diff --git a/airbyte-api.openapi.yaml b/airbyte-api.openapi.yaml
index 0103e66a..3d5aff33 100644
--- a/airbyte-api.openapi.yaml
+++ b/airbyte-api.openapi.yaml
@@ -1525,6 +1525,76 @@ components:
OAuthInputConfiguration:
$ref: "#/components/schemas/OAuthConfiguration"
x-speakeasy-component: true
+ ApplicationCreate:
+ required:
+ - "name"
+ type: "object"
+ properties:
+ name:
+ type: "string"
+ x-speakeasy-component: true
+ ApplicationReadList:
+ required:
+ - "applications"
+ type: "object"
+ properties:
+ applications:
+ type: "array"
+ items:
+ $ref: "#/components/schemas/ApplicationRead"
+ x-speakeasy-component: true
+ ApplicationRead:
+ required:
+ - "id"
+ - "name"
+ - "clientId"
+ - "clientSecret"
+ - "createdAt"
+ type: "object"
+ properties:
+ id:
+ type: "string"
+ name:
+ type: "string"
+ clientId:
+ type: "string"
+ clientSecret:
+ type: "string"
+ createdAt:
+ type: "integer"
+ format: "int64"
+ x-speakeasy-component: true
+ ApplicationTokenRequestWithGrant:
+ required:
+ - "client_id"
+ - "client_secret"
+ - "grant_type"
+ type: "object"
+ properties:
+ client_id:
+ type: "string"
+ client_secret:
+ type: "string"
+ grant-type:
+ enum:
+ - "client_credentials"
+ x-speakeasy-component: true
+ PublicAccessTokenResponse:
+ required:
+ - "access_token"
+ - "token_type"
+ - "expires_in"
+ type: "object"
+ properties:
+ access_token:
+ type: "string"
+ token_type:
+ enum:
+ - "Bearer"
+ expires_in:
+ type: "integer"
+ format: "int64"
+ x-speakeasy-component: true
RedirectUrlResponse:
title: "Root Type for RedirectUrlResponse"
description: ""
@@ -3579,6 +3649,214 @@ components:
order: 1
required:
- "api_key"
+ source-datadog:
+ title: "Datadog Source Spec"
+ type: "object"
+ required:
+ - "api_key"
+ - "application_key"
+ - "sourceType"
+ properties:
+ api_key:
+ title: "API Key"
+ description: "Datadog API key"
+ type: "string"
+ airbyte_secret: true
+ order: 1
+ x-speakeasy-param-sensitive: true
+ application_key:
+ title: "Application Key"
+ description: "Datadog application key"
+ type: "string"
+ airbyte_secret: true
+ order: 2
+ x-speakeasy-param-sensitive: true
+ query:
+ title: "Query"
+ description: "The search query. This just applies to Incremental syncs.\
+ \ If empty, it'll collect all logs."
+ type: "string"
+ order: 3
+ start_date:
+ title: "Start date"
+ pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}Z$"
+ description: "UTC date and time in the format 2017-01-25T00:00:00Z. Any\
+ \ data before this date will not be replicated. This just applies to Incremental\
+ \ syncs."
+ type: "string"
+ examples:
+ - "2022-10-01T00:00:00Z"
+ order: 4
+ site:
+ title: "Site"
+ description: "The site where Datadog data resides in."
+ type: "string"
+ enum:
+ - "datadoghq.com"
+ - "us3.datadoghq.com"
+ - "us5.datadoghq.com"
+ - "datadoghq.eu"
+ - "ddog-gov.com"
+ default: "datadoghq.com"
+ order: 5
+ end_date:
+ title: "End date"
+ pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}Z$"
+ description: "UTC date and time in the format 2017-01-25T00:00:00Z. Data\
+ \ after this date will not be replicated. An empty value will represent\
+ \ the current datetime for each execution. This just applies to Incremental\
+ \ syncs."
