Skip to content

API Reference

This section documents the curated public Python API for VERA. Pages are generated from source docstrings using mkdocstrings.

Packages

Package Import Purpose
vera-doc import vera_doc Storage, CRUD, search, corpus, library indexes
vera-ingest import vera_ingest Conversion registry, shared types, archive writing
vera-ingest-pymupdf import vera_ingest_pymupdf Default PyMuPDF PDF parsing and OCR
vera-embed-openai import vera_embed_openai Official OpenAI embeddings plugin
vera import vera_cli Command-line interface
vera-mcp import vera_mcp MCP server for AI agents

Install packages from PyPI:

python -m pip install "vera-doc>=0.3.0"
python -m pip install "vera-ingest>=0.3.0"
python -m pip install "vera-ingest-pymupdf>=0.3.0"
python -m pip install "vera-embed-openai>=0.3.0"
python -m pip install "vera>=0.3.0"
python -m pip install "vera-mcp>=0.3.0"

Or from a repository checkout:

python -m pip install ./packages/vera-doc
python -m pip install ./packages/vera-ingest
python -m pip install ./packages/vera-ingest-pymupdf
python -m pip install ./packages/vera-embed-openai
python -m pip install ./packages/vera-cli
python -m pip install ./packages/vera-mcp

Where to start

Use VeraDocument with ChunkRecord when your application already has final text.

Use VeraDocument.open() for search, inspection, figures, pages, highlight regions, and write-mode CRUD.

Use vera_ingest.convert or the vera convert CLI command.

Use VeraCorpus with build_library_index for multi-document retrieval.

Exceptions

Exception Raised when
DuplicateRecordError add() receives an ID that already exists
RecordNotFoundError A requested chunk or attachment does not exist
ReadOnlyError A write is attempted on a read-only database