Precog Pipelines API
The Pipelines API from Precog — 18 operation(s) for pipelines.
OpenAPI Specification
openapi: 3.1.0
info:
title: http-api Admin Pipelines API
version: '1.0'
summary: The Precog admin HTTP REST API.
description: The Precog admin HTTP REST API.
contact:
url: https://precog.com
email: support@precog.com
servers:
- url: http://localhost:30000
security:
- BearerAuth: []
tags:
- name: Pipelines
paths:
/pipelines/{pipeline-id}/metadata:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
get:
summary: Get metadata related to this pipeline
tags:
- Pipelines
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/pipeline-metadata'
examples:
example-1:
value:
metadata:
- datasetId: 133425/example
tables:
- tableName: example
primaryKey:
- id
columns:
- columnName: id
columnType: string
maxObservedStringLength: 42
- columnName: foo
columnType: decimal
- tableName: example_items
primaryKey:
- id_example
- array_index
foreignKeys:
example:
- local:
- id_example
- reference:
- id
columns:
- columnName: id_example
columnType: string
maxObservedStringLength: 42
- columnName: array_index
columnType: long
- columnName: bar
columnType: boolean
'401':
description: Unauthorized
'404':
description: Pipeline not found.
operationId: get-pipelines-pipeline-id-metadata
description: Get metadata for a particular particular pipeline.
/pipelines/{pipeline-id}/dataset-properties:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
get:
summary: Get dataset properties related to the in-band datasets present in this pipeline
tags:
- Pipelines
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/pipeline-datasets-properties'
examples:
example-1:
value:
pipelineId: a864cb9a-7be2-11f0-aa5e-2a65c4d820c0
datasetProperties:
70c7b714-7be3-11f0-a48c-2a65c4d820c0:/Question Bank:
primaryKey:
type: strict
components:
- $.data.results[:_].questionId
- $.data.results[:_].questionBankId
70c7b714-7be3-11f0-a48c-2a65c4d820c0:/Survey Categories:
primaryKey:
type: strict
components:
- $.data.results[:_].surveyCategoryId
- $.data.results[:_].surveyId
70c7b714-7be3-11f0-a48c-2a65c4d820c0:/Survey Templates:
primaryKey:
type: strict
components:
- $.data.results[:_].surveyTemplateId
- $.data.results[:_].surveyId
- $.data.results[:_].id
70c7b714-7be3-11f0-a48c-2a65c4d820c0:/Surveys:
primaryKey:
type: strict
components:
- $.data.id
'422':
description: Returned when the pipeline does not have any in-band datasets
'401':
description: Unauthorized
'404':
description: Pipeline not found.
operationId: get-pipeline-id-dataset-properties
description: Get dataset properties for datasets in a particular pipeline.
/pipelines:
get:
summary: Get pipelines
tags:
- Pipelines
responses:
'200':
description: OK
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/pipeline-listing'
examples:
example-1:
value:
- id: '1'
name: Ecommerce
- id: '2'
name: Internal
- id: '3'
name: Staging environment
- id: '4'
name: Test environment
'401':
description: Unauthorized
operationId: get-pipelines
description: Get all pipelines.
post:
summary: Create pipeline
tags:
- Pipelines
operationId: post-pipelines
responses:
'201':
description: Created
content:
application/json:
schema:
$ref: '#/components/schemas/id'
'400':
description: 'Bad Request. Includes the case where `vectorize: true` is set on a pipeline whose destination does not support the Snowflake VECTOR column type (LD15) — only Snowflake-family destinations are vector-capable.'
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
'401':
description: Unauthorized
'422':
description: Semantic error.
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
description: Create a new pipeline.
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/pipeline'
description: ''
/pipelines/status:
parameters: []
get:
summary: Get the pipeline status
tags:
- Pipelines
responses:
'200':
description: OK
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/pipeline-status'
examples:
example-1:
value:
- pipelineId: '1'
status:
at: 1632428787341
state: loading
- pipelineId: '3'
status:
at: 1632128787341
state: succeeded
- pipelineId: '4'
status:
at: 1631251787341
state: failed
'401':
description: Unauthorized
operationId: get-pipelines-status
description: Get the status of all the pipelines.
