From 41183ff93d51dc1e0b8ae28ecf023242973884d7 Mon Sep 17 00:00:00 2001 From: Benjamin Admin Date: Sat, 2 May 2026 17:30:33 +0200 Subject: [PATCH] fix(docker): set PDF_EXTRACTION_BACKEND to auto (was pymupdf) The default was 'pymupdf' which doesn't exist as a backend, causing fallthrough to pypdf every time. With 'auto', the priority is: unstructured > pdfplumber > pypdf. Co-Authored-By: Claude Opus 4.6 (1M context) --- docker-compose.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker-compose.yml b/docker-compose.yml index 1ba752d..97c2e98 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -434,7 +434,7 @@ services: EMBEDDING_BACKEND: ${EMBEDDING_BACKEND:-local} 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} + PDF_EXTRACTION_BACKEND: ${PDF_EXTRACTION_BACKEND:-auto} OPENAI_API_KEY: ${OPENAI_API_KEY:-} COHERE_API_KEY: ${COHERE_API_KEY:-} LOG_LEVEL: ${LOG_LEVEL:-INFO}