All checks were successful
Verify and publish V2 container / build-and-push (push) Successful in 30s
Generation - Every quiz is NCLEX style; "Practice exam" writes 50 questions. - Calculation questions only when the material involves calculations (max 5 per exam). - Broad topics: the class's topics are listed in the prompt, a quick grouping call maps narrow labels onto broad ones, and leftover variants are merged. - Exact select-all count per batch; option order shuffled. - Python check: at most 3 runs, fixed problems count as passed, cosmetic remarks ignored. Assistant - Text, tool steps and cards appear in the order they happen, with paragraph breaks between steps. - Optional thinking box: fixed height, follows the newest text, can be scrolled back. - "+" opens a material picker listing recent items; items can be dragged in from class pages; shorter placeholder. MCP servers - Streamable HTTP client; encrypted headers. - Per-server instructions and switches for chat, Explain, generation and the quiz check. - Settings UI. Share links - Optional "Explain this" and "Ask about this material" per link, off by default. - Items are loaded on the server and checked against the share; no tools; rate-limited. - Migration 4 stores the switches. Study and documents - Standard flashcard mode (optionally repeat missed cards until known) next to spaced repetition. - Streak visuals restyled in the app palette. - Side by side / Original document views, with sandboxed previews of Word and PowerPoint files. Other - Built-in embedding model baked into the image; sharp stubbed if it cannot load; real load error shown in Settings. - Python runner blocks network and process modules in JavaScript too. - "View questions and answers" removed from the quiz start screen. - Docs updated. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
159 lines
9.9 KiB
Markdown
159 lines
9.9 KiB
Markdown
# AI connections and verification
|
|
|
|
Settings → AI manages provider connections and model routing. Add a connection, test it,
|
|
discover models where supported (or add a custom model), enable models and select defaults
|
|
for generation, chat, explanations and vision. Output limits, capabilities, pricing and
|
|
reasoning settings can be edited per model. Catalog prices are estimates, not billing records.
|
|
|
|
Adapters use OpenAI Responses, Anthropic Messages, Gemini generateContent, DeepSeek and
|
|
OpenAI-compatible Chat Completions, and Ollama's native chat API.
|
|
|
|
Reasoning effort has seven levels (Off, Minimal, Low, Medium, High, Extra high, Max); each
|
|
adapter maps them onto the nearest value its API accepts. DeepSeek accepts low / high / max
|
|
and turns thinking off at "Off". DeepSeek rejects forced tool calls in thinking mode, so
|
|
structured generation keeps thinking on and asks for the tool call in the prompt; answer keys
|
|
were noticeably less reliable with thinking off. Its `reasoning_content` is replayed between
|
|
tool steps, as the API requires.
|
|
|
|
Cost estimates split input into fresh, cache-hit and cache-write tokens. A model's "Cached
|
|
input price" is used when set; otherwise the provider's published discount applies (10% of
|
|
input for GPT-5+, Claude and Gemini; DeepSeek's catalog cache-hit price). DeepSeek's
|
|
off-peak half price is applied by time of call. Configure the endpoint as shown in Settings.
|
|
Local models are reached **from the server/container**: `localhost` inside Docker is the
|
|
container itself, not your workstation or Unraid host. Use a reachable LAN address instead.
|
|
|
|
Keys are encrypted with AES-256-GCM in SQLite using `/data/secret.key` or `APP_SECRET`.
|
|
Only the server decrypts them. Keep the key with backups; changing it breaks decryption.
|
|
Documents are sent to the selected provider when you request AI processing; extraction and
|
|
full-text indexing otherwise run locally. Review generated nursing content and source
|
|
references before using it for study.
|
|
|
|
## Reading scanned PDFs (OCR)
|
|
|
|
A PDF with little selectable text is read by the "Vision and OCR" model, which must accept
|
|
PDFs (OpenAI, Anthropic, Gemini; OpenAI-compatible servers when the model is marked "PDF").
