diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html
index b0febbbef..71437bd90 100644
--- a/docs/_static/llama-stack-spec.html
+++ b/docs/_static/llama-stack-spec.html
@@ -2493,7 +2493,14 @@
"post": {
"responses": {
"200": {
- "description": "OK"
+ "description": "OK",
+ "content": {
+ "application/json": {
+ "schema": {
+ "$ref": "#/components/schemas/Dataset"
+ }
+ }
+ }
},
"400": {
"$ref": "#/components/responses/BadRequest400"
@@ -2511,7 +2518,7 @@
"tags": [
"Datasets"
],
- "description": "",
+ "description": "Register a new dataset through a file or",
"parameters": [],
"requestBody": {
"content": {
@@ -6831,81 +6838,6 @@
],
"title": "Benchmark"
},
- "AgentTurnInputType": {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "agent_turn_input",
- "default": "agent_turn_input"
- }
- },
- "additionalProperties": false,
- "required": [
- "type"
- ],
- "title": "AgentTurnInputType"
- },
- "ArrayType": {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "array",
- "default": "array"
- }
- },
- "additionalProperties": false,
- "required": [
- "type"
- ],
- "title": "ArrayType"
- },
- "BooleanType": {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "boolean",
- "default": "boolean"
- }
- },
- "additionalProperties": false,
- "required": [
- "type"
- ],
- "title": "BooleanType"
- },
- "ChatCompletionInputType": {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "chat_completion_input",
- "default": "chat_completion_input"
- }
- },
- "additionalProperties": false,
- "required": [
- "type"
- ],
- "title": "ChatCompletionInputType"
- },
- "CompletionInputType": {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "completion_input",
- "default": "completion_input"
- }
- },
- "additionalProperties": false,
- "required": [
- "type"
- ],
- "title": "CompletionInputType"
- },
"Dataset": {
"type": "object",
"properties": {
@@ -6923,14 +6855,11 @@
"const": "dataset",
"default": "dataset"
},
- "dataset_schema": {
- "type": "object",
- "additionalProperties": {
- "$ref": "#/components/schemas/ParamType"
- }
+ "schema": {
+ "$ref": "#/components/schemas/Schema"
},
- "url": {
- "$ref": "#/components/schemas/URL"
+ "uri": {
+ "type": "string"
},
"metadata": {
"type": "object",
@@ -6964,135 +6893,19 @@
"provider_resource_id",
"provider_id",
"type",
- "dataset_schema",
- "url",
+ "schema",
+ "uri",
"metadata"
],
"title": "Dataset"
},
- "JsonType": {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "json",
- "default": "json"
- }
- },
- "additionalProperties": false,
- "required": [
- "type"
+ "Schema": {
+ "type": "string",
+ "enum": [
+ "jsonl_messages"
],
- "title": "JsonType"
- },
- "NumberType": {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "number",
- "default": "number"
- }
- },
- "additionalProperties": false,
- "required": [
- "type"
- ],
- "title": "NumberType"
- },
- "ObjectType": {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "object",
- "default": "object"
- }
- },
- "additionalProperties": false,
- "required": [
- "type"
- ],
- "title": "ObjectType"
- },
- "ParamType": {
- "oneOf": [
- {
- "$ref": "#/components/schemas/StringType"
- },
- {
- "$ref": "#/components/schemas/NumberType"
- },
- {
- "$ref": "#/components/schemas/BooleanType"
- },
- {
- "$ref": "#/components/schemas/ArrayType"
- },
- {
- "$ref": "#/components/schemas/ObjectType"
- },
- {
- "$ref": "#/components/schemas/JsonType"
- },
- {
- "$ref": "#/components/schemas/UnionType"
- },
- {
- "$ref": "#/components/schemas/ChatCompletionInputType"
- },
- {
- "$ref": "#/components/schemas/CompletionInputType"
- },
- {
- "$ref": "#/components/schemas/AgentTurnInputType"
- }
- ],
- "discriminator": {
- "propertyName": "type",
- "mapping": {
- "string": "#/components/schemas/StringType",
- "number": "#/components/schemas/NumberType",
- "boolean": "#/components/schemas/BooleanType",
- "array": "#/components/schemas/ArrayType",
- "object": "#/components/schemas/ObjectType",
- "json": "#/components/schemas/JsonType",
- "union": "#/components/schemas/UnionType",
- "chat_completion_input": "#/components/schemas/ChatCompletionInputType",
- "completion_input": "#/components/schemas/CompletionInputType",
- "agent_turn_input": "#/components/schemas/AgentTurnInputType"
- }
- }
- },
- "StringType": {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "string",
- "default": "string"
- }
- },
- "additionalProperties": false,
- "required": [
- "type"
- ],
- "title": "StringType"
- },
- "UnionType": {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "union",
- "default": "union"
- }
- },
- "additionalProperties": false,
- "required": [
- "type"
- ],
- "title": "UnionType"
+ "title": "Schema",
+ "description": "Schema of the dataset. Each type has a different column format."
