phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

merge

Browse source
This commit is contained in:
Xi Yan 2025-03-23 15:48:14 -07:00
commit a54d757ade
197 changed files with 9392 additions and 3089 deletions
Download patch file Download diff file Expand all files Collapse all files

523
docs/_static/llama-stack-spec.yaml vendored
View file

@ -1562,6 +1562,109 @@ 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:
@ -1820,7 +1923,7 @@ paths:
default:
$ref: '#/components/responses/DefaultError'
tags:
- Models
- Providers
description: ''
parameters: []
post:
@ -2841,30 +2944,34 @@ components:
title: BuiltinTool
- type: string
arguments:
type: object
additionalProperties:
oneOf:
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
- type: array
items:
oneOf:
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
- type: object
additionalProperties:
oneOf:
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
oneOf:
- type: string
- type: object
additionalProperties:
oneOf:
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
- type: array
items:
oneOf:
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
- type: object
additionalProperties:
oneOf:
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
arguments_json:
type: string
additionalProperties: false
required:
- call_id
@ -4341,6 +4448,252 @@ 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:
@ -5098,7 +5451,6 @@ components:
- in_progress
- failed
- scheduled
- cancelled
title: JobStatus
scheduled_at:
type: string
@ -5373,6 +5725,7 @@ components:
properties:
document_id:
type: string
description: The unique identifier for the document.
content:
oneOf:
- type: string
@ -5381,8 +5734,10 @@ components:
items:
$ref: '#/components/schemas/InterleavedContentItem'
- $ref: '#/components/schemas/URL'
description: The content of the document.
mime_type:
type: string
description: The MIME type of the document.
metadata:
type: object
additionalProperties:
@ -5393,12 +5748,15 @@ components:
- type: string
- type: array
- type: object
description: Additional metadata for the document.
additionalProperties: false
required:
- document_id
- content
- metadata
title: RAGDocument
description: >-
A document to be used for document ingestion in the RAG Tool.
InsertRequest:
type: object
properties:
@ -5516,8 +5874,6 @@ components:
- type: array
- type: object
additionalProperties: false
required:
- content
title: ToolInvocationResult
IterrowsResponse:
type: object
@ -5545,6 +5901,24 @@ 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:
@ -6610,9 +6984,8 @@ components:
description: The candidate to evaluate.
additionalProperties: false
required:
- task
- candidate
title: RunRequest
- benchmark_config
title: RunEvalRequest
RunShieldRequest:
type: object
properties:
@ -6685,6 +7058,90 @@ 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'
- $ref: '#/components/schemas/QATFinetuningConfig'
discriminator:
propertyName: type
mapping:
LoRA: '#/components/schemas/LoraFinetuningConfig'
QAT: '#/components/schemas/QATFinetuningConfig'
LoraFinetuningConfig:
type: object
properties:
@ -6768,9 +7225,7 @@ components:
checkpoint_dir:
type: string
algorithm_config:
oneOf:
- $ref: '#/components/schemas/LoraFinetuningConfig'
- $ref: '#/components/schemas/QATFinetuningConfig'
$ref: '#/components/schemas/AlgorithmConfig'
additionalProperties: false
required:
- job_uuid