AITEZA Docs Help

Settings

Owners and editors can manage a Dataroom by clicking on the Settings button in the Dataroom.

Files

Upload files to the Dataroom by clicking on the Upload Files button.

Supported File Types

AITEZA supports a wide variety of file formats for document processing. Files are automatically processed and indexed for retrieval.

Documents

  • PDF (.pdf) – Portable Document Format, including scanned documents

  • Word (.doc, .docx) – Microsoft Word documents (legacy and modern)

  • PowerPoint (.ppt, .pptx) – Microsoft PowerPoint presentations

  • Excel (.xls, .xlsx) – Microsoft Excel spreadsheets

  • RTF (.rtf) – Rich Text Format

  • Plain Text (.txt) – Plain text files

  • Markdown (.md) – Markdown formatted text

  • CSV (.csv) – Comma-separated values

  • HTML/XML (.html, .htm, .xml) – Web and markup files

Images

  • JPEG (.jpg, .jpeg) – Common image format

  • PNG (.png) – Portable Network Graphics

  • TIFF (.tiff, .tif) – Tagged Image File Format

  • BMP (.bmp) – Bitmap images

  • GIF (.gif) – Graphics Interchange Format

Audio (with automatic transcription)

  • MP3 (.mp3) – MPEG Audio Layer 3

  • WAV (.wav) – Waveform Audio File Format

  • FLAC (.flac) – Free Lossless Audio Codec

  • AAC (.aac, .m4a) – Advanced Audio Coding

  • OGG (.ogg) – Ogg Vorbis audio

  • WebM (.webm) – WebM audio

  • WMA (.wma) – Windows Media Audio

  • AIFF (.aiff) – Audio Interchange File Format

Email

  • Outlook (.msg) – Microsoft Outlook messages

  • EML (.eml) – Standard email format (RFC 822)

  • MBOX (.mbox) – Mailbox format for multiple emails

Uploading Files

  1. Either drag and drop files from your computer onto the settings page or click `Upload Files` to select files from your computer.

  2. After processing, the files will be listed in the Dataroom.

File Content Viewer

When you open a file from the file list, the content viewer displays the extracted markdown representation. For PDFs, the original document is shown alongside the markdown. The viewer provides several tools:

  • Version History (Versionsverlauf): View all versions of the file with type indicators and notes.

  • Copy MD (MD kopieren): Copy the extracted markdown content to your clipboard.

  • Download: Download the original source file or the extracted markdown file.

  • Edit (Bearbeiten): Open the built-in markdown editor to modify file content directly.

  • Search Highlighting: Search terms are highlighted within the document content for quick navigation.

File Versioning

Files in datarooms have full version history. Every change — whether an initial upload, manual edit, reprocessing, or file replacement — creates a new version that is tracked and can be restored.

View File Version History

  1. Open a file in the content viewer by clicking on it in the file list.

  2. Click the Version History button in the viewer toolbar.

  3. The version history panel shows all versions with type indicators (Initial upload, Manual edit, Reprocess, File upload, Restore), user information, timestamps, and optional notes.

  4. Click any version to view its content. Use the Restore action to revert to a previous version.

Editing File Content

You can edit file content directly using the built-in rich-text markdown editor. Each edit creates a new version automatically, preserving the full history.

Edit a File

  1. Open a file in the content viewer.

  2. Click the Edit button to switch to edit mode.

  3. Make your changes in the markdown editor.

  4. (Optional) Add a note describing your changes (max 1000 characters). This note will be visible in the version history.

  5. Click Save to create a new version with your changes, or Cancel to discard.

Uploading a New File Version

You can upload a new file to replace the source document while preserving the full version history. This is useful when you have an updated version of a document but want to keep the previous versions accessible.

Upload a New File Version

  1. Locate the file in the file list and open the actions menu.

  2. Select Upload New Version.

  3. Select the new file from your computer. The file will be processed and a new version will be created.

Moving Files to Another Dataroom

Owners and Editors can move a file to a different Dataroom they have access to. Moving a file removes it from the original Dataroom and re-indexes it in the target Dataroom; future retrieval will use the target Dataroom only.

