> For the complete documentation index, see [llms.txt](https://help.jurisphere.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.jurisphere.ai/file-upload-and-management/your-files-and-documents/ocr.md).

# OCR

If you have scanned or image-based PDFs, you can OCR the file on Jurisphere to make the text searchable and usable for AI-powered tools like [Document Review](/document-review/overview-of-the-document-review-tool.md) and [Translation](/translation/overview-of-the-translation-tool.md).

<mark style="color:blue;">**OCR is automatically applied to all files when they are being uploaded and processed**</mark>. However, in some cases, you may be required to manually apply OCR again.

{% hint style="info" %}
You can check whether a document is OCR'ed, by simply opening the document in the left pane, and selecting the text within the document. If you are able to select all the text in the document, then your <mark style="color:green;">**document is machine readable**</mark>.
{% endhint %}

Additionally, you can also manually **Apply OCR** to files. Follow these steps:

1. In the [file options](/file-upload-and-management/your-files-and-documents/file-options.md) menu, select **Apply OCR and Re-Process**.
2. Confirm your action in the popup box that appears.

{% hint style="info" %}
The OCR process takes time. Check the notification drawer for updates, and feel free to use other files and features while you wait.
{% endhint %}

### When is manual OCR needed?

* **Encrypted or protected PDFs**: If your document contains pages without selectable text with either a image-over-text layer or any other anomaly, manual OCR is necessary to make it searchable and usable for AI.
* **Low-quality scans**: Files with unclear text, skewed pages, or handwritten annotations may require a manual OCR pass to improve text recognition.
* **Documents uploaded without auto-OCR**: If the files due to incorrect indexing skipped Jurisphere's automatic OCR during file upload, you can manually apply OCR and reprocess them.
* **Language detection issues**: In rare cases where a document has mixed languages or unusual formatting, manual OCR ensures correct text extraction.

***

### Why is manual OCR important?

{% hint style="danger" %}
Without OCR, AI tools cannot "read" your file — they treat it as an image, and search, translation, extraction, and analysis won’t work.
{% endhint %}

. By manually applying OCR:

* [x] The document becomes fully searchable.
* [x] Jurisphere can extract dates, parties, and key legal terms.
* [x] You can generate Lists of Dates, run Redline comparisons, and translate the text.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://help.jurisphere.ai/file-upload-and-management/your-files-and-documents/ocr.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.