diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html
index 0e5996e21..ae6a01e15 100644
--- a/docs/_static/llama-stack-spec.html
+++ b/docs/_static/llama-stack-spec.html
@@ -40,75 +40,7 @@
}
],
"paths": {
- "/v1/datasetio/rows": {
- "get": {
- "responses": {
- "200": {
- "description": "OK",
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/PaginatedRowsResult"
- }
- }
- }
- },
- "400": {
- "$ref": "#/components/responses/BadRequest400"
- },
- "429": {
- "$ref": "#/components/responses/TooManyRequests429"
- },
- "500": {
- "$ref": "#/components/responses/InternalServerError500"
- },
- "default": {
- "$ref": "#/components/responses/DefaultError"
- }
- },
- "tags": [
- "DatasetIO"
- ],
- "description": "Get a paginated list of rows from a dataset.",
- "parameters": [
- {
- "name": "dataset_id",
- "in": "query",
- "description": "The ID of the dataset to get the rows from.",
- "required": true,
- "schema": {
- "type": "string"
- }
- },
- {
- "name": "rows_in_page",
- "in": "query",
- "description": "The number of rows to get per page.",
- "required": true,
- "schema": {
- "type": "integer"
- }
- },
- {
- "name": "page_token",
- "in": "query",
- "description": "The token to get the next page of rows.",
- "required": false,
- "schema": {
- "type": "string"
- }
- },
- {
- "name": "filter_condition",
- "in": "query",
- "description": "(Optional) A condition to filter the rows by.",
- "required": false,
- "schema": {
- "type": "string"
- }
- }
- ]
- },
+ "/v1/datasets/{dataset_id}/rows": {
"post": {
"responses": {
"200": {
@@ -131,7 +63,16 @@
"DatasetIO"
],
"description": "",
- "parameters": [],
+ "parameters": [
+ {
+ "name": "dataset_id",
+ "in": "path",
+ "required": true,
+ "schema": {
+ "type": "string"
+ }
+ }
+ ],
"requestBody": {
"content": {
"application/json": {
@@ -2194,6 +2135,76 @@
}
}
},
+ "/v1/datasets/{dataset_id}/iterrows": {
+ "get": {
+ "responses": {
+ "200": {
+ "description": "OK",
+ "content": {
+ "application/json": {
+ "schema": {
+ "$ref": "#/components/schemas/PaginatedRowsResult"
+ }
+ }
+ }
+ },
+ "400": {
+ "$ref": "#/components/responses/BadRequest400"
+ },
+ "429": {
+ "$ref": "#/components/responses/TooManyRequests429"
+ },
+ "500": {
+ "$ref": "#/components/responses/InternalServerError500"
+ },
+ "default": {
+ "$ref": "#/components/responses/DefaultError"
+ }
+ },
+ "tags": [
+ "DatasetIO"
+ ],
+ "description": "Get a paginated list of rows from a dataset.",
+ "parameters": [
+ {
+ "name": "dataset_id",
+ "in": "path",
+ "description": "The ID of the dataset to get the rows from.",
+ "required": true,
+ "schema": {
+ "type": "string"
+ }
+ },
+ {
+ "name": "rows_in_page",
+ "in": "query",
+ "description": "The number of rows to get per page.",
+ "required": true,
+ "schema": {
+ "type": "integer"
+ }
+ },
+ {
+ "name": "page_token",
+ "in": "query",
+ "description": "The token to get the next page of rows.",
+ "required": false,
+ "schema": {
+ "type": "string"
+ }
+ },
+ {
+ "name": "filter_condition",
+ "in": "query",
+ "description": "(Optional) A condition to filter the rows by.",
+ "required": false,
+ "schema": {
+ "type": "string"
+ }
+ }
+ ]
+ }
+ },
"/v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}": {
"get": {
"responses": {
@@ -3789,9 +3800,6 @@
"AppendRowsRequest": {
"type": "object",
"properties": {
- "dataset_id": {
- "type": "string"
- },
"rows": {
"type": "array",
"items": {
@@ -3823,7 +3831,6 @@
},
"additionalProperties": false,
"required": [
- "dataset_id",
"rows"
],
"title": "AppendRowsRequest"
@@ -6794,9 +6801,6 @@
{
"$ref": "#/components/schemas/URIDataSource"
},
- {
- "$ref": "#/components/schemas/HuggingfaceDataSource"
- },
{
"$ref": "#/components/schemas/RowsDataSource"
}
@@ -6805,7 +6809,6 @@
"propertyName": "type",
"mapping": {
"uri": "#/components/schemas/URIDataSource",
- "huggingface": "#/components/schemas/HuggingfaceDataSource",
"rows": "#/components/schemas/RowsDataSource"
}
}
@@ -6878,65 +6881,6 @@
],
"title": "Dataset"
},
- "HuggingfaceDataSource": {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "huggingface",
- "default": "huggingface",
- "description": "The type of the data source."
