Files & Resources
Alongside Chat, each workspace window has Knowledge and Assets sections. Web results can be added to Assets, while Profile is managed from node settings. This guide covers how to upload files, what types are supported, how the model uses your files when answering questions, and how to turn responses into documents you can keep.
The workspace sections
The workspace toolbar has three sections: Chat, Knowledge, and Assets. Profile is a node-level view opened from Node Settings rather than a workspace section. These sections aren't storage for its own sake — the content in them is context that can inform the model's responses. Files you've uploaded, pages fetched during research, and facts from your knowledge base are all drawn on automatically when they're relevant to what you're asking.
Uploading files
Click Upload in the Assets section to add a file to the workspace. Files are durably stored on the node. They may be sent through SaaS to extraction or inference services when the configured processing path requires it. After upload, the file is processed: text-native files (plain text, Markdown, HTML, CSV, JSON, XML, YAML) are ingested directly into the knowledge base. Binary files — PDFs and images — go through an extraction step that converts them to readable text first. Other formats, including Word and Excel documents, are not currently accepted — the upload is rejected; export or copy their content into a supported format such as plain text, Markdown, CSV, or PDF.
Both paths result in the file's content being available to the model when it's relevant. The processing happens automatically in the background after upload; you don't need to do anything once the file is uploaded.
A 32 MB per-file limit applies to uploads; the server rejects files larger than 32 MB. For large documents, consider splitting them into smaller files by section or chapter.
Supported file types
Two categories of file are supported: text-native and extractable. Text-native files are read directly — their content is plain text that needs no conversion. Extractable files go through a processing step that converts them to text before they're ingested.
| Type | Extensions | How it's processed |
|---|---|---|
| Plain text | .txt |
Read directly |
| Markdown | .md |
Read directly |
| HTML | .html, .htm |
Read directly |
| CSV | .csv |
Read directly |
| JSON | .json |
Read directly |
| XML | .xml |
Read directly |
| YAML | .yaml, .yml |
Read directly |
.pdf |
Text extracted by the extraction service | |
| Image | .png, .jpg, .jpeg, .webp |
Visual content extracted by the extraction service |
Files that don't match any of the supported types are rejected at upload. If you need to reference content from an unsupported file format, export it as PDF, or copy the relevant text into a plain text or Markdown file and upload that.
How the model uses uploaded files
When you send a question, Varen searches your uploaded files — along with your knowledge base — for content relevant to the question. If a file contains relevant content, it's included in the model's context automatically. You don't need to tell Varen which files are relevant; it works this out from the content of your question.
You can also refer to files by name to bring them in explicitly — "summarise the Q4 report I uploaded" or "what does the lease say about the break clause?" This is useful when the question is specifically about that document and you want to make sure the model focuses on it.
For dense reference documents — a tenancy agreement, a financial statement, an inspection report, a medical letter — uploading them and then asking specific questions is often more effective than pasting the text into a message. The model can re-read the file in future sessions without you re-uploading it, and you can ask different questions about the same document across multiple sessions.
Documents and the editor
Anything worth keeping can be turned into a document. Varen has a built-in WYSIWYG document editor — what you see is the formatted document, not raw markup — and there are three ways into it:
- A whole session. The Export button in the workspace header assembles the visible conversation — every turn you haven't collapsed — into a single document and opens it in the editor. Re-exporting the session updates the same document in place, so you can keep one running record of the thread.
- A single turn. Each answer has an Open in editor (⤢) button, which opens just that answer as a new document — useful when one response is the thing you want to keep or rework.
- A document Varen creates. When a response includes a drafted document, the turn shows a button to open it. If Varen later revises that document, the open window updates in place — silently if you haven't touched it, or with a choice to Replace with Varen's version, Keep my edits, or Open as new window when you have.
From the editor you can edit freely and download the result as .rtf (the primary format — it opens formatted in Word, LibreOffice, and Google Docs), .md, or .html. Downloads are produced locally in your browser; nothing is sent anywhere when you save. Documents are deliberately not saved back into Assets: generated drafts must not quietly re-enter the corpus the model draws on. If a finished document should become reference material, download it and upload it explicitly as a file — that way only final versions enter the knowledge base.
Web search
Varen can search the web as part of answering a question. Results appear in a collapsible Web results panel in the conversation. You can open a result in a new tab or use Add to Assets to fetch it into the workspace for later retrieval. Web search is covered in detail in Lens & Web Search.
Outcomes
Outcome workspaces are guided workflows with a defined output document: rather than a free conversation, the workflow leads you through the information needed to complete a specific artefact. Outcomes are in early development and not yet alpha quality — see Outcomes for what they are and the current state of the feature.