Martin Dvorak
3ea2cea100
Next.js 15 app that turns photos, PDFs, DOCX/PPTX and text into a swipeable feed of AI-generated activities (flashcards, multiple choice, true/false, fill-in-the-blank, matching, ordering, short answer) using the user's own Ollama models. Highlights: - All AI calls run in server route handlers; the browser never talks to Ollama. - Bring-your-own-key mode (default): the key lives only in the browser and is sent per-request; server, local-daemon and shared-key modes also supported. - Client-side document extraction (pdf.js, mammoth, jszip) with scanned-PDF page rendering for the vision model; notes stay in their original language. - ChatGPT-style shell: collapsible sidebar / mobile drawer, neutral token-based light + dark themes, folder organisation, PWA (manifest, SW, offline page). - Strict JSON validation with zod + auto-repair, rate limiting, and request guards (cross-origin, body-size, API-key sanitising). - setup.sh bootstraps deps, .env.local and a production build. Gitignore excludes .env*, the generated pdf.js worker and local scratch files.
14 lines
671 B
XML
14 lines
671 B
XML
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 64 64" width="64" height="64">
|
|
<defs>
|
|
<linearGradient id="frost" x1="0" y1="0" x2="1" y2="1">
|
|
<stop offset="0%" stop-color="#38bdf8" />
|
|
<stop offset="100%" stop-color="#0369a1" />
|
|
</linearGradient>
|
|
</defs>
|
|
<rect width="64" height="64" rx="16" fill="url(#frost)" />
|
|
<g stroke="#ffffff" stroke-width="3.4" stroke-linecap="round" fill="none">
|
|
<path d="M32 12v40M14.7 22l34.6 20M49.3 22 14.7 42" />
|
|
<path d="M32 20.5 26.8 15.3M32 20.5l5.2-5.2M32 43.5l-5.2 5.2M32 43.5l5.2 5.2" />
|
|
<path d="M20.7 27.5l-6.6-1.7M20.7 36.5l-6.6 1.7M43.3 27.5l6.6-1.7M43.3 36.5l6.6 1.7" />
|
|
</g>
|
|
</svg>
|