).
+
 <a href="https://app.humansignal.com/b/MTk4"
   target="_blank" rel="noopener" aria-label="Open in Label Studio" style="all:unset;cursor:pointer;display:inline-flex;align-items:center;justify-content:center;border-radius:4px;border:1px solid rgb(109,135,241);padding:8px 12px;background:rgb(87 108 193);color:white;font-weight:500;font-family:sans-serif;gap:6px;transition:background 0.2s ease;" onmouseover="this.style.background='rgb(97 122 218)'" onmouseout="this.style.background='rgb(87 108 193)'">
   <svg style="width:20px;height:20px" viewBox="0 0 26 26" fill="none"><path fill="none" d="M3.5 4.5h19v18h-19z"/><path fill-rule="evenodd" clip-rule="evenodd" d="M25.7 7.503h-7.087V5.147H7.588V2.792h11.025V.436H25.7v7.067Zm-18.112 0H5.225v10.994H2.863V7.503H.5V.436h7.088v7.067Zm0 18.061v-7.067H.5v7.067h7.088ZM25.7 18.497v7.067h-7.088v-2.356H7.588v-2.355h11.025v-2.356H25.7Zm-2.363 0V7.503h-2.363v10.994h2.363Z" fill="white"/></svg>

diff --git a/docs/source/templates/pdf_ocr.md b/docs/source/templates/pdf_ocr.md
@@ -0,0 +1,74 @@
+---
+title: OCR Labeling for PDFs
+type: templates
+category: Computer Vision
+cat: computer-vision
+order: 126
+meta_title: PDF OCR Data Labeling Template
+meta_description: Template for correcting text in a PDF document.
+---
+
+Use this template to perform region-level OCR directly on native PDFs. 
+
+The `Pdf` tag renders multi-page documents (up to 100 pages) with zoom and rotation, while OcrLabels lets you draw bounding boxes, assign labels, and capture editable OCR text per region. 
+
+Each region stores normalized coordinates, rotation, and a page index, making outputs reliable for downstream extraction tasks. 
+
+Ideal for document intelligence, QA on OCR output, and structured data capture workflows. 
+
+!!! error Enterprise
+    This template can only be used with in Label Studio Enterprise.
+
+![Screenshot](/images/templates-misc/pdf-opossum.png)
+
+## Labeling Configuration
+
+```xml
+<View>
+  <Header value="Select text to correct" size="4"/>
+  <OcrLabels name="ocr" toName="pdf">
+    <Label value="Typo" />
+    <Label value="Incorrect Amount" />
+    <Label value="Incorrect Name" />
+  </OcrLabels>
+  <Pdf name="pdf" value="$pdf"/>
+</View>
+
+<!-- {
+  "data": {
+    "pdf": "/static/samples/opossum-cuteness.pdf"
+  }
+} -->
+```
+
+## About the labeling configuration
+
+* **`Pdf`**
+
+    This will display your PDF natively in Label Studio, allowing you to zoom in and rotate as needed. 
+
+    Support for PDFs up to 100 pages. 
+
+* **OcrLabels**
+
+  Used only with the `Pdf` tag, and allows you to draw bounding boxes around text. Note that the PDF must have a text overlay for this to work (for example, verify whether you can highlight text in the PDF using your cursor).
+
+  Select the text under the **Regions** panel to correct it. 
+
+  <img src="/images/templates-misc/ocrlabels.png" alt="" class="gif-border" style="max-width:400px" />
+
+
+
+## Input data
+
+```json
+{
+    "data": {
+      "pdf": "/static/samples/opossum-cuteness.pdf"
+    }
+}
+```
+
+## Related tags
+- [Header](/tags/header.html)
+- [Pdf](/tags/pdf.html)
diff --git a/docs/themes/v2/source/images/tags/pdf-ocr.mp4 b/docs/themes/v2/source/images/tags/pdf-ocr.mp4
diff --git a/docs/themes/v2/source/images/tags/pdf2-ocr.mp4 b/docs/themes/v2/source/images/tags/pdf2-ocr.mp4
diff --git a/docs/themes/v2/source/images/templates-misc/ocrlabels.png b/docs/themes/v2/source/images/templates-misc/ocrlabels.png
diff --git a/docs/themes/v2/source/images/templates-misc/pdf-opossum.png b/docs/themes/v2/source/images/templates-misc/pdf-opossum.png
diff --git a/label_studio/core/static/samples/opossum-cuteness.pdf b/label_studio/core/static/samples/opossum-cuteness.pdf