> For the complete documentation index, see [llms.txt](https://docs.katara.ai/about/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.katara.ai/about/agents-and-answering/content-uploader.md).

# Content Uploader

A Content Uploader is an explicit destination for manually supplied documents. Use it for corpus content; upload directly to a Brain instead when the files should become that Brain's sources. Uploading to a Content Uploader does not attach documents to a Brain later.

## Before you start

Select the correct organization and ensure you can create agents and upload documents. Prepare supported files: PDF, supported image formats, HTML, DOCX, PPTX, XLSX, Markdown, or plain text. The upload form enforces a 20 MiB limit per file. Review [document access](https://docs.katara.ai/about/documents-and-collections/documents.md) before setting defaults that share future uploads.

## Create the destination

1. Open **Agent Library → Create an agent → Content Uploader**.
2. Complete **Name** and any optional description.
3. Set **Tags** if future content should receive those tags automatically.
4. Review **Default Shares**. These select people or groups who receive viewer access to future uploaded documents. Do not assume changing defaults rewrites existing document grants.
5. Select **Create agent** and confirm the destination appears in the library.

## Upload and check each file

1. Open **Document Upload**.
2. In **Upload destination**, explicitly select your Content Uploader.
3. Add files under **Documents** and remove any unintended selections before submitting.
4. Use the upload button, whose label reflects the selected documents.
5. Inspect every file's outcome. Use the failed-file retry control for unsuccessful items rather than resubmitting accepted files blindly.
6. Open **Content Management → Content**, or the agent's **Documents**, to inspect accessible uploaded content. Use [collections](https://docs.katara.ai/about/documents-and-collections/collections.md) to prepare a collection-backed Q\&A workflow.

Acceptance means the file was accepted for processing, not that extraction, indexing, or answer retrieval has completed. Content Uploader is not a generic scheduled runner: do not look for a run button as the way to submit files.

## Recover from upload problems

**No Ready Upload Destinations Found** means you need an eligible destination, not a different file. Check the organization, destination state, and permissions. For a Brain, initialization and current contribution disclosure must also be ready; follow [Brain sources](https://docs.katara.ai/about/brains/sources.md).

Retries retain the exact destination. Clear the selection before deliberately choosing another destination rather than assuming retry can move an upload. If access or organization changes during upload, resolve that scope issue before continuing. For individual failures, review file size, format, and the reported error; verify accepted records before starting another upload.
