Add OCR_AGENT_CACHE_SIZE environment variable (#4066)

## Problem OCR agents used unlimited caching, causing excessive memory usage. Each cached OCR agent consumes different amounts of memory, but can easily consume ~800MB. ## Solution Add `OCR_AGENT_CACHE_SIZE` environment variable to limit cached OCR agents per process. - **Default**: 1 cached agent - **Configurable**: Set to 0 to disable caching, or higher for more languages

Author: CyMule

CHANGELOG.md

@@ -1,3 +1,12 @@
+## 0.18.10
+
+### Enhancements
+
+### Features
+- **Add OCR_AGENT_CACHE_SIZE environment variable** Added configurable cache size for OCR agents to control memory usage.
+
+### Fixes
+
 ## 0.18.10-dev0
 
 ### Enhancements

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.18.10-dev0" # pragma: no cover
+__version__ = "0.18.10" # pragma: no cover

unstructured/partition/utils/config.py

@@ -111,6 +111,11 @@ def OCR_AGENT(self) -> str:
  """OCR Agent to use"""
  return self._get_string("OCR_AGENT", OCR_AGENT_TESSERACT)
 
+ @property
+ def OCR_AGENT_CACHE_SIZE(self) -> int:
+ """Maximum number of OCR agents to cache per process"""
+ return self._get_int("OCR_AGENT_CACHE_SIZE", 1)
+
  @property
  def EXTRACT_IMAGE_BLOCK_CROP_HORIZONTAL_PAD(self) -> int:
  """extra image block content to add around an identified element(`Image`, `Table`) region

unstructured/partition/utils/ocr_models/ocr_interface.py

@@ -34,7 +34,7 @@ def get_agent(cls, language: str) -> OCRAgent:
  return cls.get_instance(ocr_agent_cls_qname, language)
 
  @staticmethod
- @functools.lru_cache(maxsize=None)
+ @functools.lru_cache(maxsize=env_config.OCR_AGENT_CACHE_SIZE)
  def get_instance(ocr_agent_module: str, language: str) -> "OCRAgent":
  module_name, class_name = ocr_agent_module.rsplit(".", 1)
  if module_name not in OCR_AGENT_MODULES_WHITELIST: