Build bounded lexical indexes of supported course text and text PDFs

Aperta
  • Qualcosa non va?
#39 0 commenti 0 reazioni 0 assegnatari Vedi su GitHub

I maintainer di solito rispondono entro 1 giorno

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
5/5
Tempo stimato
Più di una settimana
Idoneità per principianti
35/100
Tipo di issue
Funzionalità
Chiarezza
Abbastanza chiara
Stato di attività
Attiva
Stack tecnologico
javascript, node.js
Ambito
backend, search

Direzione di ricerca

Read AGENTS.md and docs/PROJECT_CONTEXT.md, then review #38 and #37 because their contracts must land first. Start with src/content.js and the HTML, PDF, and folder readers; the issue also calls for a new index/chunk model. Use the synthetic MK/EN/SQ corpus to check bounded chunks, citations, access boundaries, extraction scope, and unsupported sources; follow the listed offline and runtime checks.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

area:backend area:docs priority:medium status:blocked type:feature

Part of #28 · Target: Retrieval / v0.4

Goal and scope

Index explicitly selected enrolled courses and supported documents with stable resource/page citations. Use Unicode-aware lexical tokens and bounded chunks; retain extraction scope, freshness and unsupported/partial sources.

Implementation starting points

new index/chunk model, src/content.js, HTML/PDF/folder readers. Follow AGENTS.md and docs/PROJECT_CONTEXT.md; reuse existing authorization, safe-error and synthetic-fixture patterns. New runtime dependencies need a documented reason.

Dependencies and readiness

Depends on #38, #37. Discuss the design before starting implementation; dependent contracts must land first.

Out of scope

No embeddings/vector service, OCR, external crawling or silently indexing every course.

Acceptance criteria and test plan

Synthetic MK/EN/SQ corpus tests cover PDF pages, HTML tables, duplicate sources, inaccessible/non-text material and input limits. Chunks cannot cross account boundaries; each hit traces to an accessible source/page and extraction version.

Run the relevant offline tests, npm run check and git diff --check; runtime changes also require npm test and npm audit. Report checks not run. No faculty credentials or private course material are required for a contribution.

Contributing

Comment here before starting so the maintainer can coordinate the approach and avoid duplicate work. Fork the repository, branch from master, and open a focused PR referencing this issue. No assignee or delivery deadline is set; required checks and review apply.

Lingua principale
JavaScript
Stelle
0
Fork
0
Merge medio
1h 25m
PR unite (30g)
13

Preparare l'ambiente

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di mahmutmft/courses-mcp

Tutte le issue di mahmutmft/courses-mcp

Issue simili

Altre issue su JavaScript

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.