* Fix bug (https://github.com/vespa-engine/pyvespa/issues/341) that requires users to install ml packages when importing the application module. (https://github.com/vespa-engine/pyvespa/pull/342) * Improve feed_batch robustness by processing the batch in mini-batches and adding a retry layer (https://github.com/vespa-engine/pyvespa/pull/340)
0.19.0
* Improve output on deployment failure (https://github.com/vespa-engine/pyvespa/pull/326) * Hard-code onnx model path separator to avoid misbehavior when using Windows. (https://github.com/vespa-engine/pyvespa/pull/328) * Add `namespace` argument to document operations (https://github.com/vespa-engine/pyvespa/pull/337) * Include evaluation example with `recall` argument (https://github.com/vespa-engine/pyvespa/pull/338) * Introduce `vespa.experimental.ranking` module (https://github.com/vespa-engine/pyvespa/pull/336)
0.18.0
* Enable Docker deployment via a POST request (https://github.com/vespa-engine/pyvespa/pull/318)
0.17.0
* Enable Docker deployment without `disk_folder` specification through a zip file. (https://github.com/vespa-engine/pyvespa/pull/313, https://github.com/vespa-engine/pyvespa/pull/315)
0.16.0
* Use latest `transformer` library and `pipeline` class. (https://github.com/vespa-engine/pyvespa/pull/254) * Make it possible to specify `container_image` when creating a `VespaDocker` instance.
0.15.0
* `app.query_batch`: Add method to send queries in batch (https://github.com/vespa-engine/pyvespa/pull/244)