Add support for html_remove_navigation_elements.

2026-07-19 16:43:32 -04:00 · 2024-12-06 11:03:16 +01:00
2 changed files with 10 additions and 1 deletions
@@ -173,6 +173,10 @@ class LlamaParse(BasePydanticReader):
        default=False,
        description="If set to true, when parsing HTML the parser will remove fixed elements. Useful to hide cookie banners.",
    )
+    html_remove_navigation_elements: Optional[bool] = Field(
+        default=False,
+        description="If set to true, when parsing HTML the parser will remove navigation elements. Useful to hide menus, header, footer.",
+    )
    http_proxy: Optional[str] = Field(
        default=None,
        description="(optional) If set with input_url will use the specified http proxy to download the file.",
@@ -465,6 +469,11 @@ class LlamaParse(BasePydanticReader):
        if self.html_remove_fixed_elements:
            data["html_remove_fixed_elements"] = self.html_remove_fixed_elements

+        if self.html_remove_navigation_elements:
+            data[
+                "html_remove_navigation_elements"
+            ] = self.html_remove_navigation_elements
+
        if self.http_proxy is not None:
            data["http_proxy"] = self.http_proxy

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

 [tool.poetry]
 name = "llama-parse"
-version = "0.5.16"
+version = "0.5.17"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"