All checks were successful
Verify and publish V2 container / build-and-push (push) Successful in 1m2s
Providers and pricing - Add a DeepSeek provider: thinking mode with low/high/max effort, reasoning_content replayed between tool steps, cache-hit usage, /models discovery and catalog prices. - Fix "does not support tool calling": a rejected forced tool_choice (DeepSeek thinking mode) now asks for the call in the prompt; only a genuine no-tools 400 is "unsupported". - Seven reasoning-effort levels (Off to Max) mapped per adapter. - Cached-input price per model, cache-write and DeepSeek off-peak aware cost estimates. - Built-in bge-small embedding model (transformers.js) as the semantic search default. Quizzes - Numeric (type-the-answer) questions: units ignored, optional ± tolerance; editor, runner, importer, templates and generation prompts. - Quiz start screen instead of showing answers; navigator ring no longer clipped and key legend removed; clock only for timed exams; 7-point letter grades. Assistant and generation - Assistant turns run on the server independently of the browser, with re-attach and an explicit stop; drafts tray shows generations in progress. - Per-chat model switcher, @-tagging of class materials, full-width assistant page and a smaller assistant button. - Editable generation instructions and built-in presets, separate from the chatbot import instructions. Other - Dialog footer padding, keyboard hints removed, copy buttons work over plain HTTP, class and folder shares include documents. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
83 lines
5.6 KiB
Markdown
83 lines
5.6 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. It is downloaded once (about 35 MB) from huggingface.co into
|
|
`DATA_DIR/models` on first use and costs nothing. `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.
|
|
|
|
## 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.
|