+ examples:
+ - "2022-10-01T00:00:00Z"
+ type: "string"
+ order: 6
+ max_records_per_request:
+ type: "integer"
+ title: "Max records per requests"
+ default: 5000
+ minimum: 1
+ maximum: 5000
+ description: "Maximum number of records to collect per request."
+ order: 7
+ queries:
+ title: "Queries"
+ description: "List of queries to be run and used as inputs."
+ type: "array"
+ order: 8
+ default: []
+ items:
+ type: "object"
+ required:
+ - "name"
+ - "data_source"
+ - "query"
+ properties:
+ name:
+ title: "Query Name"
+ description: "The variable name for use in queries."
+ type: "string"
+ order: 1
+ data_source:
+ title: "Data Source"
+ description: "A data source that is powered by the platform."
+ type: "string"
+ enum:
+ - "metrics"
+ - "cloud_cost"
+ - "logs"
+ - "rum"
+ order: 2
+ query:
+ title: "Query"
+ description: "A classic query string."
+ type: "string"
+ order: 3
+ sourceType:
+ title: "datadog"
+ const: "datadog"
+ enum:
+ - "datadog"
+ order: 0
+ type: "string"
+ source-datadog-update:
+ title: "Datadog Source Spec"
+ type: "object"
+ required:
+ - "api_key"
+ - "application_key"
+ properties:
+ api_key:
+ title: "API Key"
+ description: "Datadog API key"
+ type: "string"
+ airbyte_secret: true
+ order: 1
+ application_key:
+ title: "Application Key"
+ description: "Datadog application key"
+ type: "string"
+ airbyte_secret: true
+ order: 2
+ query:
+ title: "Query"
+ description: "The search query. This just applies to Incremental syncs.\
+ \ If empty, it'll collect all logs."
+ type: "string"
+ order: 3
+ start_date:
+ title: "Start date"
+ pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}Z$"
+ description: "UTC date and time in the format 2017-01-25T00:00:00Z. Any\
+ \ data before this date will not be replicated. This just applies to Incremental\
+ \ syncs."
+ type: "string"
+ examples:
+ - "2022-10-01T00:00:00Z"
+ order: 4
+ site:
+ title: "Site"
+ description: "The site where Datadog data resides in."
+ type: "string"
+ enum:
+ - "datadoghq.com"
+ - "us3.datadoghq.com"
+ - "us5.datadoghq.com"
+ - "datadoghq.eu"
+ - "ddog-gov.com"
+ default: "datadoghq.com"
+ order: 5
+ end_date:
+ title: "End date"
+ pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}Z$"
+ description: "UTC date and time in the format 2017-01-25T00:00:00Z. Data\
+ \ after this date will not be replicated. An empty value will represent\
+ \ the current datetime for each execution. This just applies to Incremental\
+ \ syncs."
+ examples:
+ - "2022-10-01T00:00:00Z"
+ type: "string"
+ order: 6
+ max_records_per_request:
+ type: "integer"
+ title: "Max records per requests"
+ default: 5000
+ minimum: 1
+ maximum: 5000
+ description: "Maximum number of records to collect per request."
+ order: 7
+ queries:
+ title: "Queries"
+ description: "List of queries to be run and used as inputs."
+ type: "array"
+ order: 8
+ default: []
+ items:
+ type: "object"
+ required:
+ - "name"
+ - "data_source"
+ - "query"
+ properties:
+ name:
+ title: "Query Name"
+ description: "The variable name for use in queries."
+ type: "string"
+ order: 1
+ data_source:
+ title: "Data Source"
+ description: "A data source that is powered by the platform."
+ type: "string"
+ enum:
+ - "metrics"
+ - "cloud_cost"
+ - "logs"
+ - "rum"
+ order: 2
+ query:
+ title: "Query"
+ description: "A classic query string."
