mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
ed58eeb9c5
Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
47 lines
1.6 KiB
Python
47 lines
1.6 KiB
Python
"""Loads Microsoft Excel files."""
|
|
from typing import Any, List
|
|
|
|
from langchain_community.document_loaders.unstructured import (
|
|
UnstructuredFileLoader,
|
|
validate_unstructured_version,
|
|
)
|
|
|
|
|
|
class UnstructuredExcelLoader(UnstructuredFileLoader):
|
|
"""Load Microsoft Excel files using `Unstructured`.
|
|
|
|
Like other
|
|
Unstructured loaders, UnstructuredExcelLoader can be used in both
|
|
"single" and "elements" mode. If you use the loader in "elements"
|
|
mode, each sheet in the Excel file will be a an Unstructured Table
|
|
element. If you use the loader in "elements" mode, an
|
|
HTML representation of the table will be available in the
|
|
"text_as_html" key in the document metadata.
|
|
|
|
Examples
|
|
--------
|
|
from langchain_community.document_loaders.excel import UnstructuredExcelLoader
|
|
|
|
loader = UnstructuredExcelLoader("stanley-cups.xlsd", mode="elements")
|
|
docs = loader.load()
|
|
"""
|
|
|
|
def __init__(
|
|
self, file_path: str, mode: str = "single", **unstructured_kwargs: Any
|
|
):
|
|
"""
|
|
|
|
Args:
|
|
file_path: The path to the Microsoft Excel file.
|
|
mode: The mode to use when partitioning the file. See unstructured docs
|
|
for more info. Optional. Defaults to "single".
|
|
**unstructured_kwargs: Keyword arguments to pass to unstructured.
|
|
"""
|
|
validate_unstructured_version(min_unstructured_version="0.6.7")
|
|
super().__init__(file_path=file_path, mode=mode, **unstructured_kwargs)
|
|
|
|
def _get_elements(self) -> List:
|
|
from unstructured.partition.xlsx import partition_xlsx
|
|
|
|
return partition_xlsx(filename=self.file_path, **self.unstructured_kwargs)
|