Cameron CordesandClaude Opus 5.5
09b9e87396
README, CLAUDE.md and .env.example now point at llm.toml for LLM settings (OPENROUTER_API_KEY stays in env) and describe the legacy env override window, the discovered picker and the startup cross-check. ADR-0003 records the move and amends ADR-0002's deployment-config home; CONTEXT.md's Deployment config / Hard default entries follow. Source comments and the "set LLAMA_SWAP_URL" error strings name the llm.toml keys. Also fixes README's AGENTIC_MAX_ITERATIONS default (10 -> 12, what the code uses). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
131 lines
6.9 KiB
Bash
131 lines
6.9 KiB
Bash
# ImageApi configuration template. Copy to `.env` and fill in for your
|
|
# deploy. Comments mirror the canonical docs in CLAUDE.md — see there
|
|
# for the full picture (especially the AI-Insights / Apollo / face
|
|
# integration sections).
|
|
|
|
# ── Required ────────────────────────────────────────────────────────────
|
|
DATABASE_URL=./database.db
|
|
BASE_PATH=/path/to/media
|
|
THUMBNAILS=/path/to/thumbnails
|
|
VIDEO_PATH=/path/to/video/hls
|
|
GIFS_DIRECTORY=/path/to/gifs
|
|
PREVIEW_CLIPS_DIRECTORY=/path/to/preview-clips
|
|
BIND_URL=0.0.0.0:8080
|
|
# Secondary loopback listener (default localhost:8088). Empty = don't bind it
|
|
# (e.g. a second instance next to one that already owns 8088).
|
|
# LOCAL_BIND_URL=localhost:8088
|
|
CORS_ALLOWED_ORIGINS=http://localhost:3000
|
|
SECRET_KEY=replace-me-with-a-long-random-secret
|
|
RUST_LOG=info
|
|
|
|
# ── File watching ───────────────────────────────────────────────────────
|
|
# Quick scan = recently-modified-files only; full scan = comprehensive walk.
|
|
WATCH_QUICK_INTERVAL_SECONDS=60
|
|
WATCH_FULL_INTERVAL_SECONDS=3600
|
|
# Comma-separated path prefixes / component names to skip in /memories
|
|
# AND in face detection (e.g. @eaDir, .thumbnails, /private).
|
|
EXCLUDED_DIRS=
|
|
|
|
# ── Video / HLS ─────────────────────────────────────────────────────────
|
|
HLS_CONCURRENCY=2
|
|
HLS_TIMEOUT_SECONDS=900
|
|
# Sources above this bitrate (bits/s) or 1080p are transcoded instead of
|
|
# stream-copied, so HLS segments stay small enough to start and seek quickly.
|
|
HLS_COPY_MAX_BITRATE=20000000
|
|
PLAYLIST_CLEANUP_INTERVAL_SECONDS=86400
|
|
|
|
# ── Telemetry ────────────────────────────────────────────────────────────
|
|
# Span + log export over OTLP in any build when set (unset = nothing
|
|
# exported). Logs carry trace ids, so SigNoz links them to traces.
|
|
# RUST_LOG also gates export: keep it at info or debug.
|
|
# OTLP_OTLS_ENDPOINT=http://localhost:4317
|
|
|
|
# ── AI Insights — LLMs ──────────────────────────────────────────────────
|
|
# Models, backends, the embedding contract, TTS and agentic caps live in
|
|
# llm.toml — copy llm.example.toml. Only the secret stays here.
|
|
# LLM_CONFIG_PATH=./llm.toml
|
|
# Enables the hybrid backend (chat via OpenRouter; photos stay local).
|
|
# OPENROUTER_API_KEY=sk-or-...
|
|
#
|
|
# The old OLLAMA_* / LLAMA_SWAP_* / OPENROUTER_* / LLM_BACKEND / EMBED* /
|
|
# AGENTIC_* / UNIFIED_SEARCH_MODEL vars still override llm.toml for now, with a
|
|
# startup deprecation warning. Move them into llm.toml.
|
|
|
|
# ── AI Insights — sibling services (optional) ───────────────────────────
|
|
# Apollo (places, face inference, CLIP encoders). Single-Apollo deploys
|
|
# typically set only APOLLO_API_BASE_URL and let the face + CLIP
|
|
# clients fall back to it.
|
|
# APOLLO_API_BASE_URL=http://apollo.lan:8000
|
|
# APOLLO_FACE_API_BASE_URL=http://apollo.lan:8000
|
|
