phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 08:20:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'eval_api_final' into delete_eval_scoring_scoring_fn

Browse source
This commit is contained in:
Xi Yan 2025-03-19 09:50:40 -07:00
commit e23531c9d0
4 changed files with 50 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

37
docs/_static/llama-stack-spec.html vendored
View file

@ -7617,7 +7617,7 @@
"EvaluationResponse": {
"type": "object",
"properties": {
"generations": {
"result_rows": {
"type": "array",
"items": {
"type": "object",
@ -7644,20 +7644,39 @@
]
}
},
"description": "The generations in rows for the evaluation."
"description": "The result data containing inputs, generations and grades in each row."
},
"scores": {
"grades": {
"type": "object",
"additionalProperties": {
"$ref": "#/components/schemas/ScoringResult"
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
},
"description": "The scores for the evaluation. Map of grader id to ScoringResult."
"description": "Map of grader id to aggregated value."
}
},
"additionalProperties": false,
"required": [
"generations",
"scores"
"result_rows",
"grades"
],
"title": "EvaluationResponse",
"description": "A response to an inline evaluation."
@ -9313,14 +9332,14 @@
"properties": {
"dataset_id": {
"type": "string",
"description": "The ID of the dataset to be used to run the benchmark."
"description": "The ID of the dataset to be used to run the benchmark. ID obtained through `datasets.register()`"
},
"grader_ids": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of grader ids to use for this benchmark."
"description": "List of grader ids to use for this benchmark. ID obtained through `graders.register()`"
},
"benchmark_id": {
"type": "string",