unitxt issues

2

Hi, We have a judgement metric that is not rating based but a descriptive one (we want the judge to describe the errors in the prediction). There is no existing...

ShirApp

Refactor unit tests to use only local data

elronbandel

Cards for the Real MM RAG datasets

assaftibm

Add ToRR Benchmark Readme file

Added a simple, dedicated README file with basic details and run instructions for the ToRR benchmark in Unitxt.

csrajmohan

Documenation updates

yoavkatz

Support inference engine initialization with an existing ibm_watsonx_ai.client.APIClient

Requirement: support an `ibm_watsonx_ai.client.APIClient` with specially defined headers within an inference engine. Motivation: This is required for the use of such inference engines within `LLMaaJ` based metrics.

matanor