Arize Phoenix Datasets API
The datasets API from Arize Phoenix — 9 operation(s) for datasets.
The datasets API from Arize Phoenix — 9 operation(s) for datasets.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/phoenix:phoenix-datasets-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: Arize-Phoenix REST Datasets API
description: Schema for Arize-Phoenix REST API
version: '1.0'
tags:
- name: Datasets
paths:
/v1/datasets:
get:
tags:
- Datasets
summary: List datasets
operationId: listDatasets
parameters:
- name: cursor
in: query
required: false
schema:
type:
- string
- 'null'
description: Cursor for pagination
title: Cursor
description: Cursor for pagination
- name: name
in: query
required: false
schema:
type:
- string
- 'null'
description: An optional dataset name to filter by
title: Name
description: An optional dataset name to filter by
- name: limit
in: query
required: false
schema:
type: integer
exclusiveMinimum: 0
description: The max number of datasets to return at a time.
default: 10
title: Limit
description: The max number of datasets to return at a time.
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/ListDatasetsResponseBody'
'403':
content:
text/plain:
schema:
type: string
description: Forbidden
'422':
content:
text/plain:
schema:
type: string
description: Unprocessable Entity
/v1/datasets/{id}:
delete:
tags:
- Datasets
summary: Delete dataset by ID
operationId: deleteDatasetById
parameters:
- name: id
in: path
required: true
schema:
type: string
description: The ID of the dataset to delete.
title: Id
description: The ID of the dataset to delete.
responses:
'204':
description: Successful Response
'403':
content:
text/plain:
schema:
type: string
description: Forbidden
'404':
content:
text/plain:
schema:
type: string
description: Dataset not found
'422':
content:
text/plain:
schema:
type: string
description: Invalid dataset ID
get:
tags:
- Datasets
summary: Get dataset by ID
operationId: getDataset
parameters:
- name: id
in: path
required: true
schema:
type: string
description: The ID of the dataset
title: Id
description: The ID of the dataset
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/GetDatasetResponseBody'
'403':
content:
text/plain:
schema:
type: string
description: Forbidden
'404':
content:
text/plain:
schema:
type: string
description: Not Found
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/v1/datasets/{id}/versions:
get:
tags:
- Datasets
summary: List dataset versions
operationId: listDatasetVersionsByDatasetId
parameters:
- name: id
in: path
required: true
schema:
type: string
description: The ID of the dataset
title: Id
description: The ID of the dataset
- name: cursor
in: query
required: false
schema:
type:
- string
- 'null'
description: Cursor for pagination
title: Cursor
description: Cursor for pagination
- name: limit
in: query
required: false
schema:
type: integer
exclusiveMinimum: 0
description: The max number of dataset versions to return at a time
default: 10
title: Limit
description: The max number of dataset versions to return at a time
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/ListDatasetVersionsResponseBody'
'403':
content:
text/plain:
schema:
type: string
description: Forbidden
'422':
content:
text/plain:
schema:
type: string
description: Unprocessable Entity
/v1/datasets/upload:
post:
tags:
- Datasets
summary: Upload dataset from JSON, JSONL, CSV, or PyArrow
operationId: uploadDataset
parameters:
- name: sync
in: query
required: false
schema:
type: boolean
description: If true, fulfill request synchronously and return JSON containing dataset_id.
default: false
title: Sync
description: If true, fulfill request synchronously and return JSON containing dataset_id.
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/UploadDatasetResponseBody'
title: Response Uploaddataset
'403':
content:
text/plain:
schema:
type: string
description: Forbidden
'409':
content:
text/plain:
schema:
type: string
description: Dataset with the given name already exists (action=create).
'422':
content:
text/plain:
schema:
type: string
description: Invalid request body
requestBody:
content:
application/json:
schema:
type: object
required:
- name
- inputs
properties:
action:
type: string
enum:
- create
- append
- update
name:
type: string
description:
type: string
inputs:
type: array
items:
type: object
outputs:
type: array
items:
type: object
metadata:
type: array
items:
type: object
splits:
type: array
items:
oneOf:
- type: string
- type: array
items:
type: string
- type: 'null'
description: 'Split per example: string, string array, or null'
span_ids:
type: array
items:
oneOf:
- type: string
- type: 'null'
description: Span IDs to link examples back to spans
example_ids:
type: array
items:
oneOf:
- type: string
- type: 'null'
description: Optional example ID per example. If provided, it is used as the example's stable public ID.
