Annie

Ingestion + Knowledge Infrastructure

corpora → chunker → embedder → ChromaDB → metaindex.

Ingestion + Knowledge Infrastructure (v2026-09-30T101003Z-5e473105f4) 2026-09-30 | corpora → chunker → embedder → ChromaDB → metaindex. 1 - APPROVAL PROCESS - Document approval and ingestion corpus_ingest.py approved doc has a URL? fetch looks like a doc? write .md 1. Check document approval 2. Verify URL presence 3. Fetch document content 4. Validate document type 5. Write document to sour… 6. Trigger existing inges… 7. Confirm corpus growth Example Outcome JSON {"doc_id": "12345", "title": "Sample Document", "status": "ingested", "detail": "", "chars": 1234, "path": "knowledge_ba… Domain Configuration JSON {"id": "ai_agentic", "name": "AI and Agentic Systems", "description": "Multi-agent architectures, LLM engineering, RAG p… The ingestion process strictly follows the approval workflow, ensuring only approved documents are processed. Legend actor = initiates work · process = code path · store = state on disk · bus = durable queue · dashed = separate process cyan = request flow · pink = state read/write · dashed green = pull / return path · red = refusal As of 2026-09-30 10:10 UTC, from commit 5e47310

Provenance

This drawing is generated, not drawn. It is rebuilt from the source files below, so when they change the picture changes — a diagram here cannot quietly describe a system that no longer works this way.

Owner
Annie
Slug
ingestion-knowledge
Rendered
2026-09-30T101003Z
From commit
5e473105f4
Updated
30 Sep 2026, 10:10 UTC
Sources at
5e47310
Watches
3 paths
  • daemon/src/corpus_ingest.py
  • knowledge-infra
  • corpora