42 lines
1.8 KiB
Bash
42 lines
1.8 KiB
Bash
# Brain of Reese — environment configuration
|
|
# Copy to `.env` and adjust: cp .env.example .env
|
|
# (`.env` is gitignored; never commit secrets.)
|
|
|
|
# --- App ---
|
|
BOR_ENVIRONMENT=development
|
|
# BOR_LOG_LEVEL=INFO
|
|
# BOR_STATIC_DIR=frontend # dev default; container sets /app/static
|
|
|
|
# --- Database (matches `podman compose` db service) ---
|
|
BOR_DATABASE_URL=postgresql+psycopg://reese:reese@localhost:5432/brain_of_reese
|
|
|
|
# --- LLM (self-hosted, OpenAI-compatible "aipi") ---
|
|
BOR_LLM_BASE_URL=https://aipi.reeseapps.com/v1
|
|
BOR_LLM_API_KEY= # falls back to $AIPI_KEY, then "not-needed"
|
|
BOR_LLM_CHAT_MODEL=turbo
|
|
BOR_LLM_EMBED_MODEL=embed
|
|
BOR_EMBEDDING_DIM=768 # verified 2026-08 via scripts/llm_probe.py
|
|
|
|
# --- RAG tuning ---
|
|
BOR_TOP_N_DOCS=2
|
|
BOR_RELEVANCE_THRESHOLD=0.62 # answer when best cosine >= this OR an FTS hit; else honest deflection
|
|
BOR_MAX_CONTEXT_CHARS=24000 # cap on total document text sent to the LLM
|
|
BOR_MAX_OUTPUT_TOKENS=32768 # max answer length in tokens (answers must not be cut off)
|
|
BOR_STEERING_MAX_CHARS=8000 # char budget for the <tuning> (steering notes) prompt section
|
|
BOR_CHUNK_TARGET_CHARS=2000
|
|
BOR_CHUNK_OVERLAP_CHARS=200
|
|
BOR_EMBED_BATCH_SIZE=16
|
|
|
|
# --- Hybrid retrieval (vector + Postgres FTS, RRF-fused) ---
|
|
BOR_HYBRID_VECTOR_CANDIDATES=100 # cosine list width for the fusion
|
|
BOR_HYBRID_LEXICAL_CANDIDATES=30 # FTS list width for the fusion
|
|
BOR_RRF_K=60 # Reciprocal Rank Fusion damping constant
|
|
|
|
# --- Import scope (A9 formats; may only narrow, never widen) ---
|
|
# BOR_IMPORT_EXTENSIONS=md,markdown,txt,yaml,yml,json,py
|
|
# BOR_SUGGESTIONS=["How is my Kubernetes cluster set up?"] # JSON list of onboarding chips
|
|
|
|
# --- Debugging (0/1 — 1 enables attach-on-demand debugpy on port 5678) ---
|
|
DEBUGPY=0
|
|
# DEBUGPY_PORT=5678
|