feat: ingest cf-harvest knowledge base for companion planting, grow techniques, and medicinal uses #1

Open
opened 2026-06-08 08:35:42 -07:00 by pyr0ball · 0 comments
Owner

Summary

Waxwing will consume structured knowledge extracted by the cf-harvest pipeline (Circuit-Forge/circuitforge-orch#82). cf-harvest processes specialist gardening and cooking video content using Marlin-2B video captioning + Whisper STT + LLM classification to produce structured, labeled segments. The gardening domain taxonomy routes relevant classes to Waxwing.

What Waxwing receives from cf-harvest

Class label Data shape Waxwing feature it feeds
companion_planting PlantPairing (plant_a, plant_b, relationship, rationale, source_timestamp) Companion planting bed-level compatibility matrix
instruction GardenTask (action, subject, tools, timing, conditions) Grow calendar, care schedule generation
medicinal HerbalUse (plant, use, preparation, caution, source_timestamp) Medicinal herb index (with safety notes)
history_context HistoricalNote (subject, note, region, era) Variety notes, provenance context
soil_amendment SoilNote (condition, amendment, rationale) Soil composition and amendment suggestions

Design notes

  • cf-harvest routes are configured in the domain taxonomy YAML: config/domains/gardening.yaml. Waxwing does not need to know about the pipeline internals.
  • Waxwing defines its own KB schema. cf-harvest produces typed JSON; Waxwing maps it to its local SQLite store on ingest.
  • Source provenance (show title, timestamp, domain) is preserved on every record so users can trace a recommendation back to the clip it came from.
  • Medicinal entries require a safety_note_required: true flag in the taxonomy config. Waxwing must surface the caution text whenever displaying medicinal use data.

Scope for this issue

  • Define Waxwing KB schema for each incoming class (SQLite tables or JSON store)
  • Implement ingest endpoint or CLI command that accepts cf-harvest output JSON
  • Display companion planting data in the bed compatibility matrix UI
  • Display grow technique data in the care schedule and variety notes
  • Surface medicinal data with caution text prominently shown
  • Track source provenance per record
## Summary Waxwing will consume structured knowledge extracted by the cf-harvest pipeline (Circuit-Forge/circuitforge-orch#82). cf-harvest processes specialist gardening and cooking video content using Marlin-2B video captioning + Whisper STT + LLM classification to produce structured, labeled segments. The gardening domain taxonomy routes relevant classes to Waxwing. ## What Waxwing receives from cf-harvest | Class label | Data shape | Waxwing feature it feeds | |---|---|---| | `companion_planting` | PlantPairing (plant_a, plant_b, relationship, rationale, source_timestamp) | Companion planting bed-level compatibility matrix | | `instruction` | GardenTask (action, subject, tools, timing, conditions) | Grow calendar, care schedule generation | | `medicinal` | HerbalUse (plant, use, preparation, caution, source_timestamp) | Medicinal herb index (with safety notes) | | `history_context` | HistoricalNote (subject, note, region, era) | Variety notes, provenance context | | `soil_amendment` | SoilNote (condition, amendment, rationale) | Soil composition and amendment suggestions | ## Design notes - cf-harvest routes are configured in the domain taxonomy YAML: `config/domains/gardening.yaml`. Waxwing does not need to know about the pipeline internals. - Waxwing defines its own KB schema. cf-harvest produces typed JSON; Waxwing maps it to its local SQLite store on ingest. - Source provenance (show title, timestamp, domain) is preserved on every record so users can trace a recommendation back to the clip it came from. - Medicinal entries require a `safety_note_required: true` flag in the taxonomy config. Waxwing must surface the caution text whenever displaying medicinal use data. ## Scope for this issue - Define Waxwing KB schema for each incoming class (SQLite tables or JSON store) - Implement ingest endpoint or CLI command that accepts cf-harvest output JSON - Display companion planting data in the bed compatibility matrix UI - Display grow technique data in the care schedule and variety notes - Surface medicinal data with caution text prominently shown - Track source provenance per record ## Related - cf-harvest pipeline: Circuit-Forge/circuitforge-orch#82 - Kiwi consumer issue: Circuit-Forge/kiwi (cross-link TBD)
Sign in to join this conversation.
No labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference: Circuit-Forge/waxwing#1
No description provided.