add high_res_ocr to the package

2026-07-21 12:05:23 -04:00 · 2025-06-16 14:34:47 +08:00
3 changed files with 9 additions and 2 deletions
@@ -273,6 +273,10 @@ class LlamaParse(BasePydanticReader):
        default=False,
        description="Whether to guess the sheet names of the xlsx file.",
    )
+    high_res_ocr: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will use high resolution OCR to extract text from images. This will increase the accuracy of the parsing job, but reduce the speed.",
+    )
    html_make_all_elements_visible: Optional[bool] = Field(
        default=False,
        description="If set to true, when parsing HTML the parser will consider all elements display not element as display block.",
@@ -758,6 +762,9 @@ class LlamaParse(BasePydanticReader):
        if self.html_make_all_elements_visible:
            data["html_make_all_elements_visible"] = self.html_make_all_elements_visible

+        if self.high_res_ocr:
+            data["high_res_ocr"] = self.high_res_ocr
+
        if self.html_remove_fixed_elements:
            data["html_remove_fixed_elements"] = self.html_remove_fixed_elements

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"

 [tool.poetry]
 name = "llama-parse"
-version = "0.6.32"
+version = "0.6.33"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"
@@ -8,7 +8,7 @@ python_version = "3.10"

 [tool.poetry]
 name = "llama-cloud-services"
-version = "0.6.32"
+version = "0.6.33"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = ["Logan Markewich <logan@runllama.ai>"]
 license = "MIT"