doc-reader

Text extraction from PDFs, Word, and Excel files is handled by built-in format handlers that output a unified, structured text envelope. You provide a file path and receive consistent text data with encoding notes for downstream indexing.

Pulling data from JSON and CSV files requires no pre-processing with this approach. The built-in handlers parse structured formats like JSON, YAML, TOML, CSV, and TSV directly into a standardized text envelope for immediate search and analysis.

You can use OCR to extract text from images as part of a unified document collection workflow. The tool applies built-in OCR handlers to images, returning the extracted text alongside metadata in the same consistent envelope used for other formats.

This text extraction approach works directly with HTML, XML, and code files. Built-in format handlers process these diverse formats without requiring any pre-processing, delivering structured text that can be indexed, searched, or summarized.

You do not need any external dependencies to parse diverse document formats. The tool relies entirely on built-in format handlers to process PDFs, Office documents, images, and structured data files into a standardized text envelope.

A unified text envelope is a consistent, structured output format that standardizes extracted text and metadata from diverse document types. It ensures that downstream search, analysis, and indexing workflows receive predictable data regardless of the source format.