changeset

.changeset/angry-insects-flash.md

@@ -0,0 +1,5 @@
+---
+"llama-cloud-services-py": patch
+---
+
+Add line-level bbox support

py/llama_cloud_services/parse/base.py

@@ -564,6 +564,10 @@ class LlamaParse(BasePydanticReader):
         default=None,
         description="Whether to extract the printed page numbers from pages in the document.",
     )
+    line_level_bounding_box: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will include line-level bounding boxes in the result.",
+    )
 
     # Deprecated
     bounding_box: Optional[str] = Field(
@@ -1118,6 +1122,9 @@ class LlamaParse(BasePydanticReader):
         if self.extract_printed_page_number is not None:
             data["extract_printed_page_number"] = self.extract_printed_page_number
 
+        if self.line_level_bounding_box is not None:
+            data["line_level_bounding_box"] = self.line_level_bounding_box
+
         # Deprecated
         if self.bounding_box is not None:
             data["bounding_box"] = self.bounding_box

py/llama_cloud_services/parse/types.py

@@ -115,6 +115,26 @@ class BBox(SafeBaseModel):
     )
 
 
+class LineLevelBboxItem(SafeBaseModel):
+    """A line-level bounding box item."""
+
+    md: Optional[str] = Field(
+        default=None, description="The markdown-formatted content of the line."
+    )
+    text: Optional[str] = Field(
+        default=None, description="The text content of the line."
+    )
+    bBox: Optional[BBox] = Field(
+        default=None, description="The bounding box of the line."
+    )
+    startIndex: Optional[int] = Field(
+        default=None, description="The start index of the line in the page text."
+    )
+    endIndex: Optional[int] = Field(
+        default=None, description="The end index of the line in the page text."
+    )
+
+
 class PageItem(SafeBaseModel):
     """An item in a page."""
 
@@ -138,6 +158,9 @@ class PageItem(SafeBaseModel):
         default=None,
         description="The HTML-formatted content of the item. Only applicable for table items when output_tables_as_HTML=True.",
     )
+    lines: Optional[List[LineLevelBboxItem]] = Field(
+        default=None, description="The line-level bounding box items of the item."
+    )
 
 
 class ImageItem(SafeBaseModel):