> For the complete documentation index, see [llms.txt](https://docs.nested-knowledge.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nested-knowledge.com/review-workflow/screening/full-text-import.md).

# Full Text Import

Learn how to import full texts in bulk.

**Full Text Import** adds PDFs to many records at once. Use it before Full Text Screening to prepare a batch, rather than uploading PDFs record by record in Screening.

### Open Access And Proprietary Full Texts

For open access records, Nested Knowledge retrieves PDFs through unpaywall.org. It matches each PDF by title, DOI, and authors. If a journal CAPTCHA blocks retrieval, download and upload the PDF manually.

For proprietary or paywalled records, upload PDFs yourself. Nested Knowledge matches them using the same fields. PDFs without a close match remain unmatched. You'll receive an email listing them. Re-upload those files using **Ref ID** or **External ID** matching.

<figure><img src="https://305208404-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fxb7uNGATUgwQAjDVQRXG%2Fuploads%2FJKluCKEJhfwCHjBG4av9%2Ffull%20text%20import.png?alt=media&amp;token=c7252b55-94fb-40e8-84c1-87541b7345e8" alt="Full Text Import page with automatic import and PDF upload options"><figcaption><p>Use **Full Text Import** to retrieve open access PDFs or upload proprietary PDFs.</p></figcaption></figure>

Full Text Import automatically filters to **Advanced** or **Included** studies, so you're only importing full texts for records at that stage. If you want to bulk import full texts outside that filter, use **Bulk Document Import** on the Bulk Actions page instead — it supports the same open-access and proprietary, automatic and manual upload options, without the Advanced/Included restriction.

### Bulk Import Full Texts

{% stepper %}
{% step %}

#### Open Full Text Import

In the navigation menu, select **Full Text Import**.
{% endstep %}

{% step %}

<figure><img src="https://305208404-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fxb7uNGATUgwQAjDVQRXG%2Fuploads%2FMqg0GSZqVGVXmCVh2xH1%2FScreenshot%202026-08-21%20at%2015.45.51.png?alt=media&amp;token=1acedd0f-0613-441e-a8e9-f774d498f087" alt="Full Text Import page showing Open access from unpaywall.org and ClinicalTrials.gov import options"><figcaption><p>Select **Import** to retrieve open access PDFs or ClinicalTrials.gov reports.</p></figcaption></figure>

#### Run Automatic Import

#### Open Access

Import open access full texts first. Under **Open access from unpaywall.org**, select **Import**. Nested Knowledge imports and matches PDFs for your Advanced or Included records. Use the progress tabs to check totals. Select **Inspector** to view the records.

#### ClinicalTrials.gov

If you searched ClinicalTrials.gov, select **Import**. This generates and attaches reports and trial data as PDFs.
{% endstep %}

{% step %}

#### Download Proprietary Record List

Download records without an automatically retrieved PDF to source their full texts elsewhere. Select **Advanced/Included (n)** to download a spreadsheet.
{% endstep %}

{% step %}

#### Upload Proprietary PDFs

After you download the PDFs, select **Import**. Choose auto-extracted bibliographic data, **Ref ID**, or **External ID** matching. Nested Knowledge returns unmatched files to you.
{% endstep %}
{% endstepper %}

### Limits

The open access import accepts up to 500 Advanced or Included studies at a time. For larger batches, or records in other statuses, use [Bulk Actions in Study Inspector](/review-workflow/study-inspector/bulk-actions.md).

### FAQs

<details>

<summary>Why weren't all open access PDFs retrieved and matched?</summary>

This can happen when a journal CAPTCHA blocks unpaywall.org from retrieving a PDF.

Choose one of these options:

* Upload individual PDFs from the record's **Full Text** tab.

<figure><img src="https://305208404-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fxb7uNGATUgwQAjDVQRXG%2Fuploads%2FJALBUcKze26gNAtOzFQw%2Ffailed%20full%20text%20import.png?alt=media&amp;token=1883c153-0d67-4d4c-9506-3b9ff147f71f" alt="Full Text tab showing the option to upload a PDF"><figcaption><p>Upload a PDF from an individual record's **Full Text** tab.</p></figcaption></figure>

* In **Study Inspector**, filter for **Open Access Full Text** and **Full Text Status: No Full Text**. Upload PDFs individually, or select **Download** to source several PDFs externally. Then upload them through [**Bulk Actions**](/review-workflow/study-inspector/bulk-actions.md).

<figure><img src="https://305208404-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fxb7uNGATUgwQAjDVQRXG%2Fuploads%2Fxa3cIDJ2l4QktF1M0dzf%2Fview%20failed%20open%20access.png?alt=media&amp;token=f613652d-0c6b-4af6-b95b-5ed5911e6122" alt="Study Inspector filters for open access records without full text"><figcaption><p>Filter for open access records without full text in **Study Inspector**.</p></figcaption></figure>

</details>

<details>

<summary>Why did some of my proprietary PDFs fail to match their records?</summary>

Usually, the auto-extracted title, DOI, or authors don't match the record closely enough. You'll receive an email listing unmatched files. Re-upload them using **Ref ID** or **External ID** matching instead.

</details>

### Next Steps

<table data-card-size="large" data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><i class="fa-file-lines">:file-lines:</i><br><strong>Screen Records</strong></td><td>Review records during Full Text Screening.</td><td><a href="/review-workflow/screening/screen-records.md">Screen Records</a></td></tr><tr><td><i class="fa-scale-balanced">:scale-balanced:</i><br><strong>Adjudicate Records</strong></td><td>Resolve disagreements in Dual Screening.</td><td><a href="/review-workflow/screening/adjudicate-records.md">Adjudicate Records</a></td></tr><tr><td><i class="fa-tags">:tags:</i><br><strong>Tagging</strong></td><td>Capture data from included records.</td><td><a href="/review-workflow/tagging.md">Tagging</a></td></tr></tbody></table>


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.nested-knowledge.com/review-workflow/screening/full-text-import.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.