relari-ai/continuous-eval

Issues

• Metadata comparison for retrieval metrics

  #54 opened 9 months ago by yisz
  1

• LLMBasedFaithfulness does not work when using LLMs other than OpenAI

  #69 opened 6 months ago by kelvinchanwh
  2

• LLMBasedFaithfulness fails when response cannot be split into score and reasoning

  #71 opened 6 months ago by kelvinchanwh
  0

• Integration with DSPy

  #64 opened 7 months ago by pantonante
  4

• Add Custom Metric Creation

  #13 opened 7 months ago by yisz
  1

• Aggregate classification metrics

  #36 opened 7 months ago by yisz
  6

• Add CONTRIBUTING.md

  #40 opened 7 months ago by yisz
  1

• Langchain dependency switch

  #52 opened 8 months ago by yisz
  2

• Enhancement: Integration with LiteLLM

  #53 opened 9 months ago by rachittshah
  4

• Highlight LLM Based Custom Metric in ReadMe and Docs

  #51 opened 9 months ago by yisz
  0

• Handling context limit

  #50 opened 9 months ago by yisz
  0

• Doc fixes

  #47 opened 9 months ago by yisz
  0

• Add support for Cohere LLM

  #35 opened 9 months ago by yisz
  2

• Change default matching strategy to RougeChunkMatch

  #25 opened 10 months ago by yisz
  1

• No support for Azure OpenAI endpoints

  #31 opened 10 months ago by prasang-gupta
  2

• Fix typos in generation LLM metric docstrings

  #26 opened 10 months ago by yisz
  0

• Fix docs link on home page

  #27 opened 10 months ago by yisz
  0

• Should only throw error for missing OpenAI key if needed

  #17 opened a year ago by pantonante
  1

• Typo: Rename Blue to BLEU

  #18 opened a year ago by pantonante
  1

• Error handling for generation LLM metrics

  #19 opened a year ago by yisz
  0

• Add LLM-based Answer Relevance / Style Consistency

  #12 opened a year ago by yisz
  0

• Add Softmax Output for DebertaAnswerScores batch_calculate method

  #6 opened a year ago by satriowputra
  1

• Add BERT variations for faithfulness

  #5 opened a year ago by yisz
  0

• Batch processing for semantic metrics

  #2 opened a year ago by yisz
  0