Version 0.20.0

• Fix bug (#341) that requires users to install ml packages when importing the application module. (#342)
• Improve feed_batch robustness by processing the batch in mini-batches and adding a retry layer (#340)

Version 0.19.0

• Improve output on deployment failure (#326)
• Hard-code onnx model path separator to avoid misbehavior when using Windows. (#328)
• Add namespace argument to document operations (#337)
• Include evaluation example with recall argument (#338)
• Introduce vespa.experimental.ranking module (#336)

Version 0.18.0

• Enable Docker deployment via a POST request (#318)

Version 0.17.0

• Enable Docker deployment without disk_folder specification through a zip file. (#313, #315)

Version 0.16.0

• Use latest transformer library and pipeline class. (#254)
• Make it possible to specify container_image when creating a VespaDocker instance.

Version 0.15.0

• app.query_batch: Add method to send queries in batch (#244)

Version 0.14.0

• Add retry strategy to delete_data, get_data and update_data (#222)
• Deployment parameter disk_folder defaults to the current working directory for both Docker and Cloud deployment (#225)
• Vespa connection now accepts cert and key as separate arguments. Using both certificate and key values in the cert file continue to work as before. (#226)

Version 0.13.0

• Infer schema name whenever possible for batch document operations (#210)
  • When we have application package information containing just one schema, it is possible to simplify the batch document operations by not specifying the schema name. For those cases, we can for example use app.feed_batch(docs) instead of app.feed_batch(docs, schema = "sentence") when we know there is only one schema named "sentence".
• Introduce TextSearch use case (#212)
• Create a convenience function to feed df to a Vespa app (#213)
• Allow a data frame to be used when collecting training data (#215)
• Allow default query model to be specified and define it for TextSearch (#217)

Version 0.12.0

Removes vespa.package module dependency on the vespa.ml module. The main goal is to avoid installing vespa.ml specific dependencies through pip install pyvespa[ml] unless the user explicitly wants to use vespa.ml classes.

Version 0.11.0

• Use tasks instead of models as argument name for ModelServer to align with the fact this argument takes instances of type TextTask.
• Use model_id instead of model_name to identify a model since model_id is what we use when defining a Task.