v1.4.3

What's Changed

• Fix for boolean evals to return 0 or 1 by @vivek-athina in #66
• modify prompt execution step by @akshat-g in #64

Full Changelog: v1.4.0...v1.4.3

v1.2.15

What's Changed

• add chat history to context contains enough information evaluator ATH-1029 by @akshat-g in #52

Full Changelog: v1.2.14...v1.2.15

Release v1.2.14

Fix context similarity grounded eval

v1.2.13

• Adds Groundedness Eval to LLM EvalType enum

v1.2.12

What's Changed

• Vivek/ath 1124 bug fixes in safety evals by @vivek-athina in #50

Full Changelog: v1.2.11...v1.2.12

v1.2.11

What's Changed

• mistral large model name fixed and version bump by @vivek-athina in #49

Full Changelog: v1.2.10...v1.2.11

v1.2.10

What's Changed

• added newer models by @vivek-athina in #47

Full Changelog: v1.2.9...v1.2.10

v1.2.9

What's Changed

• Remove SDK print statement "You can view the results at app.athina.ai/develop/request" by @akshat-g in #46
• Remove expected response from the RAGAS evaluators that don't require expected_response

Full Changelog: v1.2.8...v1.2.9

v1.2.8

• Add interface to create dataset in athina
• Add interface to add rows to the existing dataset in athina