TRtraceloop
evaluators

Execute semantic-similarity evaluator

Changed on

Calculate semantic similarity between completion and reference

Request Body:

  • input.completion (string, required): The completion text to compare
  • input.reference (string, required): The reference text to compare against
post/v2/evaluators/semantic-similarity/execute

Request

Request body

Example request

{
  "input": {
    "completion": "The cat sat on the mat.",
    "reference": "A feline was resting on the rug."
  }
}

Response

OK

similarity_scorenumber

Example response

{
  "similarity_score": 0.92
}

Changes