forked from phoenix-oss/llama-stack-mirror
precommit
This commit is contained in:
Xi Yan
parent
45f6d5cd08
commit
3f8c7a584a
8 changed files with 31 additions and 1037 deletions
452
docs/_static/llama-stack-spec.yaml
vendored
452
docs/_static/llama-stack-spec.yaml
vendored
|
|
@ -1562,109 +1562,6 @@ paths:
|
|||
required: false
|
||||
schema:
|
||||
type: integer
|
||||
/v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}:
|
||||
get:
|
||||
responses:
|
||||
'200':
|
||||
description: The status of the evaluationjob.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/Job'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Eval
|
||||
description: Get the status of a job.
|
||||
parameters:
|
||||
- name: benchmark_id
|
||||
in: path
|
||||
description: >-
|
||||
The ID of the benchmark to run the evaluation on.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
- name: job_id
|
||||
in: path
|
||||
description: The ID of the job to get the status of.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
delete:
|
||||
responses:
|
||||
'200':
|
||||
description: OK
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Eval
|
||||
description: Cancel a job.
|
||||
parameters:
|
||||
- name: benchmark_id
|
||||
in: path
|
||||
description: >-
|
||||
The ID of the benchmark to run the evaluation on.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
- name: job_id
|
||||
in: path
|
||||
description: The ID of the job to cancel.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
/v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result:
|
||||
get:
|
||||
responses:
|
||||
'200':
|
||||
description: The result of the job.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/EvaluateResponse'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Eval
|
||||
description: Get the result of a job.
|
||||
parameters:
|
||||
- name: benchmark_id
|
||||
in: path
|
||||
description: >-
|
||||
The ID of the benchmark to run the evaluation on.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
- name: job_id
|
||||
in: path
|
||||
description: The ID of the job to get the result of.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
/v1/agents/{agent_id}/sessions:
|
||||
get:
|
||||
responses:
|
||||
|
|
@ -1923,7 +1820,7 @@ paths:
|
|||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Providers
|
||||
- Models
|
||||
description: ''
|
||||
parameters: []
|
||||
post:
|
||||
|
|
@ -1974,7 +1871,7 @@ paths:
|
|||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Inspect
|
||||
- Providers
|
||||
description: ''
|
||||
parameters: []
|
||||
/v1/inspect/routes:
|
||||
|
|
@ -4448,252 +4345,6 @@ components:
|
|||
title: EmbeddingsResponse
|
||||
description: >-
|
||||
Response containing generated embeddings.
|
||||
AgentCandidate:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: agent
|
||||
default: agent
|
||||
config:
|
||||
$ref: '#/components/schemas/AgentConfig'
|
||||
description: >-
|
||||
The configuration for the agent candidate.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
- config
|
||||
title: AgentCandidate
|
||||
description: An agent candidate for evaluation.
|
||||
AggregationFunctionType:
|
||||
type: string
|
||||
enum:
|
||||
- average
|
||||
- weighted_average
|
||||
- median
|
||||
- categorical_count
|
||||
- accuracy
|
||||
title: AggregationFunctionType
|
||||
BasicScoringFnParams:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: basic
|
||||
default: basic
|
||||
aggregation_functions:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/AggregationFunctionType'
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
title: BasicScoringFnParams
|
||||
BenchmarkConfig:
|
||||
type: object
|
||||
properties:
|
||||
eval_candidate:
|
||||
$ref: '#/components/schemas/EvalCandidate'
|
||||
description: The candidate to evaluate.
|
||||
scoring_params:
|
||||
type: object
|
||||
additionalProperties:
|
||||
$ref: '#/components/schemas/ScoringFnParams'
|
||||
description: >-
|
||||
Map between scoring function id and parameters for each scoring function
|
||||
you want to run
|
||||
num_examples:
|
||||
type: integer
|
||||
description: >-
|
||||
(Optional) The number of examples to evaluate. If not provided, all examples
|
||||
in the dataset will be evaluated
|
||||
additionalProperties: false
|
||||
required:
|
||||
- eval_candidate
|
||||
- scoring_params
|
||||
title: BenchmarkConfig
|
||||
description: >-
|
||||
A benchmark configuration for evaluation.
|
||||
EvalCandidate:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/ModelCandidate'
|
||||
- $ref: '#/components/schemas/AgentCandidate'
|
||||
discriminator:
|
||||
propertyName: type
|
||||
mapping:
|
||||
model: '#/components/schemas/ModelCandidate'
|
||||
agent: '#/components/schemas/AgentCandidate'
|
||||
LLMAsJudgeScoringFnParams:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: llm_as_judge
|
||||
default: llm_as_judge
|
||||
judge_model:
|
||||
type: string
|
||||
prompt_template:
|
||||
type: string
|
||||
judge_score_regexes:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
aggregation_functions:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/AggregationFunctionType'
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
- judge_model
|
||||
title: LLMAsJudgeScoringFnParams
|
||||
ModelCandidate:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: model
|
||||
default: model
|
||||
model:
|
||||
type: string
|
||||
description: The model ID to evaluate.
|
||||
sampling_params:
|
||||
$ref: '#/components/schemas/SamplingParams'
|
||||
description: The sampling parameters for the model.
|
||||
system_message:
|
||||
$ref: '#/components/schemas/SystemMessage'
|
||||
description: >-
|
||||
(Optional) The system message providing instructions or context to the
|
||||
model.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
- model
|
||||
- sampling_params
|
||||
title: ModelCandidate
|
||||
description: A model candidate for evaluation.