multipart/form-data:
schema:
type: object
required:
- name
- input_keys[]
- output_keys[]
- file
properties:
action:
type: string
enum:
- create
- append
- update
name:
type: string
description:
type: string
input_keys[]:
type: array
items:
type: string
uniqueItems: true
output_keys[]:
type: array
items:
type: string
uniqueItems: true
metadata_keys[]:
type: array
items:
type: string
uniqueItems: true
split_keys[]:
type: array
items:
type: string
uniqueItems: true
description: 'Deprecated: use split_key instead. Column names for auto-assigning examples to splits'
split_key:
type: string
description: Single column name containing split names (plain string or JSON list) per row
flatten_keys[]:
type: array
items:
type: string
uniqueItems: true
description: Column names whose object values should be flattened into their selected bucket
span_id_key:
type: string
description: Column name for span IDs to link examples back to spans
example_id_key:
type: string
description: Column name containing stable IDs for examples. When provided, examples with matching IDs are updated in place when their content changes.
file:
type: string
format: binary
/v1/datasets/{id}/examples:
get:
tags:
- Datasets
summary: Get examples from a dataset
operationId: getDatasetExamples
parameters:
- name: id
in: path
required: true
schema:
type: string
description: The ID of the dataset
title: Id
description: The ID of the dataset
- name: version_id
in: query
required: false
schema:
type:
- string
- 'null'
description: The ID of the dataset version (if omitted, returns data from the latest version)
title: Version Id
description: The ID of the dataset version (if omitted, returns data from the latest version)
- name: split
in: query
required: false
schema:
type:
- array
- 'null'
items:
type: string
description: List of dataset split identifiers (GlobalIDs or names) to filter by
title: Split
description: List of dataset split identifiers (GlobalIDs or names) to filter by
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/ListDatasetExamplesResponseBody'
'403':
content:
text/plain:
schema:
type: string
description: Forbidden
'404':
content:
text/plain:
schema:
type: string
description: Not Found
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/v1/datasets/{id}/csv:
get:
tags:
- Datasets
summary: Download dataset examples as CSV file
operationId: getDatasetCsv
parameters:
- name: id
in: path
required: true
schema:
type: string
description: The ID of the dataset
title: Id
description: The ID of the dataset
- name: version_id
in: query
required: false
schema:
type:
- string
- 'null'
description: The ID of the dataset version (if omitted, returns data from the latest version)
title: Version Id
description: The ID of the dataset version (if omitted, returns data from the latest version)
responses:
'200':
description: Successful Response
content:
text/csv:
schema:
type: string
contentMediaType: text/csv
'403':
content:
text/plain:
schema:
type: string
description: Forbidden
'422':
content:
text/plain:
schema:
type: string
description: Unprocessable Entity
/v1/datasets/{id}/jsonl:
get:
tags:
- Datasets
summary: Download dataset examples as JSONL file
operationId: getDatasetJSONL
parameters:
- name: id
in: path
required: true
schema:
type: string
description: The ID of the dataset
title: Id
description: The ID of the dataset
- name: version_id
in: query
required: false
schema:
type:
- string
- 'null'
description: The ID of the dataset version (if omitted, returns data from the latest version)
title: Version Id
description: The ID of the dataset version (if omitted, returns data from the latest version)
responses:
'200':
description: Successful Response
content:
text/plain:
schema:
type: string
'403':
content:
text/plain:
schema:
type: string
description: Forbidden
'422':
content:
text/plain:
schema:
type: string
description: Invalid dataset or version ID
/v1/datasets/{id}/jsonl/openai_ft:
get:
tags:
- Datasets
summary: Download dataset examples as OpenAI fine-tuning JSONL file
operationId: getDatasetJSONLOpenAIFineTuning
parameters:
- name: id
in: path
required: true
schema:
type: string
description: The ID of the dataset
title: Id
description: The ID of the dataset
- name: version_id
in: query
required: false
schema:
type:
- string
- 'null'
description: The ID of the dataset version (if omitted, returns data from the latest version)
title: Version Id
description: The ID of the dataset version (if omitted, returns data from the latest version)
responses:
'200':
description: Successful Response
content:
text/plain:
schema:
type: string
'403':
content:
text/plain:
schema:
type: string
description: Forbidden
'422':
content:
text/plain:
schema:
type: string
description: Invalid dataset or version ID
