# ocracy

> Facade to many implementations of (OCR) image-to-text-characters engines


## Pages

- [ocracy](index.html.md): One façade over many OCR engines — plus a **ledger** to help you choose between them.
- [API reference](api.html.md): | `ocracy`   | ocracy — one facade over many OCR engines, plus a ledger to choose between them.   |
- [ocracy](_autosummary/ocracy.html.md): ocracy — one facade over many OCR engines, plus a ledger to choose between them.
- [ocracy.backends](_autosummary/ocracy.backends.html.md): Implemented OCR backends.
- [ocracy.backends.aws_textract](_autosummary/ocracy.backends.aws_textract.html.md): AWS Textract backend for ocracy (cloud OCR + forms/tables).
- [ocracy.backends.aws_textract.adapter](_autosummary/ocracy.backends.aws_textract.adapter.html.md): Adapter for AWS Textract — image -> text + word boxes via detect_document_text.
- [ocracy.backends.aws_textract.config](_autosummary/ocracy.backends.aws_textract.config.html.md): Configuration for the AWS Textract backend.
- [ocracy.backends.azure_document_intelligence](_autosummary/ocracy.backends.azure_document_intelligence.html.md): Azure AI Document Intelligence backend for ocracy (cloud read/layout).
- [ocracy.backends.azure_document_intelligence.adapter](_autosummary/ocracy.backends.azure_document_intelligence.adapter.html.md): Adapter for Azure AI Document Intelligence — image -> text + word polygons.
- [ocracy.backends.azure_document_intelligence.config](_autosummary/ocracy.backends.azure_document_intelligence.config.html.md): Configuration for the Azure AI Document Intelligence backend.
- [ocracy.backends.claude_vision](_autosummary/ocracy.backends.claude_vision.html.md): Claude (Anthropic) vision backend for ocracy — VLM ‘read + reason’ OCR.
- [ocracy.backends.claude_vision.adapter](_autosummary/ocracy.backends.claude_vision.adapter.html.md): Adapter for Claude vision — image -> transcribed text via the Anthropic SDK.
- [ocracy.backends.claude_vision.config](_autosummary/ocracy.backends.claude_vision.config.html.md): Configuration for the Claude (Anthropic) vision backend.
- [ocracy.backends.easyocr](_autosummary/ocracy.backends.easyocr.html.md): EasyOCR backend for ocracy.
- [ocracy.backends.easyocr.adapter](_autosummary/ocracy.backends.easyocr.adapter.html.md): Adapter for EasyOCR — image -> text + polygon boxes via easyocr.Reader.
- [ocracy.backends.easyocr.config](_autosummary/ocracy.backends.easyocr.config.html.md): Configuration for the EasyOCR backend.
- [ocracy.backends.google_vision](_autosummary/ocracy.backends.google_vision.html.md): Google Cloud Vision API (TEXT_DETECTION & DOCUMENT_TEXT_DETECTION) backend for ocracy.
- [ocracy.backends.google_vision.adapter](_autosummary/ocracy.backends.google_vision.adapter.html.md): Adapter for Google Cloud Vision — image -> text + word boxes + confidence.
- [ocracy.backends.google_vision.config](_autosummary/ocracy.backends.google_vision.config.html.md): Configuration for the Google Cloud Vision backend.
- [ocracy.backends.gpt_4o_vision](_autosummary/ocracy.backends.gpt_4o_vision.html.md): OpenAI GPT-4o vision backend for ocracy — VLM ‘read + reason’ OCR.
- [ocracy.backends.gpt_4o_vision.adapter](_autosummary/ocracy.backends.gpt_4o_vision.adapter.html.md): Adapter for OpenAI GPT-4o vision — image -> transcribed text via the openai SDK.
- [ocracy.backends.gpt_4o_vision.config](_autosummary/ocracy.backends.gpt_4o_vision.config.html.md): Configuration for the OpenAI GPT-4o vision backend.
- [ocracy.backends.mathpix](_autosummary/ocracy.backends.mathpix.html.md): Mathpix (Snip + Convert API) backend for ocracy.
- [ocracy.backends.mathpix.adapter](_autosummary/ocracy.backends.mathpix.adapter.html.md): Adapter for Mathpix — image -> Mathpix-Markdown / LaTeX via the Convert API.
- [ocracy.backends.mathpix.config](_autosummary/ocracy.backends.mathpix.config.html.md): Configuration for the Mathpix backend (Convert API).
- [ocracy.backends.mistral_ocr](_autosummary/ocracy.backends.mistral_ocr.html.md): Mistral OCR backend for ocracy (VLM document OCR via the Mistral API).
- [ocracy.backends.mistral_ocr.adapter](_autosummary/ocracy.backends.mistral_ocr.adapter.html.md): Adapter for Mistral OCR — image -> Markdown via the Mistral OCR API.
- [ocracy.backends.mistral_ocr.config](_autosummary/ocracy.backends.mistral_ocr.config.html.md): Configuration for the Mistral OCR backend (cloud VLM document OCR).
- [ocracy.backends.ocr_space](_autosummary/ocracy.backends.ocr_space.html.md): OCR.space OCR API backend for ocracy.
- [ocracy.backends.ocr_space.adapter](_autosummary/ocracy.backends.ocr_space.adapter.html.md): Adapter for OCR.space — image -> text + word boxes via its REST API.
- [ocracy.backends.ocr_space.config](_autosummary/ocracy.backends.ocr_space.config.html.md): Configuration for the OCR.space backend (REST API).