},
"Model": {
"type": "object",
@@ -7209,6 +7022,175 @@
"title": "PaginatedRowsResult",
"description": "A paginated list of rows from a dataset."
},
+ "AgentTurnInputType": {
+ "type": "object",
+ "properties": {
+ "type": {
+ "type": "string",
+ "const": "agent_turn_input",
+ "default": "agent_turn_input"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "type"
+ ],
+ "title": "AgentTurnInputType"
+ },
+ "ArrayType": {
+ "type": "object",
+ "properties": {
+ "type": {
+ "type": "string",
+ "const": "array",
+ "default": "array"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "type"
+ ],
+ "title": "ArrayType"
+ },
+ "BooleanType": {
+ "type": "object",
+ "properties": {
+ "type": {
+ "type": "string",
+ "const": "boolean",
+ "default": "boolean"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "type"
+ ],
+ "title": "BooleanType"
+ },
+ "ChatCompletionInputType": {
+ "type": "object",
+ "properties": {
+ "type": {
+ "type": "string",
+ "const": "chat_completion_input",
+ "default": "chat_completion_input"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "type"
+ ],
+ "title": "ChatCompletionInputType"
+ },
+ "CompletionInputType": {
+ "type": "object",
+ "properties": {
+ "type": {
+ "type": "string",
+ "const": "completion_input",
+ "default": "completion_input"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "type"
+ ],
+ "title": "CompletionInputType"
+ },
+ "JsonType": {
+ "type": "object",
+ "properties": {
+ "type": {
+ "type": "string",
+ "const": "json",
+ "default": "json"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "type"
+ ],
+ "title": "JsonType"
+ },
+ "NumberType": {
+ "type": "object",
+ "properties": {
+ "type": {
+ "type": "string",
+ "const": "number",
+ "default": "number"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "type"
+ ],
+ "title": "NumberType"
+ },
+ "ObjectType": {
+ "type": "object",
+ "properties": {
+ "type": {
+ "type": "string",
+ "const": "object",
+ "default": "object"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "type"
+ ],
+ "title": "ObjectType"
+ },
+ "ParamType": {
+ "oneOf": [
+ {
+ "$ref": "#/components/schemas/StringType"
+ },
+ {
+ "$ref": "#/components/schemas/NumberType"
+ },
+ {
+ "$ref": "#/components/schemas/BooleanType"
+ },
+ {
+ "$ref": "#/components/schemas/ArrayType"
+ },
+ {
+ "$ref": "#/components/schemas/ObjectType"
+ },
+ {
+ "$ref": "#/components/schemas/JsonType"
+ },
+ {
+ "$ref": "#/components/schemas/UnionType"
+ },
+ {
+ "$ref": "#/components/schemas/ChatCompletionInputType"
+ },
+ {
+ "$ref": "#/components/schemas/CompletionInputType"
+ },
+ {
+ "$ref": "#/components/schemas/AgentTurnInputType"
+ }
+ ],
+ "discriminator": {
+ "propertyName": "type",
+ "mapping": {
+ "string": "#/components/schemas/StringType",
+ "number": "#/components/schemas/NumberType",
+ "boolean": "#/components/schemas/BooleanType",
+ "array": "#/components/schemas/ArrayType",
+ "object": "#/components/schemas/ObjectType",
+ "json": "#/components/schemas/JsonType",
+ "union": "#/components/schemas/UnionType",
+ "chat_completion_input": "#/components/schemas/ChatCompletionInputType",
+ "completion_input": "#/components/schemas/CompletionInputType",
+ "agent_turn_input": "#/components/schemas/AgentTurnInputType"
+ }
+ }
+ },
"ScoringFn": {
