46112e1221
Asking someone to find Settings → Security → Create new app password is a poor first run, and it is the step people give up on. Nextcloud has its own answer: Login Flow v2. The person enters their server address, signs in on Nextcloud the way they normally do — SSO, 2FA, a password manager — and Nextcloud generates an app password for this app. We never see their real password. Pasting an app password still works, behind "Use an app password instead". It is the fallback, not the front door. The security of this is all in what is trusted. The remote server chooses both the login URL and the poll endpoint, so both are SSRF-checked and both must be on the host the person actually typed — an endpoint pointing elsewhere would make this a request-forgery gadget aimed at whatever it named. The server Nextcloud reports at the end is re-checked before it is stored. The poll token is a credential, so polling happens server-side and the browser holds only an opaque handle bound to its own account. Flows live in memory with a 20 minute life, matching Nextcloud's own expiry: a login lasts minutes, and a restart mid-flow is a retry rather than a loss. Starting a second flow replaces the first, which is what clicking again means. The tab is opened from the click itself, before the request — opening it after an await is what a popup blocker stops. Removed with Learning Hub: the WebDAV browse path. Its field, its route and its column are gone, since nothing browses Nextcloud any more. nextcloud_folder is a different column and still in use. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
6.1 KiB
Features Explained
This file is a practical operator-oriented overview of major Ped-AI features. It intentionally describes the current fork, not historical browser Whisper behavior.
Clinical Documentation
Ped-AI generates pediatric clinical notes from typed input, dictation, or recorded audio. Major workflows include live encounters, dictation cleanup, sick visits, well visits, SOAP notes, hospital courses, chart review, ED documentation, and developmental milestones.
Model selection is available per task where the UI exposes a tab-level selector. Admin defaults provide the baseline model and user/task choices can override that baseline.
Generated notes can expose post-note helper panels. Billing suggestions and don't-miss review are clinician-facing. Patient education handouts are parent-facing drafts generated from the edited note, with optional diagnosis, medication, and preferred-language context. The clinician must verify the handout before sharing it.
Phone Extensions And Pagers
The bedside tools include a per-user phone extension and pager directory. Entries support active/trash views, search, soft delete/restore, permanent purge, ZIP export, and JSON/ZIP import. Import preview flags exact active duplicates, exact trashed matches that can be restored, and possible duplicates before committing changes.
Speech
Final transcription is server-side through LiteLLM. Configure upstream STT providers in LiteLLM rather than in Ped-AI.
Browser-native Web Speech is only an explicit opt-in preview path. It is not the final clinical transcript and may use browser-vendor cloud services.
Browser Whisper and browser-local model workers are removed. Do not expect a pre-download model button, public Whisper worker, or bundled Xenova model path.
Text To Speech
The voice preview button calls LiteLLM TTS and plays the returned audio in the browser. If preview is silent, check that a LiteLLM voice is selected, the gateway is configured, the user is authenticated, and browser autoplay has not blocked playback.
Nextcloud WebDAV
Two ways to connect. Sign in with Nextcloud uses Nextcloud's own Login Flow v2: the person enters their server address, signs in on Nextcloud itself the way they normally do — SSO, 2FA, a password manager — and Nextcloud generates an app password for this app. We never see their real password and they never have to find the app-password screen. An app password can still be pasted in directly, under Use an app password instead.
The poll token Nextcloud issues is a credential, so the polling happens on the server; the browser holds only an opaque handle bound to its own account. Both URLs the server hands back are checked and must be on the host the person typed.
Once connected, generated notes and rendered resources can be saved to it. A resource is sent as the rendered file — a PowerPoint or Word document, exactly what the download would have produced — not as text.
Documents And S3
Document upload is optional and depends on S3-compatible storage configuration. Treat uploaded documents as PHI unless you have a separate deployment reason not to.
Audio Backups
Audio backups exist to recover failed transcription attempts.
- They are created when transcription fails.
- They are encrypted before persistent storage.
- They expire automatically.
- Users can retry or delete them from Settings.
My Resources
Personal teaching material a user generates for themselves: a presentation or a document, built from a subject and optional instructions, optionally grounded in PubMed, web search, and the clinical corpus, and optionally carrying generated figures.
Decks are stored as a typed deck rather than as markdown, and
scripts/render_pptx.py (python-pptx) renders that deck to PowerPoint;
scripts/render_docx.py (python-docx) renders the same typed source to Word.
Export also offers PDF, via Gotenberg, and plain markdown. An optional vision
review pass renders the deck, looks at the slides, and returns layout fixes; it
is off by default.
Full detail in my-resources.md.
Clinical Assistant
Answers clinical questions against the indexed corpus rather than from model
memory: Ped-AI asks the MCP retrieval service for sources, builds a grounded
prompt, and renders the answer with citations and source cards. Answers are
deliberately never cached. Full detail in
clinical-assistant.md.
Admin Panel
Admins can manage users, roles, registration, security settings, model defaults, prompts and logs. Production deployments should enable SSO/2FA and restrict admin access.
Feature Status
| Feature | Status | Notes |
|---|---|---|
| Clinical note generation | Active | Provider depends on AI_PROVIDER, defaulting to LiteLLM when a gateway is configured. |
| Server transcription | Active | Routed through LiteLLM; the upstream vendor is a gateway choice. |
| Browser Web Speech preview | Optional | Explicit opt-in only. |
| Browser Whisper | Removed | No public worker or model download path. |
| Nextcloud WebDAV | Active | Used for file browsing/content import. |
| Patient handouts | Active | Parent-facing, note-derived, preferred-language draft. |
| Extension transfer | Active | ZIP export plus JSON/ZIP import preview. |
| Audio backups | Active | Failure recovery only. |
| TTS preview | Active | Depends on configured provider. |
| Clinical Assistant | Active | Grounded answers over MCP retrieval, with citations and source cards. |
| My Resources | Active | Personal teaching decks and documents, rendered by python-pptx / python-docx. |
| Deck vision review | Optional | Off by default; one pass, admin-configurable model. |
| Passwordless sign-in codes | Active | Emailed 6-digit code; password sign-in always stays available. |
| Personal notes | Active | Including dictation, with trash and restore. |
Troubleshooting
- Check browser console for frontend errors.
- Check
docker logs pediatric-ai-scribe -ffor backend errors. - Check
/api/healthfor service status. - Check provider credentials and model names before debugging UI state.
- For Nextcloud export failures, verify the URL, username, app password, and folder path.