# =============================================================================
# DiDi LOT 1 — Local GPU stack configuration
# Copy to `.env` (deploy.sh face asta automat daca lipseste) si ajusteaza.
# =============================================================================

# Host IP folosit in EXTERNAL_URL-uri si in comenzile de test.
# Lasa GOL -> deploy.sh detecteaza automat IP-ul principal si il scrie aici.
HOST_IP=

# --- Brain / Atomic / Postgres -----------------------------------------------
# Parola e folosita de postgres, atomic-server SI brain-api (trebuie sa fie una singura).
POSTGRES_PASSWORD=brain_local_dev
# Token API atomic-server. Lasa GOL -> deploy.sh il genereaza automat
# (atomic-server token create) si il scrie inapoi aici.
ATOMIC_TOKEN=

# --- Gateway -----------------------------------------------------------------
GATEWAY_API_TOKEN=didi-local-dev-token-123

# --- Dashboard ---------------------------------------------------------------
DASHBOARD_DB_USER=dashboard
DASHBOARD_DB_PASSWORD=devpass123
DASHBOARD_DB_NAME=dashboard
# staging=true -> bypass Keycloak (intri direct in UI). Scoate in productie.
DASHBOARD_STAGING_MODE=true

# --- Modele (nume servite; nu schimba fara motiv) ----------------------------
LLM_MODEL=Qwen/Qwen3.5-35B-A3B
LLM_SERVED_NAME=qwen3.5
EMB_MODEL=BAAI/bge-m3
RERANK_MODEL=BAAI/bge-reranker-v2-m3
WHISPER_MODEL=large-v3-turbo
WHISPER_REPO=mobiuslabsgmbh/faster-whisper-large-v3-turbo
BUSTER_MODEL=l8cv/BusterX_plusplus
# Extractoare (NER) — GLiNER + backbone-ul lui
NER_MODEL=urchade/gliner_multi-v2.1
NER_BACKBONE=microsoft/mdeberta-v3-base

# Zona LOCALA unica pentru TOATE modelele (un folder per model, format HF cache:
# models--<org>--<name>/). Toate containerele (Qwen/BusterX/bge/whisper/GLiNER)
# sunt servite OFFLINE de aici. Lasa GOL -> deploy.sh foloseste ai_platform/models.
# Ce lipseste se descarca automat din HF in acest director (offline-first).
MODELS_DIR=