File Upload Source Connector

The File Upload Source Connector allows you to upload files as a data source for your pipelines. This guide explains the configuration options available when setting up a File Upload connector.

Configure the Connector

To configure a connector to upload files:

1. Click Source Connectors from the main menu.

2. Click New Source Connector from the Source Connectors page.

3. Select the File Upload card.

   

4. Enter a name for your integration, and select one or more files to upload.

   • You can upload up to 25 files in one batch through the UI.
   • There is no limit to the total number of documents.

5. When you've selected all desired files, click Confirm Selection.

   

Alternative: Uploading Files via API

• In addition to using the UI, you can also upload files programmatically using the API. You can find more information here: Upload a file to the connector storage

Supported File Types

The File Upload Source Connector supports a wide range of file types. Below is a list of supported formats you can upload:

Type / Description	Common Extensions
PDF	.pdf
Word Documents	.doc, .docx
Google Docs	.gdoc
Open Document Text	.odt
Rich Text Format	.rtf
EPUB Files	.epub
PowerPoint	.ppt, .pptx
Google Slides	.gslides
Excel Spreadsheets	.xls, .xlsx
Google Sheets	.gsheets
Open Document Spreadsheet	.ods
Email (EML)	.eml
Outlook Email (MSG)	.msg
Plain Text	.txt
HTML Files	.html, .htm
Markdown	.md
JPEG Images	.jpg, .jpeg
PNG Images	.png
WebP Images	.webp
SVG Images	.svg
GIF Images	.gif
JSON	.json
CSV	.csv

Note: You can upload up to 25 files in one batch through the UI. There is no limit to the total number of documents you can upload overall.

Adding Additional Files to an Existing File Upload Connector

1. Click on Source Connectors in the sidebar, then click the edit icon next to the connector you wish to add additional files to.

2. Select additional files. They will be uploaded and added to your connector.

Configuring the File Upload Connector in a RAG Pipeline

Your File Upload connector is reusable across pipelines, and allows you to connect to this same set of files in different pipelines without specifying the files every time.

What's next?

• If you haven't yet built a connector to your vector database, go to Configuring Vector Database Connectors and select the platform you prefer to use for storing output vectors.

  OR

• If you're ready to start producing vector embeddings from your input data, head to Pipeline Basics. Select your new connector as the data source to use it in your pipeline.