- [ocracy.backends.ocrmac](_autosummary/ocracy.backends.ocrmac.html.md): ocrmac (Apple Vision) backend for ocracy.
- [ocracy.backends.ocrmac.adapter](_autosummary/ocracy.backends.ocrmac.adapter.html.md): Adapter for ocrmac — image -> text via the macOS Vision framework.
- [ocracy.backends.ocrmac.config](_autosummary/ocracy.backends.ocrmac.config.html.md): Configuration for the ocrmac backend (Apple Vision, macOS-only).
- [ocracy.backends.paddleocr](_autosummary/ocracy.backends.paddleocr.html.md): PaddleOCR backend for ocracy (PP-OCR text recognition).
- [ocracy.backends.paddleocr.adapter](_autosummary/ocracy.backends.paddleocr.adapter.html.md): Adapter for PaddleOCR — image -> text + quad boxes via PP-OCR.
- [ocracy.backends.paddleocr.config](_autosummary/ocracy.backends.paddleocr.config.html.md): Configuration for the PaddleOCR backend.
- [ocracy.backends.pix2tex_latex_ocr](_autosummary/ocracy.backends.pix2tex_latex_ocr.html.md): pix2tex (LaTeX-OCR) backend for ocracy — local math image -> LaTeX.
- [ocracy.backends.pix2tex_latex_ocr.adapter](_autosummary/ocracy.backends.pix2tex_latex_ocr.adapter.html.md): Adapter for pix2tex — image of an equation -> LaTeX, locally.
- [ocracy.backends.pix2tex_latex_ocr.config](_autosummary/ocracy.backends.pix2tex_latex_ocr.config.html.md): Configuration for the pix2tex (LaTeX-OCR) backend.
- [ocracy.backends.rapidocr](_autosummary/ocracy.backends.rapidocr.html.md): RapidOCR backend for ocracy.
- [ocracy.backends.rapidocr.adapter](_autosummary/ocracy.backends.rapidocr.adapter.html.md): Adapter for RapidOCR — image -> text + quad boxes via ONNXRuntime PP-OCR.
- [ocracy.backends.rapidocr.config](_autosummary/ocracy.backends.rapidocr.config.html.md): Configuration for the RapidOCR backend (ONNXRuntime).
- [ocracy.backends.tesseract](_autosummary/ocracy.backends.tesseract.html.md): Tesseract backend for ocracy (via pytesseract).
- [ocracy.backends.tesseract.adapter](_autosummary/ocracy.backends.tesseract.adapter.html.md): Adapter for Tesseract — image -> text+word-boxes via pytesseract.
- [ocracy.backends.tesseract.config](_autosummary/ocracy.backends.tesseract.config.html.md): Configuration for the Tesseract backend.
- [ocracy.backends.trocr_handwritten](_autosummary/ocracy.backends.trocr_handwritten.html.md): TrOCR (handwritten) backend for ocracy — local handwriting recognition.
- [ocracy.backends.trocr_handwritten.adapter](_autosummary/ocracy.backends.trocr_handwritten.adapter.html.md): Adapter for TrOCR (handwritten) — image of a text line -> text, locally.
- [ocracy.backends.trocr_handwritten.config](_autosummary/ocracy.backends.trocr_handwritten.config.html.md): Configuration for the TrOCR (handwritten) backend.
- [ocracy.base](_autosummary/ocracy.base.html.md): Core types and normalized result objects for ocracy.
- [ocracy.catalog](_autosummary/ocracy.catalog.html.md): A filterable, dict-like collection of `BackendInfo`, keyed by id.
- [ocracy.credentials](_autosummary/ocracy.credentials.html.md): Credential resolution for remote OCR backends.
- [ocracy.kit](_autosummary/ocracy.kit.html.md): The facade kit: the three helpers every fleet facade used to copy by hand.
- [ocracy.kit.credentials](_autosummary/ocracy.kit.credentials.html.md): One credential chain for every facade: explicit -> bound -> env -> store -> prompt.
- [ocracy.kit.install](_autosummary/ocracy.kit.install.html.md): Install plans: what a backend needs on *this* OS, as data an agent can act on.
- [ocracy.kit.translation](_autosummary/ocracy.kit.translation.html.md): Canonical -> native keyword translation, with an honest unsupported-parameter policy.
- [ocracy.make_backend](_autosummary/ocracy.make_backend.html.md): Abstraction tools for *building* OCR facades.
- [ocracy.registry](_autosummary/ocracy.registry.html.md): Backend discovery, registration, and lazy loading.
- [ocracy.services](_autosummary/ocracy.services.html.md): Lazy mapping of backend ids -> `ServiceHandle`.
- [ocracy.status](_autosummary/ocracy.status.html.md): Backend readiness status — four nested levels, info dicts, and a Markdown table.
- [ocracy.tools](_autosummary/ocracy.tools.html.md): Command-line tools for ocracy (dispatched via `cw` in `__main__`).
- [ocracy.translation](_autosummary/ocracy.translation.html.md): Parameter translation between ocracy’s normalized kwargs and native engines.
- [ocracy.util](_autosummary/ocracy.util.html.md): Image-input normalization and small shared helpers.
- [For AI agents](ai-agents.html.md): `ocracy` ships artifacts for coding agents alongside its code. This page lists
- [About this build](about-this-build.html.md): This documentation was built on **2026-10-14 02:29 UTC** from commit <a href="https://github.com/tho...

## Optional

- [ocracy.md](ocracy.md): Complete documentation in a single file.

## Build

- [build_info.json](build_info.json): build provenance (commit, version, tool versions, whether the docs match the package)