Manage users, app settings, and view usage statistics
Sits between open and closed registration. With registration disabled entirely, nobody can register even with a code.
The code is shown once, here. Only its hash is stored, so it cannot be read again afterwards.
| Name / Email | Role | Status | Joined | Actions |
|---|---|---|---|---|
| Loading... | ||||
Configure OpenID Connect for SSO with Azure AD, Okta, Keycloak, PocketID, Google, etc.
Callback URL:
Environment variables take precedence over DB settings. Storing password in DB is convenient but consider using env vars for production security.
Loading...
Click "Search API" to query your configured provider for all available models. Use the search box to filter results.
Nothing on this page saves by itself. Each Save button applies only the settings above it, up to the previous Save. This card has two: image settings have their own, and everything else is saved by Save model & retrieval settings at the bottom.
Models users may select in the Clinical Assistant. Leave a list empty to keep only the configured model.
To make a new model appear here, add it from the gateway: chat models under AI Model Management above, image models under Image Generation below — search there, press + Add, and it shows up in this list.
Display only. The AI prompt, retrieval and the stored answer are byte-for-byte identical either way, so turning this off cannot change what the model says. Citations are hidden, not removed — turning it back on restores them.
UTF-16 code units. Leave empty to use CLINICAL_ASSISTANT_CONVERSATION_CHARS.
This sends text outside the building. When a resource author turns it on, the model may send a short search query to the provider below. Only the query leaves — never library excerpts, never the generated content, never anything about the user — but a query written while drafting clinical material can still carry clinical detail, and the provider keeps its own logs. SearXNG is the only option here that you host yourself.
Not needed for SearXNG. Shown masked once saved.
Only used when the provider is SearXNG. Its /search?format=json endpoint must be enabled.
A separate source from the web providers above, and a separate tick box for authors. It returns structured records — title, journal, year, PMID — so a reference can be exact rather than reconstructed from a page title. Queries go to NCBI, not to a commercial provider.
Optional. PubMed works without one; a key raises the rate limit from 3 requests per second to 10, which matters for bulk work rather than for one person writing a resource. Create one at account.ncbi.nlm.nih.gov/settings — sign in, then API Key Management → Create an API Key.
NCBI asks callers to identify themselves so they can contact you before blocking you. Optional but courteous.
The model that writes a deck never sees it, so it cannot tell that a slide overflowed or that a long list wants two columns. With a reviewer chosen, each generated deck is rendered, looked at, and its layout corrected once. Wording and figures are never changed — a review that alters them is discarded.
Needs to be able to see images. One image per slide is sent on every presentation generated, so this costs money each time — a cheap capable vision model is the right choice here, not the best one available.
Answers where the assistant wrote a citation number that no returned source matched. Those markers are never turned into links, so a reader sees plain text — this is where they are recorded. Consistent entries usually mean retrieval is returning fewer sources than the answer assumes.
Click Search to query available voices from your configured TTS provider.
Click Search to query available STT models from your configured provider.
Click Search to list the image models your gateway advertises. + Add puts a model in the Clinical Assistant's Image models list; tick it there to offer it to users in chat. Unlike a voice, an image model has no single default — each workflow picks its own under Clinical Assistant / Learning.
Press Test on a model above, or type an id the gateway does not advertise.
Corpus (MCP) embeddings are configured on the indexing service, not here.
Click Search to query available embedding models from your configured provider.
Reset all announcement, feature flag, and email settings back to factory defaults. SMTP configuration and custom models are preserved.