category: reference
tags: [tasks, semantic-search, faiss, multi-tenant]
last_updated: 2026-03-20
confidence: high

Semantic Search Multi-Tenant — IMPLEMENTED

Solution (2026-03-20)

All multi-tenant issues resolved. FAISS backend with BackendRegistry provides per-wiki isolation.

Implementation

• BackendRegistry manages per-wiki FAISS backends with lazy initialization
• Per-wiki FAISS indexes at /srv/data/faiss/{slug}/ — natural isolation, no slug-prefix hacking
• Lifecycle hooks (page_saved/page_deleted/page_renamed) via HookListener replace the single-tenant sync thread
• reindex_all is per-wiki scoped — reindexing one wiki does not affect others
• Auto-index on first access — existing pages are back-filled when a wiki is first accessed
• ONNX MiniLM-L6-v2 embeddings (ChromaDB bundled) — no model download issues
• ChromaDB deprecated and disabled

Original problems (all resolved)

1. One shared ChromaDB collection — Replaced by per-wiki FAISS directories.
2. One sync thread tied to default wiki — Replaced by per-request lifecycle hooks.
3. reindex_all wipes everything — Now per-wiki scoped.
4. No auto-index for new wikis — Auto-reindex on first wiki access.
5. Embedding model download — ONNX model bundled, no download needed.

Related

• Tasks/Semantic_Search_Architecture — overall architecture
• Dev/Proxmox_CPU_Type — numpy X86_V2 issue (workaround in place)
• Design/Async_Embedding_Pipeline — original FAISS + MiniLM design (AWS, archived)