From 4f6cc4812ede99771af53b624739b20c2f2b0e06 Mon Sep 17 00:00:00 2001 From: wangwei Date: Thu, 23 Jul 2026 14:09:33 +0800 Subject: [PATCH] revert: disable Cross-Encoder reranker Live verification via POST /status/models/ping (after confirming the gateway itself is reachable -- embedding role succeeded, 1.5s latency) shows http://6.86.80.4:30080/v1/rerank returns a fast, reproducible '503 Service Unavailable' -- not a timeout/fluke. The gateway's model catalog (19 models: deepseek-*, glm-*, kimi-*, qwen3*, text-embedding-v3/4) contains no cross-encoder/rerank-capable model, confirming no reranker service is deployed behind this gateway today. Leaving RERANKER_ENABLED=true would be a permanent no-op (graceful fallback to unranked order every call) plus a misleading permanent error badge on the Status page. Revert until a reranker model is actually deployed on the gateway. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --- .env | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.env b/.env index 3a3459d..6a3fae5 100644 --- a/.env +++ b/.env @@ -102,7 +102,7 @@ DOCUMENT_PARSE_ARTIFACT_PREFIX=artifacts PARSER_FAILURE_MODE=fail # ===== Reranker 配置 ===== -RERANKER_ENABLED=true +RERANKER_ENABLED=false RERANKER_BASE_URL=http://6.86.80.4:30080/v1 RERANKER_MODEL=BAAI/bge-reranker-v2-m3 RERANKER_API_KEY=sk-fVr9KmDZNC4pGDBQj0EUWz9bDmFzNxjYC9EzZpe2bVDsxtz8