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 |
Storage, CRUD, search, corpus, library indexes |
| vera-ingest | import vera_ingest |
PDF parsing, chunking, conversion |
| vera-cli | 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>=0.2.2"
python -m pip install "vera-ingest>=0.2.2"
python -m pip install "vera-cli>=0.2.2"
python -m pip install "vera-mcp>=0.2.2"
vera-ingest may not yet be published to PyPI. If the install fails because the
package cannot be found, use a repository checkout instead.
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-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 |
Related documentation¶
- Python API guide — narrative walkthrough with examples.
- CLI reference — command-line flags and JSON output.
- Format specification — on-disk archive schema.