mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-07-25 04:26:41 -04:00
Matt Robinson
c4d53f98dc
### Summary Updates the docstrings in the Unstructured document loaders to display more useful information on the integrations page.
34 lines
1.2 KiB
Python
34 lines
1.2 KiB
Python
"""Loads image files."""
|
|
from typing import List
|
|
|
|
from langchain.document_loaders.unstructured import UnstructuredFileLoader
|
|
|
|
|
|
class UnstructuredImageLoader(UnstructuredFileLoader):
|
|
"""UnstructuredImageLoader uses unstructured to load PNG and JPG files.
|
|
You can run the loader in one of two modes: "single" and "elements".
|
|
If you use "single" mode, the document will be returned as a single
|
|
langchain Document object. If you use "elements" mode, the unstructured
|
|
library will split the document into elements such as Title and NarrativeText.
|
|
You can pass in additional unstructured kwargs after mode to apply
|
|
different unstructured settings.
|
|
|
|
Examples
|
|
--------
|
|
from langchain.document_loaders import UnstructuredImageLoader
|
|
|
|
loader = UnstructuredImageLoader(
|
|
"example.png", mode="elements", strategy="fast",
|
|
)
|
|
docs = loader.load()
|
|
|
|
References
|
|
----------
|
|
https://unstructured-io.github.io/unstructured/bricks.html#partition-image
|
|
"""
|
|
|
|
def _get_elements(self) -> List:
|
|
from unstructured.partition.image import partition_image
|
|
|
|
return partition_image(filename=self.file_path, **self.unstructured_kwargs)
|