From 903531220883b51fb067554e08b96493368c65d7 Mon Sep 17 00:00:00 2001
From: Codex <codex@local>
Date: Fri, 18 Sep 2026 00:32:21 -0700
Subject: [PATCH] use supported TEI 1.9 options

---
 servers/unraid/hindsight-retrieval/README.md  |  4 ++--
 .../unraid/hindsight-retrieval/compose.yaml   | 22 -------------------
 2 files changed, 2 insertions(+), 24 deletions(-)

diff --git a/servers/unraid/hindsight-retrieval/README.md b/servers/unraid/hindsight-retrieval/README.md
index a59fc59..314173b 100644
--- a/servers/unraid/hindsight-retrieval/README.md
+++ b/servers/unraid/hindsight-retrieval/README.md
@@ -8,8 +8,8 @@ Arcane-managed TEI services on unRaid GPU0 for the production Hindsight VM.
 | Reranker | `Alibaba-NLP/gte-multilingual-reranker-base` | `http://192.168.50.100:18084` |
 
 The BGE-M3 cache is reused from the retired unRaid Hindsight stack. The GTE
-reranker has a separate cache. Both services use physical GPU0 and conservative
-TEI concurrency/tokenizer settings.
+reranker has a separate cache. Both services use physical GPU0 and the defaults
+provided by the pinned TEI 1.9 image.
 
 Hindsight uses the local embedding directly. Hindsight has no native embedding
 provider fallback chain, so OpenRouter BGE-M3 remains a manual rollback rather
diff --git a/servers/unraid/hindsight-retrieval/compose.yaml b/servers/unraid/hindsight-retrieval/compose.yaml
index 43cd514..9c735e2 100644
--- a/servers/unraid/hindsight-retrieval/compose.yaml
+++ b/servers/unraid/hindsight-retrieval/compose.yaml
@@ -9,17 +9,6 @@ services:
       - BAAI/bge-m3
       - --dtype
       - float16
-      - --max-input-length
-      - "8192"
-      - --max-client-batch-size
-      - "32"
-      - --max-concurrent-requests
-      - "64"
-      - --max-batch-tokens
-      - "8192"
-      - --tokenization-workers
-      - "4"
-      - --auto-truncate
     environment:
       HF_HUB_CACHE: /data
       TZ: America/Los_Angeles
@@ -55,17 +44,6 @@ services:
       - Alibaba-NLP/gte-multilingual-reranker-base
       - --dtype
       - float16
-      - --max-input-length
-      - "8192"
-      - --max-client-batch-size
-      - "32"
-      - --max-concurrent-requests
-      - "32"
-      - --max-batch-tokens
-      - "8192"
-      - --tokenization-workers
-      - "4"
-      - --auto-truncate
     environment:
       HF_HUB_CACHE: /data
       TZ: America/Los_Angeles