- Q16 → image bytes stay in their source (Memos / Nextcloud / Obsidian);
Phase-3.2 backfill fetches by media_uri. Zero copy.
- Q17 → Immich stays out-of-band; Nexa does not call Immich's smart-search.
- New Q18 carries forward the unresolved sub-question of whether SAIA's
LiteLLM gateway already proxies an embedding model — a 1-line check that
could let us skip TEI in 3.1.
Decision (Q15 resolved): start with text-only via TEI + bge-m3 in Phase 3.1,
prepare data shapes so Phase 3.2 (visual collection via infinity + jina-clip-v2)
is a pure additive operation — no rename, no schema migration, no n8n rewiring.
Concretely:
- Qdrant collection renamed nexa_knowledge → nexa_knowledge_text (1024-dim
for bge-m3) with modality-aware payload (modality, source_type, media_uri,
graph_iri, content_hash, context). Visual placeholder schema committed
alongside (qdrant_schema_visual.json, 768-dim, jina-clip-v2).
- Image attachments captured in 3.1 are recorded in GraphDB as nexa:Note with
nexa:modality "image" + nexa:pendingVisualIndex true; the 3.2 backfill
workflow picks them up and embeds. No data lost between phases — the queue
is the GraphDB itself.
- RDF schema (docs/08) gains nexa:modality, nexa:mediaUri,
nexa:vectorCollection, nexa:pendingVisualIndex from day one.
- docs/02 roadmap split: 3.1 = text RAG (Path A), 3.2 = visual collection
(Path C), 3.4 = Ontotext GraphDB.
- docs/09 grows a "Phase add-on: visual collection (Phase 3.2)" section with
the TEI→infinity swap, second collection create, LiteLLM second model
registration, and the SPARQL-driven backfill query.
- New open questions: Q16 (queue ergonomics + does SAIA already proxy an
embed model?), Q17 (reuse Immich's CLIP for photo-library queries?).
- docs/03 + CLAUDE.md updated so future runs use the new collection names
and don't re-decide the staging.
- Q1 → Ontotext GraphDB (SPARQL). docs/08 fully rewritten with RDF schema,
example SPARQL queries (transitive deps via property paths, time-windowed
topic counts, cross-pillar joins via nexa:vectorId).
- Q2 → reuse qdrant_scientific with nexa_* collection prefix; docs/09 step 2
now points there explicitly.
- Q3 → no OpenAI embeddings. Self-host on the docker host. Use TEI
(HuggingFace text-embeddings-inference) — single Rust binary, ~500 MB image,
OpenAI-compatible — instead of Ollama, since we only need embeddings.
- docs/09 Phase-3.4 add-on simplified to a single Ontotext compose snippet
(Neo4j option dropped) plus repo creation curl.
- docs/11 Q3 marked resolved; new Q15 picks the model (bge-m3 vs nomic-embed)
and adds the open question of whether SAIA already proxies an embedding
model that would let us skip TEI entirely.
- docs/03 + CLAUDE.md updated with the new decisions so future runs don't
re-litigate.
Claude