langchain.document_loaders.embaas.EmbaasLoader

class langchain.document_loaders.embaas.EmbaasLoader(*, embaas_api_key: Optional[str] = None, api_url: str = 'https://api.embaas.io/v1/document/extract-text/bytes/', params: EmbaasDocumentExtractionParameters = {}, file_path: str, blob_loader: Optional[EmbaasBlobLoader] = None)

Bases: BaseEmbaasLoader, BaseLoader

Embaas’s document loader.

To use, you should have the environment variable EMBAAS_API_KEY set with your API key, or pass it as a named parameter to the constructor.

Example

# Default parsing
from langchain.document_loaders.embaas import EmbaasLoader
loader = EmbaasLoader(file_path="example.mp3")
documents = loader.load()

# Custom api parameters (create embeddings automatically)
from langchain.document_loaders.embaas import EmbaasBlobLoader
loader = EmbaasBlobLoader(
    file_path="example.pdf",
    params={
        "should_embed": True,
        "model": "e5-large-v2",
        "chunk_size": 256,
        "chunk_splitter": "CharacterTextSplitter"
    }
)
documents = loader.load()

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param api_url: str = 'https://api.embaas.io/v1/document/extract-text/bytes/'

The URL of the embaas document extraction API.

param blob_loader: Optional[langchain.document_loaders.embaas.EmbaasBlobLoader] = None

The blob loader to use. If not provided, a default one will be created.

param embaas_api_key: Optional[str] = None

The API key for the embaas document extraction API.

param file_path: str [Required]

The path to the file to load.

param params: langchain.document_loaders.embaas.EmbaasDocumentExtractionParameters = {}

Additional parameters to pass to the embaas document extraction API.

lazy_load() → Iterator[Document]

Load the documents from the file path lazily.

load() → List[Document]

Load data into Document objects.

load_and_split(text_splitter: Optional[TextSplitter] = None) → List[Document]

Load Documents and split into chunks. Chunks are returned as Documents.

Parameters

text_splitter – TextSplitter instance to use for splitting documents. Defaults to RecursiveCharacterTextSplitter.

Returns

List of Documents.

validator validate_blob_loader  »  blob_loader

validator validate_environment  »  all fields

Validate that api key and python package exists in environment.

Examples using EmbaasLoader

• Embaas