scotch-ajison/zimkb

Photo-in, diagnosis-out crop disease pipeline for Zimbabwe. Two-stage retrieval over a 281-condition knowledge base, Claude vision + reasoning. Zero-dependency BM25 core. # zimkb — wiring the Zimbabwe crop disease KB to Claude A small Python package that turns the knowledge base into a working photo-in, diagnosis-out pipeline. The core retrieval has **zero dependencies** and runs offline; only the Claude calls need the network. ```bash pip install anthropic # only needed for the diagnosis half export ANTHROPIC_API_KEY=sk-ant-... export ZIMKB_ROOT=./zimbabwe-crop-disease-kb python -m zimkb stats python -m zimkb search "grey rectangular lesions between the veins on lower leaves" --crop maize python -m zimkb diagnose photo.jpg --crop maize ``` ```python from zimkb import Diagnoser dx = Diagnoser() result = dx.diagnose_image("leaf.jpg", crop="maize", farmer_context="Pfumvudza plot, Mashonaland East, planted late November") print(result["farmer_message"]) ``` ## About the knowledge base this reads `zimkb` is the retrieval and diagnosis layer. The corpus it reads is a separate artifact and is **not included in this repository**. The knowledge base is 281 condition records across five crops — tobacco 65, bean 65, maize 58, wheat 49, sorghum 44 — pre-chunked into 1,850 passages. The category mix is a deliberate design decision rather than an accident of sourcing: disease 138, insect pest 55, **nutrient deficiency 45, abiotic disorder 33**, storage pest 6, parasitic weed 2, vertebrate pest 2. A third of it is not a pathogen at all, because a third of the wrong answers a vision model gives are pathogens that were really hunger, drought, frost, herbicide drift or lightning. Each record carries a forensic `visual_diagnosis` (lesion geometry, colour zoning, size in millimetres, margins and halos, texture, leaf surface, canopy position, distribution, progression), a `diagnostic_field_test`, a `look_alikes` differential layer, `vision_tags` and `farmer_query_phrases` for retrieval, `management` split into a chemical path and a smallholder path, `what_not_to_do`, a `safety` block, and a per-record `confidence` flag for where the un …