/v1/datasets/{id}/jsonl/openai_evals:
get:
tags:
- Datasets
summary: Download dataset examples as OpenAI evals JSONL file
operationId: getDatasetJSONLOpenAIEvals
parameters:
- name: id
in: path
required: true
schema:
type: string
description: The ID of the dataset
title: Id
description: The ID of the dataset
- name: version_id
in: query
required: false
schema:
type:
- string
- 'null'
description: The ID of the dataset version (if omitted, returns data from the latest version)
title: Version Id
description: The ID of the dataset version (if omitted, returns data from the latest version)
responses:
'200':
description: Successful Response
content:
text/plain:
schema:
type: string
'403':
content:
text/plain:
schema:
type: string
description: Forbidden
'422':
content:
text/plain:
schema:
type: string
description: Invalid dataset or version ID
components:
schemas:
Dataset:
properties:
id:
type: string
title: Id
name:
type: string
title: Name
description:
type:
- string
- 'null'
title: Description
metadata:
additionalProperties: true
type: object
title: Metadata
created_at:
type: string
format: date-time
title: Created At
updated_at:
type: string
format: date-time
title: Updated At
example_count:
type: integer
title: Example Count
type: object
required:
- id
- name
- description
- metadata
- created_at
- updated_at
- example_count
title: Dataset
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
input:
title: Input
ctx:
type: object
title: Context
type: object
required:
- loc
- msg
- type
title: ValidationError
DatasetExample:
properties:
id:
type: string
title: Id
node_id:
type: string
title: Node Id
input:
additionalProperties: true
type: object
title: Input
output:
additionalProperties: true
type: object
title: Output
metadata:
additionalProperties: true
type: object
title: Metadata
updated_at:
type: string
format: date-time
title: Updated At
type: object
required:
- id
- node_id
- input
- output
- metadata
- updated_at
title: DatasetExample
DatasetVersion:
properties:
version_id:
type: string
title: Version Id
description:
type:
- string
- 'null'
title: Description
metadata:
additionalProperties: true
type: object
title: Metadata
created_at:
type: string
format: date-time
title: Created At
type: object
required:
- version_id
- description
- metadata
- created_at
title: DatasetVersion
ListDatasetExamplesResponseBody:
properties:
data:
$ref: '#/components/schemas/ListDatasetExamplesData'
type: object
required:
- data
title: ListDatasetExamplesResponseBody
ListDatasetExamplesData:
properties:
dataset_id:
type: string
title: Dataset Id
version_id:
type: string
title: Version Id
filtered_splits:
items:
type: string
type: array
title: Filtered Splits
examples:
items:
$ref: '#/components/schemas/DatasetExample'
type: array
title: Examples
type: object
required:
- dataset_id
- version_id
- examples
title: ListDatasetExamplesData
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
UploadDatasetData:
properties:
dataset_id:
type: string
title: Dataset Id
version_id:
type: string
title: Version Id
num_created_examples:
type: integer
title: Num Created Examples
num_updated_examples:
type: integer
title: Num Updated Examples
num_deleted_examples:
type: integer
title: Num Deleted Examples
type: object
required:
- dataset_id
- version_id
- num_created_examples
- num_updated_examples
- num_deleted_examples
title: UploadDatasetData
UploadDatasetResponseBody:
properties:
data:
$ref: '#/components/schemas/UploadDatasetData'
type: object
required:
- data
title: UploadDatasetResponseBody
ListDatasetVersionsResponseBody:
properties:
data:
items:
$ref: '#/components/schemas/DatasetVersion'
type: array
title: Data
next_cursor:
type:
- string
- 'null'
title: Next Cursor
type: object
required:
- data
- next_cursor
title: ListDatasetVersionsResponseBody
DatasetWithExampleCount:
properties:
id:
type: string
title: Id
name:
type: string
title: Name
description:
type:
- string
- 'null'
title: Description
metadata:
additionalProperties: true
type: object
title: Metadata
created_at:
type: string
format: date-time
title: Created At
updated_at:
type: string
format: date-time
title: Updated At
example_count:
type: integer
title: Example Count
type: object
required:
- id
- name
- description
- metadata
- created_at
- updated_at
- example_count
title: DatasetWithExampleCount
GetDatasetResponseBody:
properties:
data:
$ref: '#/components/schemas/DatasetWithExampleCount'
type: object
required:
- data
title: GetDatasetResponseBody
ListDatasetsResponseBody:
properties:
data:
items:
$ref: '#/components/schemas/Dataset'
type: array
title: Data
next_cursor:
type:
- string
- 'null'
title: Next Cursor
type: object
required:
- data
- next_cursor
title: ListDatasetsResponseBody