Metadata-Version: 2.4
Name: vera-ingest
Version: 0.2.1
Summary: Source ingestion, chunking, and conversion adapters for VERA
Project-URL: Homepage, https://github.com/dkylewillis/vera
Project-URL: Repository, https://github.com/dkylewillis/vera
Project-URL: Documentation, https://dkylewillis.github.io/vera/packages/vera-ingest/
Author: Kyle Willis
License: Apache-2.0
Keywords: chunking,ocr,pdf,semantic-search,vera
Classifier: Development Status :: 3 - Alpha
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Text Processing :: Indexing
Requires-Python: >=3.10
Requires-Dist: pdfplumber>=0.11
Requires-Dist: pymupdf>=1.23
Requires-Dist: vera-doc>=0.2.1
Description-Content-Type: text/markdown

# vera-ingest

`vera-ingest` contains VERA's source ingestion pipeline: PDF parsing, table
extraction, selective OCR, heading detection, chunking, and conversion.

It emits ready-made `vera.ChunkRecord` values and optional opaque attachments,
then stores them through `vera.VeraDocument`. It also provides
`vera_ingest.viewer` helpers that interpret ingest-produced page, figure,
region, and source-document conventions.

## Install

```bash
python -m pip install "vera-ingest>=0.2.1"
```

See the [vera-ingest documentation](https://dkylewillis.github.io/vera/packages/vera-ingest/)
for concepts, examples, and API reference.

See the [conversion guide](https://github.com/dkylewillis/vera/blob/main/docs/conversion.md).
