Knowledge Base & Assets

The Knowledge Base is how an agent gets domain knowledge it doesn't carry in its prompt. Upload files, connect data sources, and the agent retrieves the relevant chunks at runtime — semantic search, not full-document stuffing.

What you can attach

Any source can be attached to one or many agents.

How retrieval works

When you attach a source with vectorization enabled:

1. Fruxon extracts text and splits it into semantic chunks.
2. Chunks are embedded with your chosen embedding model and stored.
3. At run time, the agent's query is embedded; the most relevant chunks are retrieved and injected into the step's context.
4. The agent's response can include the source citations.

You can disable vectorization for a source — useful when you want to reference the document literally (e.g., a template) rather than retrieve excerpts.

Uploading a file

1. Open Assets in the sidebar.
2. Click Upload.
3. Pick a file, name it, optionally tag it.
4. Choose whether to vectorize (default: yes).

The file is processed in the background. Status shows up in the Assets list — Pending → Processing → Completed (or Failed / Partial with an error you can inspect).

Vectorize later

If you uploaded a file with vectorization off (to use it as a literal template), you can vectorize it later without re-uploading. Open the asset, toggle Enable retrieval, and the existing file is re-processed in place — same asset ID, same references, now retrievable. Useful when a template you originally pinned as literal becomes worth searching over.

Connecting a data source

For Confluence, Notion, GitHub, Google Drive, etc.:

1. Make sure the underlying integration is connected at the organization level.
2. In Assets → Add Data Source, pick the integration and the scope (a specific space, repo, folder, page).
3. Fruxon syncs the content and keeps it refreshed on a schedule you control.

Attaching to an agent

In Studio, open the Knowledge Base panel. Pick the assets and data sources to attach. The agent's retrieval tool becomes available to its steps automatically.

Referencing assets directly

Sometimes you want the literal contents of an asset, not retrieval. Reference them in any prompt or tool config with placeholder syntax:

{{asset.contract_template}}
{{asset.company_logo}}
{{asset.brand_guidelines}}

This is common for templates (DOCX, HTML, system prompts) and reference data (CSV, JSON).

Supported file formats

• Documents — PDF, DOCX, TXT, Markdown, RTF
• Data — JSON, CSV, YAML, XLSX
• Web — HTML, URLs (auto-crawled)
• Images — PNG, JPG, WebP, GIF (used as media in document generation)

Best practices

• Chunk-friendly content beats long blobs. Documents with clear headings and short paragraphs retrieve better than walls of text.
• Attach what's relevant, not everything. A focused knowledge base produces better answers than a kitchen-sink one.
• Refresh data sources. For Confluence/GitHub/Drive, set sync schedules so retrieval reflects current state.
• Use citations. Have your agent quote the source — users trust answers they can verify, and you can audit hallucinations faster.

Next steps

• Studio — attach assets to a workflow
• Integrations — connect Confluence, GitHub, Drive, Notion as sources
• Use Cases — RAG and document Q&A patterns