Document Loader

Important: Agents is currently in beta. For more information, see the Nintex Beta terms document.

A Document Loader lets you import documents into a Document Store so your agent can use them to answer questions.

When you add files such as PDFs, Word documents, FAQs, guides, policies, or product information, Nintex processes the content and splits it into smaller chunks. This helps the agent search the content and return accurate responses.

Each Document Loader defines:

The source of the document
How the content is processed and split
The settings used to prepare the content for use in the agent

Use Document Loaders to build and maintain the knowledge your agent relies on.

Jump to:

Access the Document Loader
Create a new Document Loader
Edit a Document Loader
Delete a Document Loader
Document Loader columns, settings, and selections

Access the Document Loader

Go to Agents > Document Stores.
Click the document store to view all the documents in that store.

Create a new Document Loader

Go to Agents > Document Stores.
Click the document store you want to add a document loader.
Click Add Document Loader.

The Select Document Loader dialog is displayed.
Click the document loader that matches your document source.

The document loader properties page is displayed. For more information, see Document Loader properties and Flowise documentation.
Configure the document loader properties.
(Optional) Click Preview Chunks.
Click Process.

Edit a Document Loader

Go to Agents > Document Stores.
Click the document store containing the document loader you want to edit.
Click Options().
Select Preview & Process.

The document loader properties page is displayed. For more information, see Document Loader properties.

Delete a Document Loader

Go to Agents > Document Stores.
Click the document store containing the document loader you want to delete.
Click Actions ().
Click Delete.
The document loader is deleted from the document store.

Document Loader columns, settings, and selections

The following columns or selections are displayed when you view a specific Document Stores page.

Column or selection	Description
Add Document Loader	Allows you to select the type of document loader that can be included in the document store.
More Actions	Lists the actions relevant to the document loader. View & Edit Chunks: Displays all chunks in the document store and allows you to edit them. Upsert All Chunks: Updates existing chunks and adds new chunks to the document store. Refresh: Reloads the document data and chunk list to display the most up-to-date information. Delete: Deletes the document store from the tenancy.
Status Indicator	Indicates the current status of the document loader. Empty: The document store does not contain any document loader. The indicator appears blank. Processing: The document store is processing document loader content. The indicator appears yellow. Refresh the page to see the updated status when processing completes. Sync: The document store contains one or more document loaders that are synced. The indicator appears light green. Upserted: Content from the document loader has been upserted in the document store. The indicator appears teal.
Loader	The document loader configuration used to ingest the document.
Splitter	Text splitting method used to divide the document into smaller sections before processing. The types of text splitters are listed below. Note: The Recursive Character Text Splitter is the recommended text splitter. It preserves meaningful structure and is suitable for large documents. Recursive character text splitter: Splits text by progressively reducing boundary levels, such as paragraph breaks, line breaks, and spaces, until the defined chunk size is met. Chunk Size: Maximum number of characters included in each chunk when the content is split. Chunk Overlap: Number of characters that overlap between consecutive chunks to help preserve context. Custom Seperator: Custom character or sequence used to define where the text should be split. The custom seperators includes the following: Blank line(\n\n: Indicates where a paragraph starts or ends. New line (\n): Splits content at line breaks. Full stop (.): Splits when a sentence ends Space ( ): Identifies the end of a word. None: Does not split the text. The document is processed as a single section. Character text splitter: Splits text by fixed character length and overlap. Chunk Size: Maximum number of characters included in each chunk when the content is split. Chunk Overlap: Number of characters that overlap between consecutive chunks to help preserve context. Custom Seperator: Custom character or sequence used to define where the text should be split. The custom seperators includes the following: Blank line(\n\n: Indicates where a paragraph starts or ends. New line (\n): Splits content at line breaks. Full stop (.): Splits when a sentence ends Space ( ): Identifies the end of a word. Code text splitter: Splits text using programming language syntax and code structure. Language: Programming language used to guide how the code is split into chunks. Examples include: cpp, go, java, js, php, proto, python, rst, ruby, rust, scala, swift, markdown, latex. Chunk Size: Maximum number of characters included in each chunk when the content is split. Chunk Overlap: Number of characters that overlap between consecutive chunks to help preserve context. Markdown text splitter: Splits based on Markdown structure such as headers and sections. Chunk Size: Maximum number of characters included in each chunk when the content is split. Chunk Overlap: Number of characters that overlap between consecutive chunks to help preserve context. HTML-Markdown text splitter: Converts HTML to Markdown, then splits based on Markdown structure. Chunk Size: Maximum number of characters included in each chunk when the content is split. Chunk Overlap: Number of characters that overlap between consecutive chunks to help preserve context. Token text splitter: Splits text by token count for models that use token-based limits. Encoding name: Token encoding used to calculate how the content is split into tokens. For example, gpt2, r50k_base, p50k_base, p50k_edit, cl100k_base. Chunk Size: Maximum number of characters included in each chunk when the content is split. Chunk Overlap: Number of characters that overlap between consecutive chunks to help preserve context.
Sources	The document source associated with the loader. For example, Pdf File, Text File, Docx File, API Loader, Epub File.
Chunks	The total number of chunks created from the document.
Chars	The total number of characters in the source file uploaded to document loader.
Actions ()	Displays the actions available for the document loader. To open the options menu, find the document loader you want and click that's displayed on its right. Preview & Process: Displays the document loader properties page. View & Edit Chunks: Displays all chunks created from the uploaded file and allows you to edit them. Upsert Chunks: Updates existing chunks and adds new chunks to the document loader. Delete: Deletes the document loader from the document store.