elenasamuylova

Results 23 issues of elenasamuylova

- Added a Tutorial and a Quickstart for LLM evals - Misc minor fixes

Added an example for descriptors tab in the UI.

About Hacktoberfest contributions: https://github.com/evidentlyai/evidently/wiki/Hacktoberfest-2024 **Descripton**. The BLEU (Bilingual Evaluation Understudy) metric is used to evaluate the quality of machine-generated text, typically translations, by comparing it to the reference texts. BLEU...

enhancement
hacktoberfest

About Hacktoberfest contributions: https://github.com/evidentlyai/evidently/wiki/Hacktoberfest-2024 **Description:** Add the `JSONSchemaMatch()` descriptor that will evaluate whether a returned text is a JSON object with a schema that matches a structure specified by the...

enhancement
hacktoberfest

About Hacktoberfest contributions: https://github.com/evidentlyai/evidently/wiki/Hacktoberfest-2024 **Description**: Implement BERTScore - a metric that computes a similarity score for each token in the candidate sentence with each token in the reference sentence. Paper:...

enhancement
hacktoberfest

# Add a New `WordNoMatch` Descriptor to Evidently About Hacktoberfest contributions: https://github.com/evidentlyai/evidently/wiki/Hacktoberfest-2024 ## Description: Evidently already has an `ExcludesWords()` descriptor that checks if the text does **not** contain any specified...

enhancement
hacktoberfest

About Hacktoberfest contributions: https://github.com/evidentlyai/evidently/wiki/Hacktoberfest-2024 **Description** Add the `IsValidPython()` descriptor that checks whether the text in a specified column contains valid Python code. This descriptor returns `True` for valid Python code...

enhancement
hacktoberfest

# Add a New `WordMatch` Descriptor to Evidently About Hacktoberfest contributions: https://github.com/evidentlyai/evidently/wiki/Hacktoberfest-2024 ## Description: Evidently already has an `IncludesWords()` descriptor that checks if the text contains `any` (by default) or...

enhancement
hacktoberfest

About Hacktoberfest contributions: https://github.com/evidentlyai/evidently/wiki/Hacktoberfest-2024 **Description** The ROUGE (Recall-Oriented Understudy for Gisting Evaluation) metric evaluates the quality of a generated text by comparing it to a reference text (typically a summary)....

enhancement
hacktoberfest

About Hacktoberfest contributions: https://github.com/evidentlyai/evidently/wiki/Hacktoberfest-2024 **Description**: Add a new `ContainsLink` descriptor that checks if the text contains any valid hyperlinks. It returns True if at least one valid URL is detected...

enhancement
hacktoberfest