- },
- "huggingface": {
- "type": "object",
- "properties": {
- "path": {
- "type": "string",
- "description": "The path to the dataset in Huggingface. E.g. - \"llamastack/simpleqa\""
- },
- "params": {
- "type": "object",
- "additionalProperties": {
- "oneOf": [
- {
- "type": "null"
- },
- {
- "type": "boolean"
- },
- {
- "type": "number"
- },
- {
- "type": "string"
- },
- {
- "type": "array"
- },
- {
- "type": "object"
- }
- ]
- },
- "description": "The parameters for the dataset."
- }
- },
- "additionalProperties": false,
- "required": [
- "path",
- "params"
- ],
- "description": "The fields for a Huggingface dataset."
- }
- },
- "additionalProperties": false,
- "required": [
- "type",
- "huggingface"
- ],
- "title": "HuggingfaceDataSource",
- "description": "A dataset stored in Huggingface."
- },
"RowsDataSource": {
"type": "object",
"properties": {
@@ -7070,55 +7014,6 @@
],
"title": "ModelType"
},
- "PaginatedRowsResult": {
- "type": "object",
- "properties": {
- "rows": {
- "type": "array",
- "items": {
- "type": "object",
- "additionalProperties": {
- "oneOf": [
- {
- "type": "null"
- },
- {
- "type": "boolean"
- },
- {
- "type": "number"
- },
- {
- "type": "string"
- },
- {
- "type": "array"
- },
- {
- "type": "object"
- }
- ]
- }
- },
- "description": "The rows in the current page."
- },
- "total_count": {
- "type": "integer",
- "description": "The total number of rows in the dataset."
- },
- "next_page_token": {
- "type": "string",
- "description": "The token to get the next page of rows."
- }
- },
- "additionalProperties": false,
- "required": [
- "rows",
- "total_count"
- ],
- "title": "PaginatedRowsResult",
- "description": "A paginated list of rows from a dataset."
- },
"AgentTurnInputType": {
"type": "object",
"properties": {
@@ -8153,6 +8048,55 @@
],
"title": "ToolInvocationResult"
},
+ "PaginatedRowsResult": {
+ "type": "object",
+ "properties": {
+ "rows": {
+ "type": "array",
+ "items": {
+ "type": "object",
+ "additionalProperties": {
+ "oneOf": [
+ {
+ "type": "null"
+ },
+ {
+ "type": "boolean"
+ },
+ {
+ "type": "number"
+ },
+ {
+ "type": "string"
+ },
+ {
+ "type": "array"
+ },
+ {
+ "type": "object"
+ }
+ ]
+ }
+ },
+ "description": "The rows in the current page."
+ },
+ "total_count": {
+ "type": "integer",
+ "description": "The total number of rows in the dataset."
+ },
+ "next_page_token": {
+ "type": "string",
+ "description": "The token to get the next page of rows."
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "rows",
+ "total_count"
+ ],
+ "title": "PaginatedRowsResult",
+ "description": "A paginated list of rows from a dataset."
+ },
"ListAgentSessionsResponse": {
"type": "object",
"properties": {
@@ -9431,7 +9375,7 @@
},
"source": {
"$ref": "#/components/schemas/DataSource",
- "description": "The data source of the dataset. Examples: - { \"type\": \"uri\", \"uri\": \"https://mywebsite.com/mydata.jsonl\" } - { \"type\": \"uri\", \"uri\": \"lsfs://mydata.jsonl\" } - { \"type\": \"huggingface\", \"huggingface\": { \"dataset_path\": \"tatsu-lab/alpaca\", \"params\": { \"split\": \"train\" } } } - { \"type\": \"rows\", \"rows\": [ { \"messages\": [ {\"role\": \"user\", \"content\": \"Hello, world!\"}, {\"role\": \"assistant\", \"content\": \"Hello, world!\"}, ] } ] }"
+ "description": "The data source of the dataset. Examples: - { \"type\": \"uri\", \"uri\": \"https://mywebsite.com/mydata.jsonl\" } - { \"type\": \"uri\", \"uri\": \"lsfs://mydata.jsonl\" } - { \"type\": \"uri\", \"uri\": \"data:csv;base64,{base64_content}\" } - { \"type\": \"uri\", \"uri\": \"huggingface://llamastack/simpleqa?split=train\" } - { \"type\": \"rows\", \"rows\": [ { \"messages\": [ {\"role\": \"user\", \"content\": \"Hello, world!\"}, {\"role\": \"assistant\", \"content\": \"Hello, world!\"}, ] } ] }"
},
"metadata": {
"type": "object",
@@ -9461,7 +9405,7 @@
},
"dataset_id": {
"type": "string",
- "description": "The ID of the dataset. If not provided, a random ID will be generated."
