Extract layout, audio files

llama_parse/base.py

@@ -157,6 +157,10 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="If set to true, the parser will extract/tag charts from the document.",
     )
+    extract_layout: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will extract the layout information of the document. Cost 1 credit per page.",
+    )
     fast_mode: Optional[bool] = Field(
         default=False,
         description="Note: Non compatible with gpt-4o. If set to true, the parser will use a faster mode to extract text from documents. This mode will skip OCR of images, and table/heading reconstruction.",
@@ -457,6 +461,9 @@ class LlamaParse(BasePydanticReader):
         if self.extract_charts:
             data["extract_charts"] = self.extract_charts
 
+        if self.extract_layout:
+            data["extract_layout"] = self.extract_layout
+
         if self.fast_mode:
             data["fast_mode"] = self.fast_mode
 

llama_parse/utils.py

@@ -191,4 +191,11 @@ SUPPORTED_FILE_TYPES = [
     ".xlr",
     ".eth",
     ".tsv",
+    ".mp3",
+    ".mp4",
+    ".mpeg",
+    ".mpga",
+    ".m4a",
+    ".wav",
+    ".webm",
 ]

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.5.17"
+version = "0.5.18"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"