Accessing Knowledge Base from Databricks One

piotrsofts — Wed, 17 Dec 2025 17:06:12 GMT

Is it possible to use Knowledge Assistant from Databricks one ?

Re: Accessing Knowledge Base from Databricks One

Louis_Frolio — Thu, 18 Dec 2025 17:52:35 GMT

Short answer: yes, you can build and use a Databricks Knowledge Assistant today. Exposing it directly inside the Databricks One chat UI is currently limited to specific agent types.

What the Knowledge Assistant is

The Knowledge Assistant is an Agent Bricks pattern for building a domain-specific RAG assistant over your own documents. It answers questions with citations and gets better over time through expert feedback (ALHF). Think “your org’s knowledge, grounded, auditable, and improvable.”

Can you use it from Databricks One?

Right now, the Databricks One chat experience supports Genie agents. There isn’t a first-class, generic Knowledge Assistant UI in One yet. That said, this is a known gap and is being considered as a future enhancement.

What you can do today

You can build a Knowledge Assistant using Agent Bricks (Beta) and test it end-to-end in AI Playground. From there, you can generate production-ready code for API access (curl or Python) or apply it directly to data.

For end-user access, the recommended path is Databricks Apps. There’s a Marketplace app template specifically designed to front a Knowledge Assistant endpoint, which gives you a clean, turnkey UI with minimal wiring.

If you’re aiming for a more unified experience across structured and unstructured data, you can also use a Multi-Agent Supervisor. This lets you coordinate a Genie Space (for structured data) alongside your Knowledge Assistant (for unstructured content) behind a single conversational entry point.

What’s required to build one

You’ll need Mosaic AI Agent Bricks enabled (Preview/Beta), Unity Catalog, serverless compute, and access to foundation models under system.ai. On AWS, supported regions today are us-east-1 and us-west-2.

Your knowledge sources can live in Unity Catalog volumes (txt, pdf, md, ppt/pptx, docx) or in a Vector Search index built with the databricks-gte-large-en embedding model.

Quick setup flow

Go to Agents → Knowledge Assistant → Build. Configure your knowledge sources, add optional system instructions, and create the agent.

Test everything in AI Playground — review answers, citations, and traces — and use expert feedback to improve quality via ALHF.

When you’re ready to share, grant end users CAN QUERY on the agent endpoint and surface it through a Databricks App or your own custom UI.

Hope this helps, Louis.

Re: Accessing Knowledge Base from Databricks One

piotrsofts — Fri, 19 Dec 2025 07:51:38 GMT

@Louis_Frolio - thank you, I love the answer, I will try to PoC it, and share my experience

Re: Accessing Knowledge Base from Databricks One

piotrsofts — Fri, 19 Dec 2025 12:04:29 GMT

Built it - and I will be honest, not exactly what I did expected, I will wait for both features (this one, and "Domains" data segregation under Databricks One)

Re: Accessing Knowledge Base from Databricks One

Louis_Frolio — Fri, 19 Dec 2025 13:25:59 GMT

@piotrsofts , if you are happy please accept as a solution so others can be confident in the approach. Cheers, Louis.

topic Re: Accessing Knowledge Base from Databricks One in Generative AI

Accessing Knowledge Base from Databricks One

Re: Accessing Knowledge Base from Databricks One

Re: Accessing Knowledge Base from Databricks One

Re: Accessing Knowledge Base from Databricks One

Re: Accessing Knowledge Base from Databricks One