Merge pull request #858 from cbcoutinho/feat/tiered-doc-processor-b2-tier1

feat: tiered PDF processor — pypdfium2 fast path (deprecate pymupdf4llm)
2026-06-05 02:43:11 +02:00
parent cc441ba0db bc957b5bc7
commit c67b998784
16 changed files with 1145 additions and 157 deletions
@@ -46,6 +46,7 @@ dependencies = [
    "dynaconf>=3.2.13,<4.0",
    "mistralai>=2.4.5",
    "sqlalchemy[asyncio]>=2.0",
+    "pypdfium2>=5.9.0",
 ]
 classifiers = [
    "Development Status :: 4 - Beta",