Self-hosted AI interface
How to use
Open WebUI.
Giving individuals or teams one controlled interface for multiple local or hosted models, reusable prompts, tools, and document knowledge bases.
Open WebUI is a self-hosted AI interface for local and hosted models, tools, and knowledge. Giving individuals or teams one controlled interface for multiple local or hosted models, reusable prompts, tools, and document knowledge bases. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.
AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.
Access & setup
Find, install, and sign in to Open WebUI
Get into the official Open WebUI experience with the right account and a setup you understand.
- 01
Start at https://openwebui.com/ and confirm the domain before entering account or payment information.
- 02
Availability: Self-hosted deployments are documented for Docker, Python, Kubernetes, and other environments, with a separate desktop option also available.
- 03
A supported container or Python environment, persistent storage, network access to the chosen model backend, and appropriate authentication and backup controls.
- 04
Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.
- 05
Run one low-risk test task before connecting sensitive files, repositories, or workspace data.
- Use official download pages.
- Review permissions during setup.
- Keep installers and applications updated.
First session
Your first useful Open WebUI session
Learn the interaction loop using a small task with a clear outcome.
- 01
Install Open WebUI from an official method with persistent storage and private initial network access.
- 02
Create the first administrator account and connect an Ollama or compatible API provider under Admin Settings.
- 03
Verify the intended models, streaming, errors, and data path with non-sensitive prompts.
- 04
Back up configuration and data, restrict access, and document updates before adding users or knowledge.
- State the outcome before the background.
- Provide the real source material.
- Review the result before expanding the task.
Quality control
Check the quality of Open WebUI output
Establish that a model's output is reliable enough for the job you are handing it.
- 01
Restate the task, the acceptance criteria, and the failure cost before evaluating any response.
- 02
Test with a fixed evaluation set rather than ad-hoc prompts, so changes are measurable across model versions.
- 03
Check determinism and drift: record model version, parameters, and date, because providers update models underneath you.
- 04
Probe the failure modes deliberately — ambiguous inputs, adversarial phrasing, and out-of-scope requests.
- 05
Validate structure as well as content: confirm schemas, types, and required fields survive real inputs.
- Pin and record the model version with every result.
- Evaluate against a fixed set, not one-off prompts.
- Validate output structure before it reaches downstream code.
Privacy & permissions
Use Open WebUI safely
Understand what leaves your system on every call, and what the provider keeps.
- 01
Classify the data in each request before it is sent to a hosted model.
- 02
Check the provider's retention and training terms for your specific plan, not the marketing page.
- 03
Store API keys in a secret manager, scope them per project, and rotate them on a schedule.
- 04
Strip or tokenise personal and regulated data before it reaches the request body.
- 05
Set rate limits, spend caps, and monitoring so a runaway loop is bounded and visible.
- Self-hosting makes you responsible for authentication, network exposure, secrets, updates, backups, model-provider policies, and access to shared knowledge. Treat plugins and tools as executable integrations and test them with least privilege.
- Follow your organisation's approved-use policy.
- Never treat fluent output as authorization to act.
Core workflows
Step-by-step ways to use Open WebUI for the work it does best.
Each workflow is a separate guide with its own steps and review checkpoints.
Add a local or hosted inference backend and verify the full connection before inviting other users.
↗ 02 WorkflowBuild a grounded Knowledge workspace in Open WebUIOrganize approved documents into a focused knowledge base and measure whether retrieval supports accurate answers.
↗Official references
Check the current product documentation.
Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.