Moving a File to Another Dataroom

  1. Navigate to the source Dataroom and open `Settings` > `Files`.

  2. Locate the file you want to move and click the `Move` action (ellipsis menu if not directly visible).

  3. Select the target Dataroom from the list. Only Datarooms where you are `Owner` or `Editor` are selectable.

  4. Confirm the move in the dialog.

  5. After processing, the file appears in the target Dataroom and is removed from the original; its contents become available for retrieval there.

Reprocessing Files

You can reprocess existing files to update their content and embeddings using different processing pipelines. This is useful when:

  • Processing algorithms have been updated.

  • The initial processing did not extract content correctly (e.g., scanned documents).

  • You want to try a different processing model for better results.

Processing Pipelines

AITEZA offers multiple processing pipelines for document extraction:

Pipeline

Description

Best For

DOCLING

Advanced document processing with layout understanding.

Complex documents, tables, multi-column layouts

VLM

Vision Language Model pipeline using AI vision capabilities.

Hard-to-read documents, complex layouts, handwritten text

Using the VLM Pipeline

The VLM (Vision Language Model) pipeline uses advanced AI vision models to understand and extract content from documents. This is particularly useful for:

  • Scanned or photographed documents with poor quality.

  • Documents with complex visual layouts.

  • Handwritten notes or annotations.

  • Documents where standard OCR fails.

Reprocess a File with VLM

  1. Navigate to the Dataroom settings and open the `Files` section.

  2. Locate the file you want to reprocess and click the reprocess action (ellipsis menu if not directly visible).

  3. Select `VLM` as the processing pipeline.

  4. Choose a VLM model (e.g., `gpt-4o`) from the available options.

  5. Confirm to start reprocessing. The file will be re-indexed with the new content.

Retry Embeddings

If content extraction succeeded but vectorization (embedding creation) failed for a file, you can retry the embedding step without reprocessing the entire file. This is a lightweight operation.

Retry Embeddings for a File

  1. Locate the file in the file list and open the actions menu.

  2. Select Retry Embeddings (or use the bulk action Reembed for multiple files).

  3. Confirm the action. The embeddings will be regenerated without re-crawling or reprocessing the source.

Websites

Add websites to the Dataroom by clicking on the Add Website button.

Adding Websites

  1. Enter a valid URL like `https://www.example.com` in the url field.

  2. Enter a descriptive name for the website in the name field.

  3. Choose if subpages like `https://www.example.com/subpage` should be included.

  4. After processing, the website will be listed in the Dataroom.

Crawled URLs

For websites with subpage crawling enabled, you can view all crawled subpage URLs along with metadata such as max depth, max pages, and the last scanned date.

View Crawled URLs

  1. Locate the website in the Websites tab and click the Crawled URLs action button.

  2. A dialog displays all crawled subpage URLs with their metadata.

Website Version History

Web sources have version history showing snapshots of crawled content over time. This allows you to track how website content has changed between crawls.

View Website Version History

  1. Locate the website in the Websites tab and click the Version History action button.

  2. The version history panel shows all versions with timestamps and crawled content previews.

  3. Click any version to view its full crawled content.

Retry Embeddings for Websites

If a website was crawled successfully but embedding creation failed, you can retry the embedding step without re-crawling.

Retry Embeddings for a Website

  1. Locate the website in the Websites tab and open the actions menu.

  2. Select Retry Embeddings.

  3. Confirm the action. Embeddings will be regenerated from the existing crawled content.

Images

The Images tab lets you upload image files that are made available to multimodal models for true visual analysis in agent mode. This is fundamentally different from uploading images via the Files tab, where only text is extracted via OCR.

When you upload an image here, AITEZA automatically generates a short and a long description of the image. These descriptions are vectorized and used for text-based semantic search, so the agent can find and retrieve the right image based on your query. Once located, the agent can inspect the actual image file using its Get Image tool — not just the text representation.

Supported Image Formats

All common image formats are supported for upload in the Images tab, including JPEG, PNG, GIF, BMP, TIFF, WebP, and others.