"type": "object",
"properties": {
@@ -7272,6 +7254,36 @@
],
"title": "ScoringFn"
},
+ "StringType": {
+ "type": "object",
+ "properties": {
+ "type": {
+ "type": "string",
+ "const": "string",
+ "default": "string"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "type"
+ ],
+ "title": "StringType"
+ },
+ "UnionType": {
+ "type": "object",
+ "properties": {
+ "type": {
+ "type": "string",
+ "const": "union",
+ "default": "union"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "type"
+ ],
+ "title": "UnionType"
+ },
"Shield": {
"type": "object",
"properties": {
@@ -9242,23 +9254,39 @@
"RegisterDatasetRequest": {
"type": "object",
"properties": {
- "dataset_id": {
- "type": "string"
+ "schema": {
+ "$ref": "#/components/schemas/Schema",
+ "description": "The schema format of the dataset. One of - jsonl_messages: The dataset is a JSONL file with messages in column format"
},
- "dataset_schema": {
+ "uri": {
+ "type": "string",
+ "description": "The URI of the dataset. Examples: - file://mydata.jsonl - s3://mybucket/myfile.jsonl - https://mywebsite.com/myfile.jsonl - huggingface://tatsu-lab/alpaca"
+ },
+ "uri_params": {
"type": "object",
"additionalProperties": {
- "$ref": "#/components/schemas/ParamType"
- }
- },
- "url": {
- "$ref": "#/components/schemas/URL"
- },
- "provider_dataset_id": {
- "type": "string"
- },
- "provider_id": {
- "type": "string"
+ "oneOf": [
+ {
+ "type": "null"
+ },
+ {
+ "type": "boolean"
+ },
+ {
+ "type": "number"
+ },
+ {
+ "type": "string"
+ },
+ {
+ "type": "array"
+ },
+ {
+ "type": "object"
+ }
+ ]
+ },
+ "description": "The parameters for the URI. - E.g. If URL is a huggingface dataset, parameters could be uri_params={\"split\": \"train\"}"
},
"metadata": {
"type": "object",
@@ -9283,14 +9311,18 @@
"type": "object"
}
]
- }
+ },
+ "description": "The metadata for the dataset. - E.g. {\"description\": \"My dataset\"}"
+ },
+ "dataset_id": {
+ "type": "string",
+ "description": "The ID of the dataset. If not provided, a random ID will be generated."
}
},
"additionalProperties": false,
"required": [
- "dataset_id",
- "dataset_schema",
- "url"
+ "schema",
+ "uri"
],
"title": "RegisterDatasetRequest"
},
diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml
index 2985e6222..5f8d0e522 100644
--- a/docs/_static/llama-stack-spec.yaml
+++ b/docs/_static/llama-stack-spec.yaml
@@ -1682,6 +1682,10 @@ paths:
responses:
'200':
description: OK
+ content:
+ application/json:
+ schema:
+ $ref: '#/components/schemas/Dataset'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@@ -1694,7 +1698,7 @@ paths:
$ref: '#/components/responses/DefaultError'
tags:
- Datasets
- description: ''
+ description: Register a new dataset through a file or
parameters: []
requestBody:
content:
@@ -4727,61 +4731,6 @@ components:
- scoring_functions
- metadata
title: Benchmark
- AgentTurnInputType:
- type: object
- properties:
- type:
- type: string
- const: agent_turn_input
- default: agent_turn_input
- additionalProperties: false
- required:
- - type
- title: AgentTurnInputType
- ArrayType:
- type: object
- properties:
- type:
- type: string
- const: array
- default: array
- additionalProperties: false
- required:
- - type
- title: ArrayType
- BooleanType:
- type: object
- properties:
- type:
- type: string
