Documents

Objective

Build and manage your AI knowledge base. Upload documents so your agents answer questions from your own content using RAG (Retrieval Augmented Generation). Each document is indexed into your Google File Search knowledge base, can be enriched with an AI overview, and can be assigned to one or more agents.

Access

Sidebar -> Documents Route: /app/{tenant}/documents

Roles

• owner, admin, agent — open the module, upload documents, retry failed uploads, and generate AI overviews.
• owner, admin — delete documents and assign or unassign documents to agents. Agents see assignments read-only and do not get the delete action.
• viewer — no access to this module.

Prerequisites

• A Google AI API key connected in Integrations (required). Until it is connected, a banner appears and Upload Document opens a dialog that links to Integrations.
• A verified email address. Upload is blocked until your email is verified on plans that require it.
• An active subscription. Upload is blocked while the subscription is restricted or suspended.
• Available document slots in your plan (see Plans and limits).

Plans and limits

Upload a document

Steps:

1. Press Upload Document.
2. Drag a file onto the drop area, or click to browse.
3. Complete the fields.
4. (Optional) Open Advanced settings to override chunking.
5. Press Upload Document.

Fields:

Supported file types:

• PDF, DOCX, XLSX, PPTX, TXT, MD, CSV, JSON, HTML, PNG, JPEG, DOC, XLS, RTF, ODT

Some recognizable formats are not supported and are rejected with a specific message that names the format and suggests what to convert it to: HEIC/HEIF, WEBP, and TIFF images (convert to JPEG or PNG), legacy PowerPoint PPT (convert to PPTX), OpenDocument Spreadsheet ODS (convert to XLSX or CSV), and EML email exports (convert to PDF or plain text).

The file content is validated against its real type on upload, not just the file extension. A renamed or corrupted file is rejected even if it claims a supported type.

After upload the document appears as Processing and is indexed in the background. AI enrichment runs automatically: a short summary is extracted for every document, and for documents typed as Legal a per-article index is also built.

Document types (chunking presets)

The Document Type controls how the file is split into chunks for search. Choose the one that best matches the content.

If you leave Document Type at its General default, Helios picks a better preset automatically for some files: spreadsheets, CSV, and JSON are chunked with the Technical preset so a full row or record is never split mid-way. An explicit choice of any type is always respected and never overridden.

Advanced chunking settings

Open Advanced settings in the upload dialog to override the preset for technical use cases. When Advanced is on, its values are used instead of the Document Type preset.

Custom values are clamped to safe limits before processing.

Processing and statuses

Each document shows a status:

Every document also shows its knowledge base store state: Ready, Processing, Failed, or No File in Store.

A document stuck in Processing for more than 2 minutes without being indexed is automatically marked Failed so you can act on it.

For a Failed (or stuck Processing) document, the retry action lets you re-select the file and run indexing again. It re-applies the same checks as a new upload (Google AI key, email verification, file type, size, and the upload rate limit).

AI overview (enrichment)

An AI overview is a short summary your agent uses to describe what a document is about. For documents typed as Legal, a per-article index is also stored so the agent can quote any article verbatim by number.

• Enrichment runs automatically after every upload. You can also generate or regenerate the overview from the document row (Generate AI overview) or from the document detail view; the control appears once the document is Ready.
• Documents left at the General type are classified automatically during enrichment: if the extraction detects that the content is actually legal, technical, or FAQ material, the Document Type is updated — and a document detected as Legal gets its per-article index built even though you never picked Legal. An explicit type choice is never overridden.
• For Legal PDFs, the article index is extracted directly from the document text whenever possible, with AI extraction as the fallback. Regenerating reuses the stored text when available, which makes it fast and nearly free.
• The job runs in the background. You get a notification when it finishes, even if you navigate away.
• Cost on your Google AI key: about $0.005 for the summary on short documents, up to about $0.10 when both the summary and the legal article index run on long legal codes.
• Regenerate after the document content changes, or if a previous extraction missed something.

Document details

Click a document name to open its detail view. It shows:

• File info: size, file type, uploaded date, and knowledge base store state.
• AI overview: title, document type, total articles, total chapters, signing authority, signing date, jurisdiction, and summary (when extracted).
• Assigned agents.

Original files are not downloadable. Helios indexes documents into your knowledge base for retrieval and does not keep a separate copy of the original file, and Google File Search does not expose a way to download it back out once indexed.

Assign documents to agents

Each document row and the detail view include an Assign agents control.

• Toggle an agent to add or remove the document from that agent's knowledge base.
• Assigning the first document to an agent turns its knowledge base (RAG) on; removing the last one turns it off.
• Only owners and admins can change assignments; agents see them read-only.
• You can also manage the same assignments per agent from the Agents editor's knowledge base section.

Search and filters

• Search box: matches file name, display name, description, and document type.
• Status pills: All statuses, Ready, Processing, and Failed, each with a count.
• Type filter: All types, General, Legal / Regulatory, Technical / Code, and FAQ / Q&A.
• Stat chips above the list show Total Documents and Ready, plus Processing and Failed when any exist.

Delete a document

Press the delete icon on a document row and confirm. Only owners and admins see this action. It permanently removes the document from your knowledge base and from any agents it was assigned to, and it cannot be undone. If the document cannot be removed from the knowledge base store, the delete is aborted so nothing is left half-deleted — try again.

Good practices

• Give each document a clear Display Name.
• Write a Description so the agent knows when to use the document.
• Pick the right Document Type. Use Legal for laws and contracts to enable verbatim article lookup.
• Split very long documents by topic.
• Generate the AI overview so agents can describe documents at a glance.

Common errors

Screenshot

Related

• AI Agents (RAG)
• Integrations (Google AI API key)