+ "description": "The ID of the dataset. If not provided, an ID will be generated."
}
},
"additionalProperties": false,
diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml
index 1e6fc77cc..45d15407c 100644
--- a/docs/_static/llama-stack-spec.yaml
+++ b/docs/_static/llama-stack-spec.yaml
@@ -10,56 +10,7 @@ info:
servers:
- url: http://any-hosted-llama-stack.com
paths:
- /v1/datasetio/rows:
- get:
- responses:
- '200':
- description: OK
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/PaginatedRowsResult'
- '400':
- $ref: '#/components/responses/BadRequest400'
- '429':
- $ref: >-
- #/components/responses/TooManyRequests429
- '500':
- $ref: >-
- #/components/responses/InternalServerError500
- default:
- $ref: '#/components/responses/DefaultError'
- tags:
- - DatasetIO
- description: >-
- Get a paginated list of rows from a dataset.
- parameters:
- - name: dataset_id
- in: query
- description: >-
- The ID of the dataset to get the rows from.
- required: true
- schema:
- type: string
- - name: rows_in_page
- in: query
- description: The number of rows to get per page.
- required: true
- schema:
- type: integer
- - name: page_token
- in: query
- description: The token to get the next page of rows.
- required: false
- schema:
- type: string
- - name: filter_condition
- in: query
- description: >-
- (Optional) A condition to filter the rows by.
- required: false
- schema:
- type: string
+ /v1/datasets/{dataset_id}/rows:
post:
responses:
'200':
@@ -77,7 +28,12 @@ paths:
tags:
- DatasetIO
description: ''
- parameters: []
+ parameters:
+ - name: dataset_id
+ in: path
+ required: true
+ schema:
+ type: string
requestBody:
content:
application/json:
@@ -1473,6 +1429,56 @@ paths:
schema:
$ref: '#/components/schemas/InvokeToolRequest'
required: true
+ /v1/datasets/{dataset_id}/iterrows:
+ get:
+ responses:
+ '200':
+ description: OK
+ content:
+ application/json:
+ schema:
+ $ref: '#/components/schemas/PaginatedRowsResult'
+ '400':
+ $ref: '#/components/responses/BadRequest400'
+ '429':
+ $ref: >-
+ #/components/responses/TooManyRequests429
+ '500':
+ $ref: >-
+ #/components/responses/InternalServerError500
+ default:
+ $ref: '#/components/responses/DefaultError'
+ tags:
+ - DatasetIO
+ description: >-
+ Get a paginated list of rows from a dataset.
+ parameters:
+ - name: dataset_id
+ in: path
+ description: >-
+ The ID of the dataset to get the rows from.
+ required: true
+ schema:
+ type: string
+ - name: rows_in_page
+ in: query
+ description: The number of rows to get per page.
+ required: true
+ schema:
+ type: integer
+ - name: page_token
+ in: query
+ description: The token to get the next page of rows.
+ required: false
+ schema:
+ type: string
+ - name: filter_condition
+ in: query
+ description: >-
+ (Optional) A condition to filter the rows by.
+ required: false
+ schema:
+ type: string
/v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}:
get:
responses:
@@ -2583,8 +2589,6 @@ components:
AppendRowsRequest:
type: object
properties:
- dataset_id:
- type: string
rows:
type: array
items:
@@ -2599,7 +2603,6 @@ components:
- type: object
additionalProperties: false
required:
- - dataset_id
- rows
title: AppendRowsRequest
CompletionMessage:
@@ -4705,13 +4708,11 @@ components:
DataSource:
oneOf:
- $ref: '#/components/schemas/URIDataSource'
- - $ref: '#/components/schemas/HuggingfaceDataSource'
- $ref: '#/components/schemas/RowsDataSource'
discriminator:
propertyName: type
mapping:
uri: '#/components/schemas/URIDataSource'
- huggingface: '#/components/schemas/HuggingfaceDataSource'
rows: '#/components/schemas/RowsDataSource'
Dataset:
type: object
@@ -4757,43 +4758,6 @@ components:
- source
- metadata
title: Dataset
- HuggingfaceDataSource:
- type: object
- properties:
- type:
- type: string
- const: huggingface
- default: huggingface
- description: The type of the data source.
