The import page now accepts PDF files in addition to TXT. Backend uses pdf-parse to extract text from uploaded PDFs before sending to AI for paragraph parsing. Co-Authored-By: Paperclip <noreply@paperclip.ing>
- Next.js 15 with App Router, TypeScript, Tailwind CSS - Directory structure per LegalAI architecture plan - Docker Compose setup (PostgreSQL 16, Meilisearch, App) - Drizzle ORM with base schema (tenants, users, norms, decisions) - AI abstraction layer structure (Vercel AI SDK) - Normen-Engine with Quellenrang hierarchy - Search abstraction layer - Auth placeholder (NextAuth.js) Co-Authored-By: Paperclip <noreply@paperclip.ing>
