From d7cc6bfbc7d0853dbc82ab7438ee92fb6cd44a9c Mon Sep 17 00:00:00 2001 From: Benjamin Admin Date: Thu, 26 Feb 2026 23:29:23 +0100 Subject: [PATCH] Switch embedding model to bge-m3 (1024-dim) The Qdrant collections use 1024-dim vectors (bge-m3) but the embedding-service was configured with all-MiniLM-L6-v2 (384-dim). Also increase memory limit to 8G for the larger model. Co-Authored-By: Claude Opus 4.6 --- docker-compose.yml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docker-compose.yml b/docker-compose.yml index 8449106..1fecb6b 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -414,7 +414,7 @@ services: - embedding_models:/root/.cache/huggingface environment: EMBEDDING_BACKEND: ${EMBEDDING_BACKEND:-local} - LOCAL_EMBEDDING_MODEL: ${LOCAL_EMBEDDING_MODEL:-sentence-transformers/all-MiniLM-L6-v2} + LOCAL_EMBEDDING_MODEL: ${LOCAL_EMBEDDING_MODEL:-BAAI/bge-m3} LOCAL_RERANKER_MODEL: ${LOCAL_RERANKER_MODEL:-cross-encoder/ms-marco-MiniLM-L-6-v2} PDF_EXTRACTION_BACKEND: ${PDF_EXTRACTION_BACKEND:-pymupdf} OPENAI_API_KEY: ${OPENAI_API_KEY:-} @@ -423,7 +423,7 @@ services: deploy: resources: limits: - memory: 4G + memory: 8G healthcheck: test: ["CMD", "python", "-c", "import httpx; r=httpx.get('http://127.0.0.1:8087/health'); r.raise_for_status()"] interval: 30s