|
|
Long files are split with pdf-lib into batches of 8 pages (smaller if a batch exceeds 24 MB)
|
|
and sent one batch per request, so there is no whole-file size cap. Each batch keeps its real
|
|
page numbers for citations. Finished batches are cached beside the upload
|
|
(`uploads/<file>.ocr.json`), so a restart or a failed batch does not repeat paid work; "Read
|
|
with AI" on the document forces a fresh read. A batch that fails twice is skipped with a
|
|
warning on the document. At most 600 pages are read per file.
|
|
|
|
## Semantic search
|
|
|
|
Settings → AI → Semantic search chooses an embeddings provider and model (suggested:
|
|
OpenAI `text-embedding-3-small`, Gemini `gemini-embedding-001`, Ollama `nomic-embed-text`;
|
|
Anthropic and DeepSeek have no embeddings API). Until something else is chosen, the built-in
|
|
model is used: BAAI bge-small-en-v1.5 (8-bit ONNX, 384 dimensions) running on the server's CPU
|
|
through transformers.js. The Docker image ships the model in `/app/models` (`LOCAL_MODELS_DIR`),
|
|
so it works without internet access; outside Docker it is downloaded once (about 35 MB) from
|
|
huggingface.co into `DATA_DIR/models`. It costs nothing. If the model cannot load, Settings shows
|
|
the actual error. `LOCAL_EMBEDDINGS=off` disables the default. Every document passage is embedded in the background and
|
|
stored as a vector in SQLite (`chunk_vectors`). Search, the assistant's document search and
|
|
focused generation then merge keyword (FTS5) and meaning-based rankings with reciprocal-rank
|
|
fusion, so exact terms still match while paraphrased questions find the right passage. If the
|
|
embedding provider fails, search silently falls back to keywords. Changing the model clears
|
|
and rebuilds the index. Costs appear under Usage as "semantic indexing" / "semantic search".
|
|
Quiz questions, flashcards and notes are still searched by keyword.
|
|
|
|
## Python sandbox and the quiz check
|
|
|
|
The assistant has a `run_python` tool, and generated quizzes are checked with it. Code runs in
|
|
Pyodide (CPython compiled to WebAssembly) inside a separate Node process started with
|
|
`--permission`. It can read only the Pyodide files, gets an empty environment, cannot reach
|
|
the network or start processes (blocked in Python and again in JavaScript), and has no access
|
|
to `/data`. One warm process is reused and recycled every 50 runs; a run that times out kills
|
|
it.
|
|
|
|
After a quiz is generated (unless "Check answers" is off), the generation model gets the draft
|
|
as Python data plus the request (count, select-all share, calculation allowance). In at most
|
|
three Python runs it checks the count, question types, number of correct answers per type,
|
|
numeric answers, the calculation allowance and topic breadth, then reports with `submit_review`.
|
|
Fixes are applied only when the question stays valid. Remarks the model files as cosmetic or
|
|
informational (answer position, quotes) are not counted as failed checks; answer order is
|
|
shuffled whenever a quiz is taken.
|
|
|
|
## Quiz generation rules
|
|
|
|
Every quiz is NCLEX style. "Practice exam" writes 50 questions. Calculation (numeric) questions
|
|
are written only when the source material involves calculations (dosage, drip rates, mg/kg,
|
|
intake and output...): up to 5 in an exam, about one in ten otherwise, none when the material
|
|
has no calculations. Topics are kept broad ("Stroke", not "Right hemisphere stroke"): the
|
|
prompt lists the class's existing topics, and narrower labels that contain an existing one are
|
|
merged into it after generation.
|
|
|
|
## MCP servers
|
|
|
|
Settings → AI → MCP servers connects Model Context Protocol servers over Streamable HTTP
|
|
(JSON-RPC over POST, answered as JSON or SSE). Headers (usually an `Authorization` token) are
|
|
encrypted like API keys and never returned to the browser. "Test and list tools" connects
|
|
afresh and lists the tools.
|
|
|
|
Each server has:
|
|
|
|
- **When to use it**: your instructions, added to the model's prompt next to the server's tools.
