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) <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-05-02 17:30:33 +02:00
parent 75dda9ac92
commit 41183ff93d
+1 -1
View File
@@ -434,7 +434,7 @@ services:
EMBEDDING_BACKEND: ${EMBEDDING_BACKEND:-local} EMBEDDING_BACKEND: ${EMBEDDING_BACKEND:-local}
LOCAL_EMBEDDING_MODEL: ${LOCAL_EMBEDDING_MODEL:-BAAI/bge-m3} LOCAL_EMBEDDING_MODEL: ${LOCAL_EMBEDDING_MODEL:-BAAI/bge-m3}
LOCAL_RERANKER_MODEL: ${LOCAL_RERANKER_MODEL:-cross-encoder/ms-marco-MiniLM-L-6-v2} 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:-} OPENAI_API_KEY: ${OPENAI_API_KEY:-}
COHERE_API_KEY: ${COHERE_API_KEY:-} COHERE_API_KEY: ${COHERE_API_KEY:-}
LOG_LEVEL: ${LOG_LEVEL:-INFO} LOG_LEVEL: ${LOG_LEVEL:-INFO}