EasyOCRExtractor

Extractor

DashAI.back.models.RAG.extractors.EasyOCRExtractor

---

PDF text extractor using EasyOCR.

Converts PDF pages to images and runs OCR on each page. Works with any language supported by EasyOCR (80+ languages). No external system dependencies - pure pip install.

Parameters

languages : array, default=['en']

Language codes for OCR (e.g. ['en'], ['es'], ['en','fr'])

gpu : boolean, default=True

Use GPU acceleration if available

Methods

extract(self, file_path: str) -> str

Defined on EasyOCRExtractor

Extract text from PDF using EasyOCR.

get_credential(self, name: str)

Defined on ConfigObject

Resolve a registered credential component by name.

Parameters

name : str

Credential component class name (e.g. "HuggingFaceCredential").

Returns

BaseCredential

An instance of the requested credential component.

get_metadata(cls) -> Dict[str, object]

Defined on BaseExtractor

Return metadata for registry — primarily supported_file_types.

get_schema(cls) -> dict

Defined on ConfigObject

Generates the component related Json Schema.

Returns

dict

Dictionary representing the Json Schema of the component.

validate_and_transform(self, raw_data: dict) -> dict

Defined on ConfigObject

It takes the data given by the user to initialize the model and returns it with all the objects that the model needs to work.

Parameters

raw_data : dict

A dictionary with the data provided by the user to initialize the model.

Returns

dict

A validated dictionary with the necessary objects.