|
|
- **Where it can be used**: Assistant chat, Explain this, Generating material (quizzes,
|
|
flashcards, study guides) and Quiz check, each switched separately. New servers are on for
|
|
chat and Explain only.
|
|
|
|
Tools are offered as `mcp_<server>__<tool>`, at most 48 per request. A server that cannot be
|
|
reached is skipped for that request, and the assistant is told it is unavailable. During
|
|
generation the model may make up to four rounds of tool calls before it must submit its
|
|
answer; the quiz check allows four external calls. Tool output is treated as data, not
|
|
instructions. MCP tools are never offered on share links.
|
|
|
|
## AI on share links
|
|
|
|
Each share link has two switches, both off by default:
|
|
|
|
- **Explain this**: visitors can ask for an explanation of a shared question or flashcard.
|
|
The request names the item by id; the server loads its text (and checks it belongs to the
|
|
share), so a link cannot be used to run arbitrary prompts.
|
|
- **Ask about this material**: a chat that answers from the shared item (or, for a shared
|
|
class or folder, the item being viewed, the list of materials and passages from its
|
|
documents). It has no tools, cannot read the rest of the library and saves nothing.
|
|
|
|
Both use the owner's models and keys, and are rate-limited to 20 requests per visitor per 10
|
|
minutes and 150 per link per hour. They show only when an AI model is configured.
|
|
|
|
## Original documents
|
|
|
|
A document's page offers Extracted text, Side by side and Original. PDFs and images show the
|
|
file itself. Word and PowerPoint files are shown as a generated page
|
|
(`GET /api/documents/:id/preview`): the document's content, or each slide's text, pictures and
|
|
notes. Pictures are inlined; formats a browser cannot show (EMF/WMF) are listed as omitted. The
|
|
page is served with `default-src 'none'; sandbox`, so it cannot run scripts or load anything.
|
|
|
|
Pictures inside Word and PowerPoint files are **not read** for search or generation: only
|
|
their text, tables and speaker notes are extracted. PDFs are read by OCR only when they have
|
|
almost no selectable text, so pictures inside a text PDF are not read either. Material that
|
|
lives only in pictures needs to be in the text, or uploaded as an image or scanned PDF and
|
|
read with AI.
|
|
|
|
## ChatGPT account investigation (2026-11-11)
|
|
|
|
The official [Sign in with ChatGPT quickstart](https://developers.openai.com/siwc/quickstart)
|
|
now describes plan access for eligible integrations. The
|
|
[official implementation guide](https://developers.openai.com/cookbook/articles/sign-in-with-chatgpt)
|
|
distinguishes local personal/open-source tools from remotely hosted apps, which require
|
|
access approval. This Unraid/reverse-proxy deployment is a hosted web application; eligibility
|
|
for its private client has not been established. Therefore V2 currently uses conventional API
|
|
connections, and does not advertise ChatGPT plan access or reuse another client's credentials.
|
|
|
|
To add this later, obtain the appropriate approval/registration and implement the documented
|
|
OAuth/PKCE flow, verified identity, encrypted refresh tokens, approved callbacks and plan-scoped
|
|
model discovery. Keep this separate from the single administrator's local login. Never copy
|
|
ChatGPT browser session tokens or a Codex client's registration/credentials into Study Desk.
|
|
|
|
## What has been tested
|
|
|
|
Mock protocol tests cover request translation, streams, tools, usage and error handling.
|
|
Integration tests use a local OpenAI-compatible mock to generate/edit/save drafts, search
|
|
documents with citations and exercise confirmed assistant actions, batched OCR of a 20-page
|
|
scanned PDF and semantic indexing/search (the mock returns deterministic word-hash vectors).
|
|
They cost no API credits.
|
|
No successful real-provider inference or real ChatGPT OAuth authorization is claimed.
|
|
|
|
For manual local AI testing: `npx tsx scripts/mock-ai.ts` starts a scripted mock at
|
|
`http://localhost:4010/v1` with key `mock-key`. It returns clearly labeled synthetic material.
|
|
Do not use mock output as nursing guidance. Stop the mock and remove its connection after QA.
|