|
||||
RegexParserScoringFnParams:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: regex_parser
|
||||
default: regex_parser
|
||||
parsing_regexes:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
aggregation_functions:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/AggregationFunctionType'
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
title: RegexParserScoringFnParams
|
||||
ScoringFnParams:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/LLMAsJudgeScoringFnParams'
|
||||
- $ref: '#/components/schemas/RegexParserScoringFnParams'
|
||||
- $ref: '#/components/schemas/BasicScoringFnParams'
|
||||
discriminator:
|
||||
propertyName: type
|
||||
mapping:
|
||||
llm_as_judge: '#/components/schemas/LLMAsJudgeScoringFnParams'
|
||||
regex_parser: '#/components/schemas/RegexParserScoringFnParams'
|
||||
basic: '#/components/schemas/BasicScoringFnParams'
|
||||
EvaluateRowsRequest:
|
||||
type: object
|
||||
properties:
|
||||
input_rows:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: The rows to evaluate.
|
||||
scoring_functions:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: >-
|
||||
The scoring functions to use for the evaluation.
|
||||
benchmark_config:
|
||||
$ref: '#/components/schemas/BenchmarkConfig'
|
||||
description: The configuration for the benchmark.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- input_rows
|
||||
- scoring_functions
|
||||
- benchmark_config
|
||||
title: EvaluateRowsRequest
|
||||
EvaluateResponse:
|
||||
type: object
|
||||
properties:
|
||||
generations:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: The generations from the evaluation.
|
||||
scores:
|
||||
type: object
|
||||
additionalProperties:
|
||||
$ref: '#/components/schemas/ScoringResult'
|
||||
description: The scores from the evaluation.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- generations
|
||||
- scores
|
||||
title: EvaluateResponse
|
||||
description: The response from an evaluation.
|
||||
ScoringResult:
|
||||
type: object
|
||||
properties:
|
||||
score_rows:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: >-
|
||||
The scoring result for each row. Each row is a map of column name to value.
|
||||
aggregated_results:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: Map of metric name to aggregated value
|
||||
additionalProperties: false
|
||||
required:
|
||||
- score_rows
|
||||
- aggregated_results
|
||||
title: ScoringResult
|
||||
description: A scoring result for a single row.
|
||||
Agent:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -5451,6 +5102,7 @@ components:
|
|||
- in_progress
|
||||
- failed
|
||||
- scheduled
|
||||
- cancelled
|
||||
title: JobStatus
|
||||
scheduled_at:
|
||||
type: string
|
||||
|
|
@ -5901,24 +5553,6 @@ components:
|
|||
- data
|
||||
title: IterrowsResponse
|
||||
description: A paginated list of rows from a dataset.
|
||||
Job:
|
||||
type: object
|
||||
properties:
|
||||
job_id:
|
||||
type: string
|
||||
status:
|
||||
type: string
|
||||
enum:
|
||||
- completed
|
||||
- in_progress
|
||||
- failed
|
||||
- scheduled
|
||||
title: JobStatus
|
||||
additionalProperties: false
|
||||
required:
|
||||
- job_id
|
||||
- status
|
||||
title: Job
|
||||
ListAgentSessionsResponse:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -6984,8 +6618,9 @@ components:
|
|||
description: The candidate to evaluate.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- benchmark_config
|
||||
title: RunEvalRequest
|
||||
- task
|
||||
- candidate
|
||||
title: RunRequest
|
||||
RunShieldRequest:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -7058,81 +6693,6 @@ components:
|
|||
- attributes_to_save
|
||||
- dataset_id
|
||||
title: SaveSpansToDatasetRequest
|
||||
ScoreRequest:
|
||||
type: object
|
||||
properties:
|
||||
input_rows:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: The rows to score.
|
||||
scoring_functions:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/ScoringFnParams'
|
||||
- type: 'null'
|
||||
description: >-
|
||||
The scoring functions to use for the scoring.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- input_rows
|
||||
- scoring_functions
|
||||
title: ScoreRequest
|
||||
ScoreResponse:
|
||||
type: object
|
||||
properties:
|
||||
results:
|
||||
type: object
|
||||
additionalProperties:
|
||||
$ref: '#/components/schemas/ScoringResult'
|
||||
description: >-
|
||||
A map of scoring function name to ScoringResult.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- results
|
||||
title: ScoreResponse
|
||||
description: The response from scoring.
|
||||
ScoreBatchRequest:
|
||||
type: object
|
||||
properties:
|
||||
dataset_id:
|
||||
type: string
|
||||
scoring_functions:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/ScoringFnParams'
|
||||
- type: 'null'
|
||||
save_results_dataset:
|
||||
type: boolean
|
||||
additionalProperties: false
|
||||
required:
|
||||
- dataset_id
|
||||
- scoring_functions
|
||||
- save_results_dataset
|
||||
title: ScoreBatchRequest
|
||||
ScoreBatchResponse:
|
||||
type: object
|
||||
properties:
|
||||
dataset_id:
|
||||
type: string
|
||||
results:
|
||||
type: object
|
||||
additionalProperties:
|
||||
$ref: '#/components/schemas/ScoringResult'
|
||||
additionalProperties: false
|
||||
required:
|
||||
- results
|
||||
title: ScoreBatchResponse
|
||||
AlgorithmConfig:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/LoraFinetuningConfig'
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue