github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-01 11:02:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[patch]: speed up import times in the community package (#18928)

Browse Source 
This PR speeds up import times in the community package
This commit is contained in:
Leonid Ganeline
2024-03-11 13:37:36 -07:00
committed by GitHub
parent a7fc731720
commit 11195cfa42
11 changed files with 430 additions and 668 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
libs/community/langchain_community/document_loaders/parsers/__init__.py
View File

@@ -1,31 +1,27 @@
from langchain_community.document_loaders.parsers.audio import OpenAIWhisperParser
from langchain_community.document_loaders.parsers.doc_intelligence import (
AzureAIDocumentIntelligenceParser,
)
from langchain_community.document_loaders.parsers.docai import DocAIParser
from langchain_community.document_loaders.parsers.grobid import GrobidParser
from langchain_community.document_loaders.parsers.html import BS4HTMLParser
from langchain_community.document_loaders.parsers.language import LanguageParser
from langchain_community.document_loaders.parsers.pdf import (
PDFMinerParser,
PDFPlumberParser,
PyMuPDFParser,
PyPDFium2Parser,
PyPDFParser,
)
from langchain_community.document_loaders.parsers.vsdx import VsdxParser
import importlib
from typing import Any
__all__ = [
"AzureAIDocumentIntelligenceParser",
"BS4HTMLParser",
"DocAIParser",
"GrobidParser",
"LanguageParser",
"OpenAIWhisperParser",
"PDFMinerParser",
"PDFPlumberParser",
"PyMuPDFParser",
"PyPDFium2Parser",
"PyPDFParser",
"VsdxParser",
]
_module_lookup = {
"AzureAIDocumentIntelligenceParser": "langchain_community.document_loaders.parsers.doc_intelligence", # noqa: E501
"BS4HTMLParser": "langchain_community.document_loaders.parsers.html",
"DocAIParser": "langchain_community.document_loaders.parsers.docai",
"GrobidParser": "langchain_community.document_loaders.parsers.grobid",
"LanguageParser": "langchain_community.document_loaders.parsers.language",
"OpenAIWhisperParser": "langchain_community.document_loaders.parsers.audio",
"PDFMinerParser": "langchain_community.document_loaders.parsers.pdf",
"PDFPlumberParser": "langchain_community.document_loaders.parsers.pdf",
"PyMuPDFParser": "langchain_community.document_loaders.parsers.pdf",
"PyPDFParser": "langchain_community.document_loaders.parsers.pdf",
"PyPDFium2Parser": "langchain_community.document_loaders.parsers.pdf",
"VsdxParser": "langchain_community.document_loaders.parsers.vsdx",
}
def __getattr__(name: str) -> Any:
if name in _module_lookup:
module = importlib.import_module(_module_lookup[name])
return getattr(module, name)
raise AttributeError(f"module {__name__} has no attribute {name}")
__all__ = list(_module_lookup.keys())