v0.1.4 - Eval Runs, Batch Rows, Logs

What's Changed

• Add eval runs to SDK / CLI by @freddiev4 in #60
• Modify CLI to print tables & aggregate scores by @freddiev4 in #61
• Add route to allow users to see supported eval run metrics by @crekhari in #62
• Update datasets to batch rows & list datasets by @freddiev4 in #63
• Use batch rows for all dataset create operations by @waldnzwrld in #64
• [QUO-758] Add Logs, Add Hallucination Analysis by @mike-goitia in #65

New Contributors

• @crekhari made their first contribution in #62
• @waldnzwrld made their first contribution in #64
• @mike-goitia made their first contribution in #65

Full Changelog: v0.1.3...v0.1.4

v0.1.3 - Enable dataset rows to be retrieved in call to `.list()`

What's Changed

• Add include_rows parameter to .list() method to optionally include dataset rows by @jamesliounis in #58

Full Changelog: v0.1.2...v0.1.3

v0.1.2 - Fixes broken `delete` logic

What's Changed

• Fix up prompt and dataset delete and prompt updates by @freddiev4 in #56
• Bump version by @freddiev4 in #57

Full Changelog: v0.1.1...v0.1.2

v0.1.1 - Minor error handling & typo fixes

What's Changed

• Fix typos & improve 400 handling by @freddiev4 in #55

Full Changelog: v0.1.0...v0.1.1

v0.1.0 - Updated Quotient SDK

What's Changed

• QUO-82: Python SDK v2 updates by @freddiev4 in #54

Full Changelog: v0.0.7...v0.1.0

v0.0.7 - Remove pydantic to avoid compat issues with other libs Latest

Update pyproject.toml

v0.0.6 - Support for Translation Generation

What's Changed

• Fix seed when empty by @freddiev4 in #51
• Fix ups for seed data + translation by @freddiev4 in #52
• Bump version by @freddiev4 in #53

Full Changelog: v0.0.5...v0.0.6

v0.0.5 - Support for Dataset Generation in CLI

What's Changed

• Add dataset generation flow in CLI by @freddiev4 in #42
• Clean up dataset generation workflow code by @freddiev4 in #44
• Add human preferences into dataset generation process by @freddiev4 in #45
• Fix up eval scheduler url by @freddiev4 in #46
• Add dataset generation CLI cleanups & use seed data by @freddiev4 in #47
• Make dataset generation work with preferences & seed file by @freddiev4 in #49
• Pin numpy version by @freddiev4 in #50

Full Changelog: v0.0.4...v0.0.5

v0.0.4

What's Changed

• Updated the way users configure their external models to be more Pythonic

v0.0.3

What's Changed

• New functionality to transform job results into a Pandas dataframe and save to csv.