Uploading Images

  1. Navigate to the Images tab in the Dataroom settings.

  2. Click Upload Images or drag and drop image files onto the page.

  3. AITEZA automatically generates descriptions for each uploaded image. After processing, the images are indexed and available for visual analysis in agent mode.

Downloading Images

You can download images directly from the Images tab.

Download an Image

  1. Locate the image in the Images tab.

  2. Click the Download action on the image card.

Image Version History

Images support full version history, similar to files. You can view previous versions and upload new versions while preserving history.

View Image Version History

  1. Locate the image in the Images tab and click the Version History action.

  2. The version history panel shows all versions with type indicators, timestamps, and notes.

  3. Click any version to view it. Use the Restore action to revert to a previous version.

Upload a New Image Version

  1. Locate the image in the Images tab and open the actions menu.

  2. Select Upload New Version.

  3. Select the new image file. A new version will be created while preserving the full history.

Retry Embeddings for Images

If an image was processed successfully but embedding creation failed, you can retry the embedding step.

Retry Embeddings for an Image

  1. Locate the image in the Images tab and open the actions menu.

  2. Select Retry Embeddings.

  3. Confirm the action. Embeddings will be regenerated from the existing image descriptions.

You can pre-link a dataroom with other datarooms so that those linked datarooms are automatically suggested as a pre-selection when any user starts a new chat from this dataroom. This is especially useful for teams that regularly work across related datarooms and want to reduce manual setup when starting a conversation.

  1. Navigate to the Settings page of the dataroom you want to configure.

  2. Locate the Default Dataroom Links section.

  3. Select one or more datarooms from the list to pre-link them. Only datarooms you have access to are shown.

  4. Save your changes. The selected datarooms will now be pre-selected for new chats started from this dataroom.

Model Selection

Select the language model that should be used to answer questions in the Dataroom. Each user that has access to the Dataroom can select a language model that you make available.

Adding Models

  1. Click on the `Add Model` button

  2. Search for the large language model you want to add.

  3. (Optional) Enable the inheritance option (`Apply to all subdatarooms`) to make this model available in all immediate and nested subdatarooms.

  4. Click on the `Add` button to add the language model to the Dataroom.

  5. After processing, the language model will be available for selection in the Dataroom.

Removing Models

  1. Click on the `Remove` button next to the large language model you want to remove.

  2. (Optional) If inheritance was previously applied, choose whether removal should also propagate to all subdatarooms.

  3. After processing, the language model will not be available in the Dataroom.

User Access Management

Manage which users have access to the Dataroom by navigating to the Manage Access section of the settings page.

Adding Users

  1. Click on the `Add User` button.

  2. Search for the user you want to add. You can search by email address or name.

  3. Assuming you have the necessary access rights, you can also add users that are not yet registered in the system.

  4. Choose the role of the user. The role can be `Owner`, `Editor` or `Viewer`.

  5. (Optional) Click `Inherit to all subdatarooms` to automatically grant the same access role in all existing subdatarooms.

  6. Click on the `Add` button to add the user to the Dataroom.

  7. After processing, the user will have access to the Dataroom

Changing User Roles

  1. Change the role of a user by selecting the role from the dropdown menu next to the user.

  2. (Optional) If the user's access is inherited, choose whether the role change should propagate to all subdatarooms.

  3. After processing, the user will have the new role in the Dataroom.

Removing Users

  1. Click on the `Remove` button next to the user you want to remove.

  2. (Optional) If the user's access was inherited, choose whether removal should also apply to all subdatarooms.

  3. After processing, the user will not have access to the Dataroom.

Renaming a Dataroom

Renaming a Dataroom

  1. Navigating to the Dataroom Name section of the settings page

  2. Enter a new name for the Dataroom

  3. Click on the `Save` button to save the new name

Deleting a Dataroom

Deleting a Dataroom

  1. Navigate to the `Delete Dataroom` section of the settings page

  2. Click on the `Delete Dataroom` button

  3. Confirm the deletion by clicking on the `Delete` button in the confirmation dialog

Last modified: 11 June 2026
DataroomsCasual Chat