+ type: "string"
+ order: 3
source-dockerhub:
type: "object"
required:
@@ -3679,27 +3957,17 @@ components:
example: "1.0.0"
order: 2
source-wikipedia-pageviews:
- title: "Wikipedia Pageviews Spec"
type: "object"
required:
- - "project"
- "access"
- "agent"
- "article"
- - "start"
- - "end"
- "country"
+ - "end"
+ - "project"
+ - "start"
- "sourceType"
properties:
- project:
- type: "string"
- title: "Project"
- description: "If you want to filter by project, use the domain of any Wikimedia\
- \ project."
- examples:
- - "en.wikipedia.org"
- - "www.mediawiki.org"
- - "commons.wikimedia.org"
access:
type: "string"
title: "Access"
@@ -3711,6 +3979,7 @@ components:
- "desktop"
- "mobile-app"
- "mobile-web"
+ order: 0
agent:
type: "string"
title: "Agent"
@@ -3722,6 +3991,7 @@ components:
- "user"
- "spider"
- "automated"
+ order: 1
article:
type: "string"
title: "Article"
@@ -3730,16 +4000,7 @@ components:
\ so that non-URI-safe characters like %, / or ? are accepted."
examples:
- "Are_You_the_One%3F"
- start:
- type: "string"
- title: "Start"
- description: "The date of the first day to include, in YYYYMMDD or YYYYMMDDHH\
- \ format."
- end:
- type: "string"
- title: "End"
- description: "The date of the last day to include, in YYYYMMDD or YYYYMMDDHH\
- \ format."
+ order: 2
country:
type: "string"
title: "Country"
@@ -3748,6 +4009,29 @@ components:
examples:
- "FR"
- "IN"
+ order: 3
+ end:
+ type: "string"
+ title: "End"
+ description: "The date of the last day to include, in YYYYMMDD or YYYYMMDDHH\
+ \ format."
+ order: 4
+ project:
+ type: "string"
+ title: "Project"
+ description: "If you want to filter by project, use the domain of any Wikimedia\
+ \ project."
+ examples:
+ - "en.wikipedia.org"
+ - "www.mediawiki.org"
+ - "commons.wikimedia.org"
+ order: 5
+ start:
+ type: "string"
+ title: "Start"
+ description: "The date of the first day to include, in YYYYMMDD or YYYYMMDDHH\
+ \ format. Also serves as the date to retrieve data for the top articles."
+ order: 6
sourceType:
title: "wikipedia-pageviews"
const: "wikipedia-pageviews"
@@ -3756,26 +4040,16 @@ components:
order: 0
type: "string"
source-wikipedia-pageviews-update:
- title: "Wikipedia Pageviews Spec"
type: "object"
required:
- - "project"
- "access"
- "agent"
- "article"
- - "start"
- - "end"
- "country"
+ - "end"
+ - "project"
+ - "start"
properties:
- project:
- type: "string"
- title: "Project"
- description: "If you want to filter by project, use the domain of any Wikimedia\
- \ project."
- examples:
- - "en.wikipedia.org"
- - "www.mediawiki.org"
- - "commons.wikimedia.org"
access:
type: "string"
title: "Access"
@@ -3787,6 +4061,7 @@ components:
- "desktop"
- "mobile-app"
- "mobile-web"
+ order: 0
agent:
type: "string"
title: "Agent"
@@ -3798,6 +4073,7 @@ components:
- "user"
- "spider"
- "automated"
+ order: 1
article:
type: "string"
title: "Article"
@@ -3806,16 +4082,7 @@ components:
\ so that non-URI-safe characters like %, / or ? are accepted."
examples:
- "Are_You_the_One%3F"
- start:
- type: "string"
- title: "Start"
- description: "The date of the first day to include, in YYYYMMDD or YYYYMMDDHH\
- \ format."
- end:
- type: "string"
- title: "End"
- description: "The date of the last day to include, in YYYYMMDD or YYYYMMDDHH\
- \ format."
+ order: 2
country:
type: "string"
title: "Country"
@@ -3824,6 +4091,29 @@ components:
examples:
- "FR"
- "IN"
+ order: 3
+ end:
+ type: "string"
+ title: "End"
+ description: "The date of the last day to include, in YYYYMMDD or YYYYMMDDHH\
+ \ format."
