T

Claude a1e14c64c3 Apply Q1–Q3 decisions: GraphDB/SPARQL, reuse Qdrant, self-host embeddings via TEI

- 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.

2026-05-04 21:26:08 +00:00

docs

Apply Q1–Q3 decisions: GraphDB/SPARQL, reuse Qdrant, self-host embeddings via TEI

2026-05-04 21:26:08 +00:00

nexa-core

Reorganize /docs with numbered TOC; deployment rewrite for actual homelab

2026-05-04 21:18:28 +00:00

CLAUDE.md

Apply Q1–Q3 decisions: GraphDB/SPARQL, reuse Qdrant, self-host embeddings via TEI

2026-05-04 21:26:08 +00:00

README.md

Reorganize /docs with numbered TOC; deployment rewrite for actual homelab

2026-05-04 21:18:28 +00:00

README.md

nexa

Neural Nexus for Information & Automation — central nervous system for a personal IT setup.

Memos = voice & ear · n8n = reflexes · SAIA (LiteLLM) = brain · Qdrant (+ optional graph DB) = memory · Nextcloud = hands.

Start here

📖 docs/index.md — TOC, reading paths, repo layout.

Repository layout

nexa/
├── docs/        ← all documentation, numbered for reading order
└── nexa-core/   ← runtime: n8n workflows, configs, prompts, scripts