0.6.25 outlined_table_extraction

llama_cloud_services/parse/base.py

@@ -297,6 +297,10 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="If set to true, the parser will output tables as HTML in the markdown.",
     )
+    outlined_table_extraction: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will use a dedicated approach to extract tables with outlined cells. This is useful for documents with spreadsheet-like tables where cells are outlined with borders. This could lead to false positives, so use with caution.",
+    )
     page_error_tolerance: Optional[float] = Field(
         default=None,
         description="The error tolerance for the number of pages with error in a doc (percentage express as 0-1). If we fail to parse a greater percentage of pages than the tolerance value we fail the job.",
@@ -752,6 +756,9 @@ class LlamaParse(BasePydanticReader):
         if self.output_tables_as_HTML:
             data["output_tables_as_HTML"] = self.output_tables_as_HTML
 
+        if self.outlined_table_extraction:
+            data["outlined_table_extraction"] = self.outlined_table_extraction
+
         if self.page_error_tolerance is not None:
             data["page_error_tolerance"] = self.page_error_tolerance
 

llama_parse/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.6.24"
+version = "0.6.25"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"

pyproject.toml

@@ -8,7 +8,7 @@ python_version = "3.10"
 
 [tool.poetry]
 name = "llama-cloud-services"
-version = "0.6.24"
+version = "0.6.25"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = ["Logan Markewich <logan@runllama.ai>"]
 license = "MIT"