+ order: 4
+ project:
+ type: "string"
+ title: "Project"
+ description: "If you want to filter by project, use the domain of any Wikimedia\
+ \ project."
+ examples:
+ - "en.wikipedia.org"
+ - "www.mediawiki.org"
+ - "commons.wikimedia.org"
+ order: 5
+ start:
+ type: "string"
+ title: "Start"
+ description: "The date of the first day to include, in YYYYMMDD or YYYYMMDDHH\
+ \ format. Also serves as the date to retrieve data for the top articles."
+ order: 6
source-google-directory:
title: "Google Directory Spec"
type: "object"
@@ -7207,6 +7497,14 @@ components:
\ data. If you are a `Shopify Plus` user, leave the default value to speed\
\ up the fetch."
default: false
+ job_termination_threshold:
+ type: "integer"
+ title: "BULK Job termination threshold"
+ description: "The max time in seconds, after which the single BULK Job should\
+ \ be `CANCELED` and retried. The bigger the value the longer the BULK\
+ \ Job is allowed to run."
+ default: 3600
+ minimum: 1
sourceType:
title: "shopify"
const: "shopify"
@@ -7308,18 +7606,26 @@ components:
\ data. If you are a `Shopify Plus` user, leave the default value to speed\
\ up the fetch."
default: false
+ job_termination_threshold:
+ type: "integer"
+ title: "BULK Job termination threshold"
+ description: "The max time in seconds, after which the single BULK Job should\
+ \ be `CANCELED` and retried. The bigger the value the longer the BULK\
+ \ Job is allowed to run."
+ default: 3600
+ minimum: 1
source-omnisend:
- title: "Omnisend Spec"
type: "object"
required:
- "api_key"
- "sourceType"
properties:
api_key:
- title: "API Key"
type: "string"
- description: "API Key"
+ title: "API Key"
airbyte_secret: true
+ description: "API Key"
+ order: 0
x-speakeasy-param-sensitive: true
sourceType:
title: "omnisend"
@@ -7329,16 +7635,16 @@ components:
order: 0
type: "string"
source-omnisend-update:
- title: "Omnisend Spec"
type: "object"
required:
- "api_key"
properties:
api_key:
- title: "API Key"
type: "string"
- description: "API Key"
+ title: "API Key"
airbyte_secret: true
+ description: "API Key"
+ order: 0
source-mongodb-v2:
title: "MongoDb Source Spec"
type: "object"
@@ -8368,7 +8674,7 @@ components:
type: "boolean"
required:
- "filetype"
- - title: "Document File Type Format (Experimental)"
+ - title: "Unstructured Document Format"
type: "object"
properties:
filetype:
@@ -9139,7 +9445,7 @@ components:
type: "boolean"
required:
- "filetype"
- - title: "Document File Type Format (Experimental)"
+ - title: "Unstructured Document Format"
type: "object"
properties:
filetype:
@@ -12192,13 +12498,51 @@ components:
airbyte_secret: true
order: 4
x-speakeasy-param-sensitive: true
+ - title: "Key Pair Authentication"
+ type: "object"
+ order: 1
+ required:
+ - "username"
+ - "private_key"
+ properties:
+ auth_type:
+ type: "string"
+ const: "Key Pair Authentication"
+ order: 0
+ enum:
+ - "Key Pair Authentication"
+ username:
+ description: "The username you created to allow Airbyte to access\
+ \ the database."
+ examples:
+ - "AIRBYTE_USER"
+ type: "string"
+ title: "Username"
+ order: 1
+ private_key:
+ type: "string"
+ title: "Private Key"
+ description: "RSA Private key to use for Snowflake connection. See\
+ \ the docs for more information on how to obtain this key."
