> 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/literature-search/add-search/import-search-files.md). # Import Search Files Import records from database searches that run outside Nested Knowledge. **Import Search Files** adds records from databases that **Automatic Search** can't search directly. Use it for RIS or NBIB exports, or spreadsheets of DOIs or PubMed IDs. Imports don't update automatically. To add new results, rerun the source search and upload a new file as a new search. See Automatic Search available databases. ### Generate A File To Import Use RIS or NBIB files when available. Export every record in the search, not only the current page or a selected subset. * Embase: Export in RIS format using the Citation field. * Scopus: Keep the default citation format and export in RIS format. * PubMed: Export in NBIB format.

Get an NBIB file from PubMed

1. Run your search on [**PubMed**](https://pubmed.ncbi.nlm.nih.gov/). 2. In the **Send To** menu, select **Citation Manager**. 3. Select the records to export. 4. Select all results to export the full search. 5. Select **Create file**. 6. Save the downloaded file.

For other databases, export the option labeled for reference managers or its closest equivalent. This is usually RIS. {% hint style="info" %} A file with a **.txt** extension is also accepted: Nested Knowledge inspects its contents and infers whether it's structured as RIS or NBIB automatically, so you don't need to rename or convert it before uploading. {% endhint %} ### Import Your Search File {% stepper %} {% step %} #### Go To Literature Search In the navigation menu, select **Literature Search**.

The Literature Search option in the navigation menu.

{% endstep %} {% step %} #### Start A Search Select **Add Search**. Any earlier searches are listed below.

The Add Search button on Literature Search.

{% endstep %} {% step %} #### Select Import Search File Select **Import Search File**. {% endstep %} {% step %} #### Upload Your Search File Upload the search file from your computer. {% endstep %} {% step %} #### Select A Search Engine From **Search Engine**, select the matching source. If it isn't listed, select **Other** and enter its name. This is what is displayed on the PRISMA. {% endstep %} {% step %} #### Enter A Query Or Title For an index search, enter the exact query you ran. For a hand-compiled bibliography, enter a title instead. {% endstep %} {% step %} #### Add The Search Select **Add** to import the search file. {% endstep %} {% endstepper %} {% hint style="info" %} Record the query, search engine, and notes to preserve search history and support PRISMA reporting. {% endhint %} ### Import A Spreadsheet Of Studies Use a spreadsheet for records from another project or citation manager. Include a DOI column, a PubMed ID column, or both. * With only DOI or PubMed ID columns, Nested Knowledge looks up bibliographic data from PubMed and CrossRef. Fields can remain empty when the source doesn't provide them. * With additional columns, Nested Knowledge imports the data you enter. Supported headings include Title, Year, First Author, Authors, Publication Type, and PT. Name each additional column after its bibliographic field. Use one row for each record. A template is available from the **File Import** modal when you upload a spreadsheet. ### Update Or Delete A Search File Import doesn't refresh automatically. To add new results, rerun the source search, export the results, and upload them as a new search. Duplicates are automatically identified and removed so re-uploading existing studies doesn't create duplicates in your nest. {% hint style="danger" %} Deleting a search removes its records and their screening, tagging, and extraction data. You can't undo this action. Records from another search remain in the nest. {% endhint %} ### Choosing Between RIS Import And Embase Integration Use an RIS import for occasional Embase searches. For recurring Embase searches, set up the Embase Integration. ### FAQs

Why are my studies failing to load?

File formatting may be the cause. Nested Knowledge infers RIS/NBIB structure automatically, including from a `.txt` file, but if your file doesn't match either format closely enough, correct it and upload it again. Comparing its layout against a correctly formatted RIS file can help spot the difference. You can also contact [Nested Knowledge support](mailto:support@nested-knowledge.com).

How are duplicates handled?

Nested Knowledge identifies duplicate records within and between searches. See **Duplicate Review**.

Can I combine multiple databases in one file and upload that?

Each import records one query, search engine, and date. A combined file doesn't show which records came from each database. To preserve this information for PRISMA reporting, upload each database separately.

What is the import size limit?

Searches and import files share the same limit: 10,000 records per search.

Can I import screening decisions next?

Yes. If you screened these studies in another tool, use Import Screening Decisions to bring those decisions into your nest.

### Next Steps


Automatic Search	Run and schedule searches in supported databases.	Automatic Search
Smart Search	Generate PubMed queries from your research question.	Smart Search
Other Sources	Add records from gray literature and other sources.	Other Sources
Duplicate Review	Review records that may match records already in your nest.	Duplicate Review
Screening	Screen the records you imported and searched.	Screening

--- # 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/literature-search/add-search/import-search-files.md?ask=&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.