> For the complete documentation index, see [llms.txt](https://docs.neohive.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.neohive.ai/add-your-context/documents.md).
# Add documents and images
Upload markdown, text, PDF, Office, and image files to a Files Index so your agent can recall them alongside your code.
A [Files Index](/reference/glossary.md#files-index) holds documents that you upload, such as specs, runbooks, design docs, meeting notes, or an exported notes vault. NeoHive turns each file into text, and your agent recalls that text the same way as code. You create the Files Index once, and then add, replace, or delete its files whenever your documents change.
{% hint style="info" %}
If your documents are in a GitHub or GitLab repository, add the repository instead of uploading the files, so NeoHive keeps them in sync as they change. To add the repository, see [Add a repository](/add-your-context/repositories.md).
{% endhint %}
## Create the Index
NeoHive accepts markdown, text, PDF, Word, Excel, and PowerPoint files, and PNG or JPEG images, up to 50 MB each. For more information about each format and its limits, see [Supported file types](/reference/file-types.md).
To create a Files Index, do the following:
1. In the dashboard, open your [Hive](/reference/glossary.md#hive).
2. Click **+** next to **Indexes**.
3. Select **File Upload**.
4. Enter an **Index name** that describes the documents, for example `Engineering Docs`.
5. Click **Create Index**.
To upload files at the same time, drag them onto the **Files** drop zone, or click the drop zone to browse, before you click **Create Index**. NeoHive then fills in **Index name** from the first file, and you can change it. To upload files later, see [Manage files later](#manage-files-later).
Each file becomes searchable as soon as it finishes processing.
To help your agent choose this Index, set a **Description** on the **Index Info** tab. Name the kind of documents the Index holds. Your agent reads this description through `list_indexes`.
## Manage files later
To add more files, do the following:
1. Open the Index, and then select its **Files** tab.
2. Drag files onto the drop zone, or select the drop zone to browse.
3. Select the upload button, which shows the number of files, such as **Upload 3 files**.
The tab shows which file is processing and how much of the upload is done.
To replace a document, upload the new version with exactly the same file name. NeoHive replaces the old file and its content.
{% hint style="warning" %}
When you click the trash icon next to a file, NeoHive deletes the file and its content from the Index right away. NeoHive does not ask you to confirm.
{% endhint %}
## Large or scanned files
A large file can take more than five minutes to convert, and a scan with faint or very small text can fail with `No text could be extracted from this document`. For more information about conversion time limits and files with no readable text, see [Supported file types](/reference/file-types.md#file-uploads).
---
# 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.neohive.ai/add-your-context/documents.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.