- huggingface:
- type: object
- properties:
- path:
- type: string
- description: >-
- The path to the dataset in Huggingface. E.g. - "llamastack/simpleqa"
- params:
- type: object
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- description: The parameters for the dataset.
- additionalProperties: false
- required:
- - path
- - params
- description: The fields for a Huggingface dataset.
- additionalProperties: false
- required:
- - type
- - huggingface
- title: HuggingfaceDataSource
- description: A dataset stored in Huggingface.
RowsDataSource:
type: object
properties:
@@ -4883,34 +4847,6 @@ components:
- llm
- embedding
title: ModelType
- PaginatedRowsResult:
- type: object
- properties:
- rows:
- type: array
- items:
- type: object
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- description: The rows in the current page.
- total_count:
- type: integer
- description: The total number of rows in the dataset.
- next_page_token:
- type: string
- description: The token to get the next page of rows.
- additionalProperties: false
- required:
- - rows
- - total_count
- title: PaginatedRowsResult
- description: A paginated list of rows from a dataset.
AgentTurnInputType:
type: object
properties:
@@ -5557,6 +5493,34 @@ components:
required:
- content
title: ToolInvocationResult
+ PaginatedRowsResult:
+ type: object
+ properties:
+ rows:
+ type: array
+ items:
+ type: object
+ additionalProperties:
+ oneOf:
+ - type: 'null'
+ - type: boolean
+ - type: number
+ - type: string
+ - type: array
+ - type: object
+ description: The rows in the current page.
+ total_count:
+ type: integer
+ description: The total number of rows in the dataset.
+ next_page_token:
+ type: string
+ description: The token to get the next page of rows.
+ additionalProperties: false
+ required:
+ - rows
+ - total_count
+ title: PaginatedRowsResult
+ description: A paginated list of rows from a dataset.
ListAgentSessionsResponse:
type: object
properties:
@@ -6401,11 +6365,11 @@ components:
$ref: '#/components/schemas/DataSource'
description: >-
The data source of the dataset. Examples: - { "type": "uri", "uri": "https://mywebsite.com/mydata.jsonl"
- } - { "type": "uri", "uri": "lsfs://mydata.jsonl" } - { "type": "huggingface",
- "huggingface": { "dataset_path": "tatsu-lab/alpaca", "params": { "split":
- "train" } } } - { "type": "rows", "rows": [ { "messages": [ {"role": "user",
- "content": "Hello, world!"}, {"role": "assistant", "content": "Hello,
- world!"}, ] } ] }
+ } - { "type": "uri", "uri": "lsfs://mydata.jsonl" } - { "type": "uri",
+ "uri": "data:csv;base64,{base64_content}" } - { "type": "uri", "uri":
+ "huggingface://llamastack/simpleqa?split=train" } - { "type": "rows",
+ "rows": [ { "messages": [ {"role": "user", "content": "Hello, world!"},
+ {"role": "assistant", "content": "Hello, world!"}, ] } ] }
metadata:
type: object
additionalProperties:
@@ -6421,7 +6385,7 @@ components:
dataset_id:
type: string
description: >-
- The ID of the dataset. If not provided, a random ID will be generated.
+ The ID of the dataset. If not provided, an ID will be generated.
additionalProperties: false
required:
- purpose
diff --git a/llama_stack/apis/datasets/datasets.py b/llama_stack/apis/datasets/datasets.py
index c25b861c3..9fe3cd1e0 100644
--- a/llama_stack/apis/datasets/datasets.py
+++ b/llama_stack/apis/datasets/datasets.py
@@ -193,7 +193,7 @@ class Datasets(Protocol):
}
:param metadata: The metadata for the dataset.
- E.g. {"description": "My dataset"}
- :param dataset_id: The ID of the dataset. If not provided, a random ID will be generated.
+ :param dataset_id: The ID of the dataset. If not provided, an ID will be generated.
"""
...