/pipelines/{pipeline-id}:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
get:
summary: Get a pipeline
tags:
- Pipelines
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/pipeline'
examples:
example:
value:
id: '1'
name: Ecommerce
destinationId: '1'
columnNameStrategy:
tableNamePostfix: true
datasetIds:
- source-1:path/to/dataset
'401':
description: Unauthorized
'404':
description: Pipeline not found.
operationId: get-pipelines-pipeline-id
description: Get a particular pipeline.
delete:
summary: ''
tags:
- Pipelines
operationId: delete-pipelines-pipeline-id
responses:
'204':
description: No Content
'404':
description: Not Found
description: Deletes the given pipeline
/pipelines/{pipeline-id}/metrics:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
get:
summary: Get the pipeline metrics
tags:
- Pipelines
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/aggregated-pipeline-metrics'
'401':
description: Unauthorized
'404':
description: Pipeline not found.
description: Get the metrics from a pipeline
/pipelines/{pipeline-id}/datasets:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
get:
summary: Get the pipeline datasets
tags:
- Pipelines
responses:
'200':
description: OK
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/dataset'
'401':
description: Unauthorized
'404':
description: Pipeline not found.
operationId: get-pipelines-pipeline-id-datasets
description: Get the datasets in the provided pipeline.
patch:
summary: ''
tags:
- Pipelines
operationId: patch-pipelines-pipeline-id-datasets
responses:
'204':
description: No Content
'400':
description: Bad Request
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
'401':
description: Unauthorized
'404':
description: Pipeline not found. <or> Datasets not found.
'422':
description: Semantic error.
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
description: Add (or remove) datasets to (or from) the provided pipeline.
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/dataset-update'
examples:
example-1:
value:
action: add
datasetIds:
- string
/pipelines/{pipeline-id}/details:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
get:
summary: Get pipeline details
tags:
- Pipelines
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/pipeline-details'
examples:
example-1:
value:
datasets:
- dataset:
- id: '1'
name: Abandoned checkouts
- id: '2'
name: Application charges
- id: '3'
name: Application credits
- id: '4'
name: Custom collections
- id: '5'
name: Customer saved searches
- id: '6'
name: Customers
- id: '7'
name: Locations
- id: '8'
name: Orders
- id: '9'
name: Price rules
- id: '10'
name: Products
- id: '11'
name: Recurring application charges
source:
id: '1'
kind:
id: '12'
name: Shopify
name: 'Shop name: MyShop'
destination:
id: '1'
kind:
id: '14'
name: Snowflake
name: 'Account: Precog, Database: Raw, Region: west-us-2.azure'
pipeline:
id: '1'
name: Ecommerce
columnNameStrategy:
tableNamePostfix: false
schedule:
- '*/5 * * * *'
notifications:
- josie@email.com
'401':
description: Unauthorized
'404':
description: Pipeline not found
operationId: get-pipelines-pipeline-id-details
description: Get all the details for the provided pipeline.
/pipelines/{pipeline-id}/status:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
get:
summary: Get the pipeline datasets status
tags:
- Pipelines
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/pipeline-dataset-status'
examples:
example-1:
value:
pipelineId: '1'
status:
state: succeeded
at: 0
datasets:
- id: string
outOfBand:
state: staging
at: 0
inBand:
state: staging
at: 0
'401':
description: Unauthorized
'404':
description: Pipeline not found
operationId: get-pipelines-pipeline-id-status
description: Get the status of the provided pipeline.
/pipelines/{pipeline-id}/loads:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
post:
summary: Start a pipeline load
tags:
- Pipelines
operationId: post-pipelines-pipeline-id-loads
responses:
'202':
description: Accepted - there are in-band datasets and a load has been scheduled to start
'204':
description: No Content - there are no in-band datasets
'400':
description: Bad Request - there are no datasets in pipeline
'401':
description: Unauthorized
'402':
description: Payment Required - trial period has expired and there is no active subscription
content:
application/json:
schema:
type: object
properties:
error:
type: object
required:
- type
- details
properties:
type:
type: string
minLength: 1
details:
type: string
url:
type: string
required:
- error
'404':
description: Pipeline not found.
'502':
description: Problematic Request to External Server
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
description: Start a load for this pipeline.
requestBody:
content:
application/json:
schema:
type: object
properties:
returnUrl:
type: string
description: ''
/pipelines/{pipeline-id}/rename:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
put:
summary: Rename a pipelne.
tags:
- Pipelines
operationId: put-pipelines-pipeline-id-rename
responses:
'204':
description: No Content
'400':
description: Bad Request
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
'401':
description: Unauthorized
'404':
description: Pipeline not found
'422':
description: Semantic error.
