API ReferenceEvaluations

Results Partial Update

PATCH handler with superadmin lock and field protection.

Checks:

  1. Object lock (is_managed=True -> non-superadmins can’t modify)
  2. Field protection (non-superadmins can’t modify specific fields)

Authentication

AuthorizationBearer
JWT access token or Respan API key

Path parameters

idintegerRequired

Request

This endpoint expects an object.
human_text_valuestringOptional
projectstring or nullOptional>=1 character
eval_result_unique_idstringOptional1-255 characters
typeenumOptional
  • llm - Llm
  • code - Code
  • human - Human
  • function - Function
  • human_numerical - Human Numerical
  • human_categorical - Human Categorical
  • human_boolean - Human Boolean
  • human_text - Human Text
  • custom - Custom
environmentstringOptional1-30 characters
unique_organization_idstringOptional<=255 characters
evaluator_slugstringOptional<=255 characters
evaluator_namestring or nullOptional<=255 characters
scorerstringOptional1-255 characters
workflow_version_idstringOptional<=255 characters
sourcestringOptional<=64 characters
costdoubleOptional
evaluation_identifierstring or nullOptional<=255 characters
log_unique_idstring or nullOptional<=100 characters
customer_identifierstring or nullOptional<=254 characters
eval_set_idstring or nullOptional<=255 characters
log_timestampdatetime or nullOptional
prompt_version_idstring or nullOptional<=70 characters
pipeline_run_idstringOptional<=255 characters
automation_idstring or nullOptional<=255 characters
primary_scoredouble or nullOptional
string_valuestring or nullOptional
json_valuestringOptional
boolean_valueboolean or nullOptional
categorical_valuelist of stringsOptional
secondary_scoredouble or nullOptional
tertiary_scoredouble or nullOptional
quaternary_scoredouble or nullOptional
score_mappinganyOptional
human_numerical_valuedouble or nullOptional
human_categorical_valuestring or nullOptional1-100 characters
passedboolean or nullOptional
statusenumOptional
  • pending - Pending
  • completed - Completed
  • failed - Failed
error_messagestring or nullOptional
storage_object_keystringOptional1-255 characters
organizationintegerOptional
evaluationstring or nullOptional>=1 character
annotation_configstring or nullOptional>=1 character
loginteger or nullOptional

Response

idstringRead-only
evaluation_idstringRead-only
resultsstringRead-only
evaluatorobject
Mixin for internal evaluator serializers that work with full configuration format.
results_idintegerRead-only
inputsstringRead-only
created_atdatetimeRead-only
updated_atdatetimeRead-only
eval_classenum
  • ragas_faithfulness - ragas_faithfulness
  • ragas_noise_sensitivity - ragas_noise_sensitivity
  • ragas_response_relevancy - ragas_response_relevancy
  • ragas_answer_relevancy - ragas_answer_relevancy
  • ragas_context_precision - ragas_context_precision
  • ragas_context_recall - ragas_context_recall
  • ragas_context_entity_recall - ragas_context_entity_recall
  • ragas_factual_correctness - ragas_factual_correctness
  • ragas_semantic_similarity - ragas_semantic_similarity
  • ragas_non_llm_string_similarity - ragas_non_llm_string_similarity
  • ragas_non_llm_string_presence - ragas_non_llm_string_presence
  • ragas_non_llm_exact_match - ragas_non_llm_exact_match
  • relari_llm_based_custom_metric - relari_llm_based_custom_metric
  • relari_llm_based_answer_correctness - relari_llm_based_answer_correctness
  • keywordsai_custom_evaluator - keywordsai_custom_evaluator
  • keywordsai_custom_llm - keywordsai_custom_llm
  • output_char_count - output_char_count
  • output_word_count - output_word_count
  • custom_code - custom_code
updated_byinteger or nullRead-only
organizationinteger
human_text_valuestring
projectstring or null
eval_result_unique_idstring<=255 characters
typeenum
  • llm - Llm
  • code - Code
  • human - Human
  • function - Function
  • human_numerical - Human Numerical
  • human_categorical - Human Categorical
  • human_boolean - Human Boolean
  • human_text - Human Text
  • custom - Custom
environmentstring<=30 characters
unique_organization_idstring<=255 characters
evaluator_slugstring<=255 characters
evaluator_namestring or null<=255 characters
scorerstring<=255 characters
workflow_version_idstring<=255 characters
sourcestring<=64 characters
costdouble
evaluation_identifierstring or null<=255 characters
log_unique_idstring or null<=100 characters
customer_identifierstring or null<=254 characters
eval_set_idstring or null<=255 characters
log_timestampdatetime or null
prompt_version_idstring or null<=70 characters
pipeline_run_idstring<=255 characters
automation_idstring or null<=255 characters
primary_scoredouble or null
string_valuestring or null
json_valuestring
boolean_valueboolean or null
categorical_valuelist of strings
secondary_scoredouble or null
tertiary_scoredouble or null
quaternary_scoredouble or null
score_mappingany
human_numerical_valuedouble or null
human_categorical_valuestring or null<=100 characters
passedboolean or null
statusenum
  • pending - Pending
  • completed - Completed
  • failed - Failed
error_messagestring or null
storage_object_keystring<=255 characters
evaluationstring or null
annotation_configstring or null
loginteger or null