.env.example

@@ -54,10 +54,12 @@ AGENTIC_CHAT_MAX_ITERATIONS=6
 # OPENROUTER_APP_TITLE=ImageApi
 
 # ── AI Insights — sibling services (optional) ───────────────────────────
-# Apollo (places + face inference). Single Apollo deploys typically set
-# only APOLLO_API_BASE_URL and let the face client fall back to it.
+# 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=
 
@@ -80,6 +82,23 @@ FACE_DETECT_TIMEOUT_SEC=60
 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