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
description: Rename a pipeline.
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/pipeline-name'
/pipelines/{pipeline-id}/pii-config:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
put:
summary: Set PII handling policy for a pipeline.
tags:
- Pipelines
operationId: put-pipelines-pipeline-id-pii-config
responses:
'204':
description: No Content
'401':
description: Unauthorized
'404':
description: Pipeline not found
description: Set the PII handling policy for a pipeline. The policy controls how detected PII columns are transformed at load time.
requestBody:
content:
application/json:
schema:
type: object
properties:
type:
type: string
enum:
- passthrough
- hash
- omit
- nullify
description: The PII handling policy to apply.
required:
- type
/pipelines/{pipeline-id}/vectorize:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
put:
summary: Set the vectorization opt-in flag for a pipeline.
tags:
- Pipelines
operationId: put-pipelines-pipeline-id-vectorize
responses:
'204':
description: No Content
'400':
description: Destination does not support vectors. Returned when `vectorize` is `true` and the pipeline's destination is not vector-capable (LD15 — Snowflake-family destinations only).
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
'401':
description: Unauthorized
'404':
description: Pipeline not found
description: "Set the vectorization opt-in flag for a pipeline (vectorization-spec-v4 / LD13).\nSemantics:\n - `null` or omitted, or `false` → the pipeline does not vectorize;\n its loads are byte-identical to a pipeline created before this\n feature existed.\n - `true` → subsequent loads of datasets in this pipeline produce\n per-row embeddings (IBM Granite-30M, 384-dim) landed in\n `<destination_database>.<pipeline-name>.PRETEXT` on the\n pipeline's destination, in addition to the normal writer output.\n\nFlipping the flag is **not retroactive**. See the `vectorize` field on the `pipeline` schema for the full semantics.\nSetting `true` is only valid on Snowflake-family destinations (LD15); attempts on any other destination are rejected with 400."
requestBody:
content:
application/json:
schema:
type: object
properties:
vectorize:
type: boolean
nullable: true
description: 'The new value of the vectorize flag. `null` and `false` are equivalent: the pipeline does not vectorize.'
sentimentAnalysis:
type: boolean
nullable: true
description: Enables sentiment analysis on the pipeline. Requires vectorization to also be on, otherwise a 400 will be returned.
required:
- vectorize
/pipelines/{pipeline-id}/encode:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
post:
summary: Embed query text against the pipeline's vector model.
tags:
- Pipelines
operationId: post-pipelines-pipeline-id-encode
description: Embed a piece of text using the pipeline's vector model. The returned vector is directly comparable with those stored in the pipeline's PRETEXT destination table, making it suitable for cosine-similarity queries against the corpus.
requestBody:
content:
application/json:
schema:
type: object
properties:
text:
type: string
description: The query text to embed. Must be non-empty.
required:
- text
responses:
'200':
description: Embedding produced successfully.
content:
application/json:
schema:
type: object
properties:
vec:
type: array
items:
type: number
description: The embedding vector for the supplied text.
dim:
type: integer
description: Dimensionality of the returned vector.
model_id:
type: string
description: Identifier of the embedding model used to produce this vector.
required:
- vec
- dim
- model_id
'400':
description: Empty or whitespace-only text.
content:
application/json:
schema:
type: object
properties:
error:
type: string
required:
- error
'401':
description: Unauthorized
'404':
description: Pipeline not found
/pipelines/{pipeline-id}/semantic-contexts:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
get:
operationId: get-pipelines-pipeline-id-semantic-contexts
summary: Get existing semantic contexts of this pipeline
responses:
'200':
description: List of semantic contexts
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/semantic-context'
'400':
description: Bad Request
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
'401':
description: Unauthorized
'404':
description: Pipeline not found
'422':
description: Semantic error.
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
tags:
- Pipelines
post:
operationId: post-pipelines-pipeline-id-semantic-contexts
summary: Add a semantic context to the pipeline
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/semantic-context-request'
responses:
'201':
description: Semantic context created
content:
application/json:
schema:
type: object
properties:
semanticContextId:
type: string
description: ID generated for the newly created semantic context
minLength: 1
'400':
description: Bad Request
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
'401':
description: Unauthorized
'404':
description: Pipeline not found
'422':
description: Semantic error.