# APOLLO_CLIP_API_BASE_URL=http://apollo.lan:8000
|
|
# SMS_API_URL=http://localhost:8000
|
|
# SMS_API_TOKEN=
|
|
|
|
# Display name used in agentic prompts when the LLM refers to "you".
|
|
USER_NAME=
|
|
|
|
# ── Face detection (Phase 3+) ───────────────────────────────────────────
|
|
# Cosine-sim floor for auto-binding a detected face to an existing
|
|
# same-named person on detection. 0.4 ≈ moderate-confidence match.
|
|
FACE_AUTOBIND_MIN_COS=0.4
|
|
# Per-scan-tick fan-out into Apollo's detect endpoint. Apollo's GPU
|
|
# pool serializes server-side; this just overlaps file-IO with
|
|
# inference RTT.
|
|
FACE_DETECT_CONCURRENCY=8
|
|
# Per-detect HTTP timeout. CPU-only Apollo deploys may need higher.
|
|
FACE_DETECT_TIMEOUT_SEC=60
|
|
# Per-tick caps on the two backlog drains (independent of WATCH_*
|
|
# quick / full scans). Tune up if you have a large unscanned backlog
|
|
# and want it to clear faster; tune down if Apollo is overloaded.
|
|
FACE_BACKLOG_MAX_PER_TICK=64
|
|
FACE_HASH_BACKFILL_MAX_PER_TICK=2000
|
|
|
|
# ── CLIP semantic photo search ──────────────────────────────────────────
|
|
# ImageApi calls Apollo's /api/internal/clip/{encode_image,encode_text}
|
|
# to populate per-photo embeddings during the watcher's backlog drain
|
|
# and to encode user queries at /photos/search time. Disabled when
|
|
# neither APOLLO_CLIP_API_BASE_URL nor APOLLO_API_BASE_URL is set.
|
|
#
|
|
# Per-watcher-tick cap on the encode drain. Default 32 ≈ ~1 photo/sec
|
|
# on CPU, ~30 photos/sec on a single-GPU host (Apollo's threadpool
|
|
# is 1 on CUDA, so concurrency is bounded server-side regardless of
|
|
# our setting). Bump on a fresh deploy to clear the backlog faster.
|
|
CLIP_BACKLOG_MAX_PER_TICK=32
|
|
# Client-side parallel encode calls per drain pass. Apollo's GPU pool
|
|
# serializes server-side; this just overlaps file-IO with inference.
|
|
CLIP_ENCODE_CONCURRENCY=4
|
|
# Per-encode HTTP timeout. CPU-only Apollo deploys may need higher.
|
|
CLIP_REQUEST_TIMEOUT_SEC=60
|
|
|
|
# ── RAG / search ────────────────────────────────────────────────────────
|
|
# Set to `1` to enable cross-encoder reranking on /search results.
|
|
SEARCH_RAG_RERANK=0
|
|
|
|
# ── Nightly reel pre-generation (Phase 3+) ──────────────────────────────
|
|
# Set to `1` to enable the scheduler. Disabled by default.
|
|
# REEL_PREGEN_ENABLED=1
|
|
# Hour (0-23) when the nightly batch fires. Default 3 AM.
|
|
# REEL_PREGEN_HOUR=3
|
|
# Day of week for weekly reels (0=Sun, 1=Mon, …). Default Monday.
|
|
# REEL_PREGEN_WEEK_DOW=1
|
|
# Timezone offset in minutes from UTC (e.g., -480 = PST). Defaults to
|
|
# the server's local timezone.
|
|
# REEL_PREGEN_TZ_OFFSET_MINUTES=
|
|
# Fixed timezone offset — overrides auto-detect to avoid DST shifts.
|
|
# When set, both the DB fallback and env fallback use this value.
|
|
# REEL_PREGEN_TZ_FIXED_MINUTES=-480
|
|
# Voice ID for narration (e.g., "grandma"). Falls back to the value
|
|
# stored in the user_ai_prefs DB row when set.
|
|
# REEL_PREGEN_VOICE=
|
|
# Library filter: a library id (e.g. "1") or "all" for every library.
|
|
# REEL_PREGEN_LIBRARY=all
|
|
# Max agentic tool iterations for pre-gen scripter. Default 8.
|
|
# REEL_PREGEN_MAX_TOOL_ITERS=8
|
|
#
|
|
# On-disk reel cache sweep (runs every 24h, independent of pre-gen). Removes
|
|
# reel MP4s with no ledger row + no live job that are older than the max age —
|
|
# i.e. the on-demand cache, which otherwise grows forever. Set to 0 to disable.
|
|
# REEL_CACHE_SWEEP_ENABLED=1
|
|
# Age (days) before an unreferenced reel MP4 is swept. Default 7.
|
|
# REEL_CACHE_MAX_AGE_DAYS=7
|