- const: boolean
- default: boolean
- additionalProperties: false
- required:
- - type
- title: BooleanType
- ChatCompletionInputType:
- type: object
- properties:
- type:
- type: string
- const: chat_completion_input
- default: chat_completion_input
- additionalProperties: false
- required:
- - type
- title: ChatCompletionInputType
- CompletionInputType:
- type: object
- properties:
- type:
- type: string
- const: completion_input
- default: completion_input
- additionalProperties: false
- required:
- - type
- title: CompletionInputType
Dataset:
type: object
properties:
@@ -4795,12 +4744,10 @@ components:
type: string
const: dataset
default: dataset
- dataset_schema:
- type: object
- additionalProperties:
- $ref: '#/components/schemas/ParamType'
- url:
- $ref: '#/components/schemas/URL'
+ schema:
+ $ref: '#/components/schemas/Schema'
+ uri:
+ type: string
metadata:
type: object
additionalProperties:
@@ -4817,90 +4764,17 @@ components:
- provider_resource_id
- provider_id
- type
- - dataset_schema
- - url
+ - schema
+ - uri
- metadata
title: Dataset
- JsonType:
- type: object
- properties:
- type:
- type: string
- const: json
- default: json
- additionalProperties: false
- required:
- - type
- title: JsonType
- NumberType:
- type: object
- properties:
- type:
- type: string
- const: number
- default: number
- additionalProperties: false
- required:
- - type
- title: NumberType
- ObjectType:
- type: object
- properties:
- type:
- type: string
- const: object
- default: object
- additionalProperties: false
- required:
- - type
- title: ObjectType
- ParamType:
- oneOf:
- - $ref: '#/components/schemas/StringType'
- - $ref: '#/components/schemas/NumberType'
- - $ref: '#/components/schemas/BooleanType'
- - $ref: '#/components/schemas/ArrayType'
- - $ref: '#/components/schemas/ObjectType'
- - $ref: '#/components/schemas/JsonType'
- - $ref: '#/components/schemas/UnionType'
- - $ref: '#/components/schemas/ChatCompletionInputType'
- - $ref: '#/components/schemas/CompletionInputType'
- - $ref: '#/components/schemas/AgentTurnInputType'
- discriminator:
- propertyName: type
- mapping:
- string: '#/components/schemas/StringType'
- number: '#/components/schemas/NumberType'
- boolean: '#/components/schemas/BooleanType'
- array: '#/components/schemas/ArrayType'
- object: '#/components/schemas/ObjectType'
- json: '#/components/schemas/JsonType'
- union: '#/components/schemas/UnionType'
- chat_completion_input: '#/components/schemas/ChatCompletionInputType'
- completion_input: '#/components/schemas/CompletionInputType'
- agent_turn_input: '#/components/schemas/AgentTurnInputType'
- StringType:
- type: object
- properties:
- type:
- type: string
- const: string
- default: string
- additionalProperties: false
- required:
- - type
- title: StringType
- UnionType:
- type: object
- properties:
- type:
- type: string
- const: union
- default: union
- additionalProperties: false
- required:
- - type
- title: UnionType
+ Schema:
+ type: string
+ enum:
+ - jsonl_messages
+ title: Schema
+ description: >-
+ Schema of the dataset. Each type has a different column format.
Model:
type: object
properties:
@@ -4970,6 +4844,119 @@ components:
- total_count
title: PaginatedRowsResult
description: A paginated list of rows from a dataset.