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
tags:
- Pipelines
/pipelines/{pipeline-id}/semantic-contexts/{semantic-context-id}:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
- schema:
type: string
name: semantic-context-id
in: path
required: true
get:
operationId: get-pipelines-pipeline-id-semantic-contexts-semantic-context-id
summary: Get the details of the particular semantic context
responses:
'200':
description: Semantic context retrieved
content:
application/json:
schema:
$ref: '#/components/schemas/semantic-context'
'400':
description: Bad Request
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
'401':
description: Unauthorized
'404':
description: Semantic context with this pipeline ID/semantic context ID combination not found
'422':
description: Semantic error.
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
tags:
- Pipelines
put:
operationId: put-pipelines-pipeline-id-semantic-contexts-semantic-context-id
summary: Replace details of a semantic context
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/semantic-context-request'
responses:
'200':
description: Semantic context updated
'400':
description: Bad Request
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
'401':
description: Unauthorized
'404':
description: Semantic context with this pipeline ID/semantic context ID combination not found
'422':
description: Semantic error.
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
tags:
- Pipelines
delete:
operationId: delete-pipelines-pipeline-id-semantic-contexts-semantic-context-id
summary: Delete the semantic context
responses:
'200':
description: Semantic context deleted
'400':
description: Bad Request
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
'401':
description: Unauthorized
'404':
description: Semantic context with this pipeline ID/semantic context ID combination not found
'422':
description: Semantic error.
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
tags:
- Pipelines
/pipelines/{pipeline-id}/schedule:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
put:
summary: Schedule a pipeline.
tags:
- Pipelines
operationId: put-pipelines-pipeline-id-schedule
responses:
'204':
description: No Content
'400':
description: Bad Request
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
'401':
description: Unauthorized
'404':
description: Pipeline not found
'422':
description: Semantic error.
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
description: Schedule a pipeline.
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/pipeline-schedule'
description: A list of cron expressions. An empty list means that the pipeline will not be loaded on a schedule.
get:
summary: Get the pipeline schedule
tags:
- Pipelines
operationId: get-pipelines-pipeline-id-schedule
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/pipeline-schedule'
'401':
description: Unauthorized
'404':
description: Pipeline not found
description: Get the pipeline schedule.
/pipelines/{pipeline-id}/notification:
parameters:
- schema:
type: string
name: pipeline-id
in: path
required: true
put:
summary: Set email addresses to be notified on pipeline events.
tags:
- Pipelines
operationId: put-pipelines-pipeline-id-notification
responses:
'204':
description: No Content
'400':
description: Bad Request
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
'401':
description: Unauthorized
'404':
description: Pipeline not found
'422':
description: Semantic error.
content:
application/json:
schema:
$ref: '#/components/schemas/error-message'
description: Set email addresses to be notified on pipeline events.
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/pipeline-notification'
description: A list of email addresses. An empty list means that email notifications are disabled for the pipeline.
get:
summary: Get email addresses associated with the pipeline
tags:
- Pipelines
operationId: get-pipelines-pipeline-id-notification
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/pipeline-notification'
'401':
description: Unauthorized
'404':
description: Pipeline not found
description: Get email addresses associated with the pipeline.
components:
schemas:
dataset-telemetry:
title: dataset-telemetry
type: object
properties:
at:
$ref: '#/components/schemas/epoch-millis'
bytesStaged:
type: integer
ratelimitReset:
$ref: '#/components/schemas/epoch-millis'
required:
- at
dataset:
title: ''
type: object
properties:
id:
type: string
minLength: 1
name:
type: string
minLength: 1
sourceId:
type: string
minLength: 1
required:
- id
- name
- sourceId
id:
title: ''
type: object
properties:
id:
type: string
required:
- id
pipeline-metadata:
description: Tables in this pipeline
type: object
title: Pipeline metadata
properties:
metadata:
type: array
title: Datasets
items:
$ref: '#/components/schemas/dataset-metadata'
epoch-millis:
type: integer
title: epoch-millis
minimum: 0
example: 1742922912239
initial-load-params-message-limit:
title: initial-load-params-message-limit
type: object
properties:
maxMessages:
type: number
required:
- maxMessages
pipeline:
title: ''
type: object
properties:
id:
type: string
minLength: 1
readOnly: tr
# --- truncated at 32 KB (48 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/precog/refs/heads/main/openapi/precog-pipelines-api-openapi.yml