AI_Agro_Support/config.yaml
Arsham Mirehvandi 099d1e0af9 Initial commit
2026-08-22 08:47:56 +02:00

91 lines
4.5 KiB
YAML

# ── LLM configuration ─────────────────────────────────────────────────────────
# Two independent profiles, one per pipeline stage. Each accepts the same keys:
# provider: openai | anthropic | gemini
# openai_model / anthropic_model / gemini_model / max_tokens / temperature
llm:
# Part_One: vector-search query synthesis (small structured JSON in,
# 1-2 short queries out). A lighter/cheaper model is sufficient here.
query_synthesis:
provider: gemini
openai_model: gpt-4o-mini
anthropic_model: claude-haiku-4-5
gemini_model: gemini-2.5-flash
max_tokens: 8192
temperature: 0.0
# Part_Two: the farmer-facing advisory generator. Receives the full
# json_for_advice_generation payload (weather, phenology, model output,
# applied treatments, product labels) and returns the structured advice
# JSON stored in the advice table. Needs a more capable model.
advice_generation:
provider: gemini
openai_model: gpt-4o
anthropic_model: claude-opus-4-5
gemini_model: gemini-2.5-pro
max_tokens: 16384
temperature: 0.0
# ── Crop-first worklist ────────────────────────────────────────────────────────
# `python -m pipeline batch` discovers jobs from this list: for every crop, it
# finds all fields growing it (AI_agrosupport_cmp_layers ⨝ an_colture) that also
# have a matching row in AI_agrosupport_agro_models for each listed disease's
# model_name, and runs the full single-field pipeline for every resulting
# (field, disease) pair. `disease` is the canonical English name used for the
# product prefilter, the vector search, and the advice/prompt lookup; it must
# exist in vocab/diseases.yaml. `model_name` is matched (case-insensitively)
# against AI_agrosupport_agro_models.anmod_model.
#
# Each crop-disease pair needs a matching prompt directory under
# prompts/advice/<crop>__<disease slug>/ (see prompts/README or the pipeline
# README for the exact slug rules); pairs without one fall back to
# prompts/advice/_default/ and are logged at startup.
crops:
- crop: grapevine
diseases:
- model_name: PERONOSPORA
disease: downy mildew
# ── Worklist filters ───────────────────────────────────────────────────────────
worklist:
# AI_agrosupport_agro_models.anmod_enabled is True for every model row in the
# current database; keep this on so a disabled model never generates advice.
require_enabled_model: true
# Restrict the batch to specific field IDs while testing; empty = no filter.
field_allowlist: []
# ── Concurrency & rate limiting ────────────────────────────────────────────────
# One "gemini" budget covers both direct LLM calls (query synthesis, advice
# generation) and Weaviate near_text search, because the ProductProfile
# collection is vectorised with text2vec-palm (gemini-embedding-001) using the
# same GEMINI_API_KEY — they share one quota.
concurrency:
workers: 8
limits:
sql: 6
gemini: 4
gemini_requests_per_minute: 60
# ── Retry policy for transient LLM / Weaviate / SQL failures ──────────────────
retry:
attempts: 3
initial_backoff_seconds: 2
max_backoff_seconds: 30
# ── Daily SLA ───────────────────────────────────────────────────────────────────
# The batch must not still be running after this local time; jobs not yet
# started by then are skipped (status skipped_deadline) rather than risking a
# late advisory. Schedule the run itself no earlier than ~07:00 so weather is
# fresh (see README).
schedule:
deadline: "09:00"
# ── Single-field debug mode (`python -m pipeline one`) ────────────────────────
# Not used by `batch`; kept for ad-hoc single-field runs and debugging.
field_id: 4012
disease_name: "PERONOSPORA"
# ── Vocabulary paths ──────────────────────────────────────────────────────────
vocab:
crops: vocab/crops.yaml
diseases: vocab/diseases.yaml