Docs /Templates/ sinapsis_langchain_readers

ImageCaptionLoaderWrapper

sinapsis_langchain_readersLangChaindocumentsdocument_loadingdynamicfiles

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

ImageCaptionLoader — inherited documentation

Load image captions.

By default, the loader utilizes the pre-trained Salesforce BLIP image captioning model. https://huggingface.co/Salesforce/blip-image-captioning-baseInitialize with a list of image data (bytes) or file paths

Args: images: Either a single image or a list of images. Accepts image data (bytes) or file paths to images. blip_processor: The name of the pre-trained BLIP processor. blip_model: The name of the pre-trained BLIP model.

Capabilities

Capabilities: not set

Installation

Install the published package using pip or uv.

Terminalbash
pip install sinapsis_langchain_readers==1.0.0
uv pip install sinapsis_langchain_readers==1.0.0
uv add sinapsis_langchain_readers==1.0.0

Configuration

Effective fields from the inspector schema, including nested Pydantic model fields.

metadata
sinapsis_core.template_base.base_models.TemplateMetadata | None
Optional
Default: null
imagecaptionloader_initRequired
__init__Attributes
Required
Default: null
images
typing.Union[str, pathlib._local.Path, bytes, typing.List[typing.Union[str, bytes, pathlib._local.Path]]]
Optional
Default: null
blip_model
str
Optional
Default: "Salesforce/blip-image-captioning-base"
blip_processor
str
Optional
Default: "Salesforce/blip-image-captioning-base"
add_document_as_text_packet
Whether to add document as text packet or not. imagecaptionloader_init images typing.Union[str, pathlib._local.Path, bytes, typing.List[typing.Union[str, bytes, pathlib._local.Path]]]: default: None blip_processor… Read full field description

Whether to add document as text packet or not. imagecaptionloader_init images typing.Union[str, pathlib._local.Path, bytes, typing.List[typing.Union[str, bytes, pathlib._local.Path]]]: default: None blip_processor <class 'str'>: default: Salesforce/blip-image-captioning-base blip_model <class 'str'>: default: Salesforce/blip-image-captioning-base

bool
Optional
Default: false

Configuration example

Generated from documented defaults. Replace any placeholders and complete required nested settings before running.

yaml
templates:
  - template_name: "ImageCaptionLoaderWrapper"
    class_name: "ImageCaptionLoaderWrapper"
    attributes:
      imagecaptionloader_init:
        images: null
        blip_model: "Salesforce/blip-image-captioning-base"
        blip_processor: "Salesforce/blip-image-captioning-base"
      add_document_as_text_packet: false
View original docstring example

The source example references WikipediaLoaderWrapper, not ImageCaptionLoaderWrapper.

yaml
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: 4000

Inheritance

Immediate parent: sinapsis_langchain_readers.templates.langchain_data_readers.LangChainDataReaderBase

Environment variables

Environment definitions belong to their canonical Python modules.

SINAPSIS_BUILD_DOCS · defined elsewhere