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

Merge branch 'main' into eval_api_final

Browse source
This commit is contained in:
Xi Yan 2025-03-26 12:29:45 -07:00
commit bc0cd07008
79 changed files with 3257 additions and 2358 deletions
Download patch file Download diff file Expand all files Collapse all files

162
docs/_static/llama-stack-spec.html vendored
View file

@ -818,14 +818,7 @@
"delete": {
"responses": {
"200": {
"description": "OK",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/FileResponse"
}
}
}
"description": "OK"
},
"400": {
"$ref": "#/components/responses/BadRequest400"
@ -4002,22 +3995,33 @@
"type": "object",
"properties": {
"strategy": {
"$ref": "#/components/schemas/SamplingStrategy"
"$ref": "#/components/schemas/SamplingStrategy",
"description": "The sampling strategy."
},
"max_tokens": {
"type": "integer",
"default": 0
"default": 0,
"description": "The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."
},
"repetition_penalty": {
"type": "number",
"default": 1.0
"default": 1.0,
"description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."
},
"stop": {
"type": "array",
"items": {
"type": "string"
},
"description": "Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."
}
},
"additionalProperties": false,
"required": [
"strategy"
],
"title": "SamplingParams"
"title": "SamplingParams",
"description": "Sampling parameters."
},
"SamplingStrategy": {
"oneOf": [
@ -6078,46 +6082,6 @@
"title": "FileUploadResponse",
"description": "Response after initiating a file upload session."
},
"FileResponse": {
"type": "object",
"properties": {
"bucket": {
"type": "string",
"description": "Bucket under which the file is stored (valid chars: a-zA-Z0-9_-)"
},
"key": {
"type": "string",
"description": "Key under which the file is stored (valid chars: a-zA-Z0-9_-/.)"
},
"mime_type": {
"type": "string",
"description": "MIME type of the file"
},
"url": {
"type": "string",
"description": "Upload URL for the file contents"
},
"bytes": {
"type": "integer",
"description": "Size of the file in bytes"
},
"created_at": {
"type": "integer",
"description": "Timestamp of when the file was created"
}
},
"additionalProperties": false,
"required": [
"bucket",
"key",
"mime_type",
"url",
"bytes",
"created_at"
],
"title": "FileResponse",
"description": "Response representing a file entry."
},
"EmbeddingsRequest": {
"type": "object",
"properties": {
@ -6498,52 +6462,47 @@
"title": "URIDataSource",
"description": "A dataset that can be obtained from a URI."
},
"EqualityGrader": {
"FileResponse": {
"type": "object",
"properties": {
"type": {
"bucket": {
"type": "string",
"const": "equality",
"default": "equality"
"description": "Bucket under which the file is stored (valid chars: a-zA-Z0-9_-)"
},
"key": {
"type": "string",
"description": "Key under which the file is stored (valid chars: a-zA-Z0-9_-/.)"
},
"mime_type": {
"type": "string",
"description": "MIME type of the file"
},
"url": {
"type": "string",
"description": "Upload URL for the file contents"
},
"bytes": {
"type": "integer",
"description": "Size of the file in bytes"
},
"created_at": {
"type": "integer",
"description": "Timestamp of when the file was created"
}
},
"additionalProperties": false,
"required": [
"type"
"bucket",
"key",
"mime_type",
"url",
"bytes",
"created_at"
],
"title": "EqualityGrader"
"title": "FileResponse",
"description": "Response representing a file entry."
},
"FactualityGrader": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "factuality",
"default": "factuality"
}
},
"additionalProperties": false,
"required": [
"type"
],
"title": "FactualityGrader"
},
"FaithfulnessGrader": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "faithfulness",
"default": "faithfulness"
}
},
"additionalProperties": false,
"required": [
"type"
],
"title": "FaithfulnessGrader"
},
"Grader": {
"Model": {
"type": "object",
"properties": {
"identifier": {
@ -7895,6 +7854,31 @@
"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",
"cancelled"
],
"title": "JobStatus"
}
},
"additionalProperties": false,
"required": [
"job_id",
"status"
],
"title": "Job"
},
"ListAgentSessionsResponse": {
"type": "object",
"properties": {

131
docs/_static/llama-stack-spec.yaml vendored
View file

@ -557,10 +557,6 @@ paths:
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/FileResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@ -2764,16 +2760,33 @@ components:
properties:
strategy:
$ref: '#/components/schemas/SamplingStrategy'
description: The sampling strategy.
max_tokens:
type: integer
default: 0
description: >-
The maximum number of tokens that can be generated in the completion.
The token count of your prompt plus max_tokens cannot exceed the model's
context length.
repetition_penalty:
type: number
default: 1.0
description: >-
Number between -2.0 and 2.0. Positive values penalize new tokens based
on whether they appear in the text so far, increasing the model's likelihood
to talk about new topics.
stop:
type: array
items:
type: string
description: >-
Up to 4 sequences where the API will stop generating further tokens. The
returned text will not contain the stop sequence.
additionalProperties: false
required:
- strategy
title: SamplingParams
description: Sampling parameters.
SamplingStrategy:
oneOf:
- $ref: '#/components/schemas/GreedySamplingStrategy'
@ -4246,39 +4259,6 @@ components:
title: FileUploadResponse
description: >-
Response after initiating a file upload session.
FileResponse:
type: object
properties:
bucket:
type: string
description: >-
Bucket under which the file is stored (valid chars: a-zA-Z0-9_-)
key:
type: string
description: >-
Key under which the file is stored (valid chars: a-zA-Z0-9_-/.)
mime_type:
type: string
description: MIME type of the file
url:
type: string
description: Upload URL for the file contents
bytes:
type: integer
description: Size of the file in bytes
created_at:
type: integer
description: Timestamp of when the file was created
additionalProperties: false
required:
- bucket
- key
- mime_type
- url
- bytes
- created_at
title: FileResponse
description: Response representing a file entry.
EmbeddingsRequest:
type: object
properties:
@ -4550,40 +4530,40 @@ components:
title: URIDataSource
description: >-
A dataset that can be obtained from a URI.
EqualityGrader:
FileResponse:
type: object
properties:
type:
bucket:
type: string
const: equality
default: equality
description: >-
Bucket under which the file is stored (valid chars: a-zA-Z0-9_-)
key:
type: string
description: >-
Key under which the file is stored (valid chars: a-zA-Z0-9_-/.)
mime_type:
type: string
description: MIME type of the file
url:
type: string
description: Upload URL for the file contents
bytes:
type: integer
description: Size of the file in bytes
created_at:
type: integer
description: Timestamp of when the file was created
additionalProperties: false
required:
- type
title: EqualityGrader
FactualityGrader:
type: object
properties:
type:
type: string
const: factuality
default: factuality
additionalProperties: false
required:
- type
title: FactualityGrader
FaithfulnessGrader:
type: object
properties:
type:
type: string
const: faithfulness
default: faithfulness
additionalProperties: false
required:
- type
title: FaithfulnessGrader
Grader:
- bucket
- key
- mime_type
- url
- bytes
- created_at
title: FileResponse
description: Response representing a file entry.
Model:
type: object
properties:
identifier:
@ -5453,6 +5433,25 @@ 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
- cancelled
title: JobStatus
additionalProperties: false
required:
- job_id
- status
title: Job
ListAgentSessionsResponse:
type: object
properties: