LLMSherpaFileLoaderWrapper
Python template · sinapsis_langchain_readers.templates.langchain_data_readers
Overview
Dynamic Template to load documents from Langchain document_loaders module The template loads the document either as a Document object in the generic_data field of DataContainer of each string as a TextPacket if add_document_as_text_packet is set as True
LLMSherpaFileLoader — inherited documentation
Load Documents using `LLMSherpa`.
LLMSherpaFileLoader use LayoutPDFReader, which is part of the LLMSherpa library. This tool is designed to parse PDFs while preserving their layout information, which is often lost when using most PDF to text parsers.
Examples -------- from langchain_community.document_loaders.llmsherpa import LLMSherpaFileLoader
loader = LLMSherpaFileLoader( "example.pdf", strategy="chunks", llmsherpa_api_url="http://localhost:5010/api/parseDocument?renderFormat=all", ) docs = loader.load()Initialize with a file path.
Capabilities
Capabilities: not setInstallation
Install the published package using pip or uv.
pip install sinapsis_langchain_readers==1.0.0uv pip install sinapsis_langchain_readers==1.0.0uv add sinapsis_langchain_readers==1.0.0Configuration
Effective fields from the inspector schema, including nested Pydantic model fields.
Optional
Default: null
Required
Default: null
Optional
Default: "chunks"
Optional
Default: true
Optional
Default: null
Optional
Default: "https://readers.llmsherpa.com/api/document/developer/parseDocument?renderFormat=all"
Optional
Default: true
Whether to add document as text packet or not. llmsherpafileloader_init file_path typing.Union[str, pathlib._local.Path]: default: None new_indent_parser <class 'bool'>: default: True apply_ocr <class 'bool'>: default:… Read full field description
Whether to add document as text packet or not. llmsherpafileloader_init file_path typing.Union[str, pathlib._local.Path]: default: None new_indent_parser <class 'bool'>: default: True apply_ocr <class 'bool'>: default: True strategy <class 'str'>: default: chunks llmsherpa_api_url <class 'str'>: default: https://readers.llmsherpa.com/api/document/developer/parseDocument?renderFormat=all
Optional
Default: false
Configuration example
Generated from documented defaults. Replace any placeholders and complete required nested settings before running.
templates:
- template_name: "LLMSherpaFileLoaderWrapper"
class_name: "LLMSherpaFileLoaderWrapper"
attributes:
llmsherpafileloader_init:
strategy: "chunks"
apply_ocr: true
file_path: null
llmsherpa_api_url: "https://readers.llmsherpa.com/api/document/developer/parseDocument?renderFormat=all"
new_indent_parser: true
add_document_as_text_packet: false
View original docstring example
The source example references WikipediaLoaderWrapper, not LLMSherpaFileLoaderWrapper.
agent:
name: my_test_agent
templates:
- template_name: InputTemplate
class_name: InputTemplate
attributes: {}
- template_name: WikipediaLoaderWrapper
class_name: WikipediaLoaderWrapper ## note that because it is a dynamic template,
template_input: InputTemplate ## the class name depends on the actual class that is used.
attributes:
add_document_as_text_packet: false
wikipedialoader_init:
query: the query for wikipedia
lang: en
load_max_docs: 5000
load_all_available_meta: False
doc_content_chars_max: 4000Inheritance
sinapsis_langchain_readers.templates.langchain_data_readers.LangChainDataReaderBaseEnvironment variables
Environment definitions belong to their canonical Python modules.