+ AgentTurnInputType:
+ type: object
+ properties:
+ type:
+ type: string
+ const: agent_turn_input
+ default: agent_turn_input
+ additionalProperties: false
+ required:
+ - type
+ title: AgentTurnInputType
+ ArrayType:
+ type: object
+ properties:
+ type:
+ type: string
+ const: array
+ default: array
+ additionalProperties: false
+ required:
+ - type
+ title: ArrayType
+ BooleanType:
+ type: object
+ properties:
+ type:
+ type: string
+ const: boolean
+ default: boolean
+ additionalProperties: false
+ required:
+ - type
+ title: BooleanType
+ ChatCompletionInputType:
+ type: object
+ properties:
+ type:
+ type: string
+ const: chat_completion_input
+ default: chat_completion_input
+ additionalProperties: false
+ required:
+ - type
+ title: ChatCompletionInputType
+ CompletionInputType:
+ type: object
+ properties:
+ type:
+ type: string
+ const: completion_input
+ default: completion_input
+ additionalProperties: false
+ required:
+ - type
+ title: CompletionInputType
+ JsonType:
+ type: object
+ properties:
+ type:
+ type: string
+ const: json
+ default: json
+ additionalProperties: false
+ required:
+ - type
+ title: JsonType
+ NumberType:
+ type: object
+ properties:
+ type:
+ type: string
+ const: number
+ default: number
+ additionalProperties: false
+ required:
+ - type
+ title: NumberType
+ ObjectType:
+ type: object
+ properties:
+ type:
+ type: string
+ const: object
+ default: object
+ additionalProperties: false
+ required:
+ - type
+ title: ObjectType
+ ParamType:
+ oneOf:
+ - $ref: '#/components/schemas/StringType'
+ - $ref: '#/components/schemas/NumberType'
+ - $ref: '#/components/schemas/BooleanType'
+ - $ref: '#/components/schemas/ArrayType'
+ - $ref: '#/components/schemas/ObjectType'
+ - $ref: '#/components/schemas/JsonType'
+ - $ref: '#/components/schemas/UnionType'
+ - $ref: '#/components/schemas/ChatCompletionInputType'
+ - $ref: '#/components/schemas/CompletionInputType'
+ - $ref: '#/components/schemas/AgentTurnInputType'
+ discriminator:
+ propertyName: type
+ mapping:
+ string: '#/components/schemas/StringType'
+ number: '#/components/schemas/NumberType'
+ boolean: '#/components/schemas/BooleanType'
+ array: '#/components/schemas/ArrayType'
+ object: '#/components/schemas/ObjectType'
+ json: '#/components/schemas/JsonType'
+ union: '#/components/schemas/UnionType'
+ chat_completion_input: '#/components/schemas/ChatCompletionInputType'
+ completion_input: '#/components/schemas/CompletionInputType'
+ agent_turn_input: '#/components/schemas/AgentTurnInputType'
ScoringFn:
type: object
properties:
@@ -5008,6 +4995,28 @@ components:
- metadata
- return_type
title: ScoringFn
+ StringType:
+ type: object
+ properties:
+ type:
+ type: string
+ const: string
+ default: string
+ additionalProperties: false
+ required:
+ - type
+ title: StringType
+ UnionType:
+ type: object
+ properties:
+ type:
+ type: string
+ const: union
+ default: union
+ additionalProperties: false
+ required:
+ - type
+ title: UnionType
Shield:
type: object
properties:
@@ -6262,18 +6271,29 @@ components:
RegisterDatasetRequest:
type: object
properties:
- dataset_id:
+ schema:
+ $ref: '#/components/schemas/Schema'
+ description: >-
+ The schema format of the dataset. One of - jsonl_messages: The dataset
+ is a JSONL file with messages in column format
+ uri:
type: string
- dataset_schema:
+ description: >-
+ The URI of the dataset. Examples: - file://mydata.jsonl - s3://mybucket/myfile.jsonl
+ - https://mywebsite.com/myfile.jsonl - huggingface://tatsu-lab/alpaca
+ uri_params:
type: object
additionalProperties:
- $ref: '#/components/schemas/ParamType'
- url:
- $ref: '#/components/schemas/URL'
- provider_dataset_id:
- type: string
- provider_id:
- type: string
+ oneOf:
+ - type: 'null'
+ - type: boolean
+ - type: number
+ - type: string
+ - type: array
+ - type: object
+ description: >-
+ The parameters for the URI. - E.g. If URL is a huggingface dataset, parameters
+ could be uri_params={"split": "train"}
metadata:
type: object
additionalProperties:
@@ -6284,11 +6304,16 @@ components:
- type: string
- type: array
- type: object
+ description: >-
+ The metadata for the dataset. - E.g. {"description": "My dataset"}
+ dataset_id:
+ type: string
+ description: >-
+ The ID of the dataset. If not provided, a random ID will be generated.
additionalProperties: false
required:
- - dataset_id
- - dataset_schema
- - url
+ - schema
+ - uri
title: RegisterDatasetRequest
RegisterModelRequest:
type: object