+ multiline: true
+ airbyte_secret: true
+ order: 2
+ x-speakeasy-param-sensitive: true
+ private_key_password:
+ type: "string"
+ title: "Passphrase"
+ description: "Passphrase for private key"
+ airbyte_secret: true
+ order: 3
+ x-speakeasy-param-sensitive: true
- title: "Username and Password"
type: "object"
required:
- "username"
- "password"
- "auth_type"
- order: 1
+ order: 2
properties:
auth_type:
type: "string"
@@ -12325,13 +12669,49 @@ components:
description: "Refresh Token for making authenticated requests."
airbyte_secret: true
order: 4
+ - title: "Key Pair Authentication"
+ type: "object"
+ order: 1
+ required:
+ - "username"
+ - "private_key"
+ properties:
+ auth_type:
+ type: "string"
+ const: "Key Pair Authentication"
+ order: 0
+ enum:
+ - "Key Pair Authentication"
+ username:
+ description: "The username you created to allow Airbyte to access\
+ \ the database."
+ examples:
+ - "AIRBYTE_USER"
+ type: "string"
+ title: "Username"
+ order: 1
+ private_key:
+ type: "string"
+ title: "Private Key"
+ description: "RSA Private key to use for Snowflake connection. See\
+ \ the docs for more information on how to obtain this key."
+ multiline: true
+ airbyte_secret: true
+ order: 2
+ private_key_password:
+ type: "string"
+ title: "Passphrase"
+ description: "Passphrase for private key"
+ airbyte_secret: true
+ order: 3
- title: "Username and Password"
type: "object"
required:
- "username"
- "password"
- "auth_type"
- order: 1
+ order: 2
properties:
auth_type:
type: "string"
@@ -12956,7 +13336,7 @@ components:
type: "boolean"
required:
- "filetype"
- - title: "Document File Type Format (Experimental)"
+ - title: "Unstructured Document Format"
type: "object"
properties:
filetype:
@@ -13445,7 +13825,7 @@ components:
type: "boolean"
required:
- "filetype"
- - title: "Document File Type Format (Experimental)"
+ - title: "Unstructured Document Format"
type: "object"
properties:
filetype:
@@ -14822,6 +15202,16 @@ components:
default: "Fail sync"
order: 3
always_show: true
+ initial_load_timeout_hours:
+ type: "integer"
+ title: "Initial Load Timeout in Hours (Advanced)"
+ description: "The amount of time an initial load is allowed to continue\
+ \ for before catching up on CDC logs."
+ default: 8
+ min: 4
+ max: 24
+ order: 4
+ always_show: true
- title: "Scan Changes with User Defined Cursor"
description: "Incrementally detects new inserts and updates using the\
\ here."
airbyte_secret: true
+ source-goldcast:
+ title: "goldcast.io Source Spec"
+ type: "object"
+ required:
+ - "access_key"
+ - "sourceType"
+ properties:
+ access_key:
+ type: "string"
+ description: "Your API Access Key. See here. The key is case sensitive."
+ airbyte_secret: true
+ x-speakeasy-param-sensitive: true
+ sourceType:
+ title: "goldcast"
+ const: "goldcast"
+ enum:
+ - "goldcast"
+ order: 0
+ type: "string"
+ source-goldcast-update:
+ title: "goldcast.io Source Spec"
+ type: "object"
+ required:
+ - "access_key"
+ properties:
+ access_key:
+ type: "string"
+ description: "Your API Access Key. See here. The key is case sensitive."
+ airbyte_secret: true
source-pinterest:
title: "Pinterest Spec"
type: "object"
@@ -20046,190 +20483,6 @@ components:
desciption: "Optional, Possible values for an endpoint. Example values for\
\ launches-latest, upcoming, past"
order: 1
- source-google-analytics-v4-service-account-only:
- title: "Google Analytics (V4) Spec"
- type: "object"
- required:
- - "view_id"
- - "start_date"
- - "sourceType"
- properties:
- credentials:
- order: 0
- type: "object"
- title: "Credentials"
- description: "Credentials for the service"
- oneOf:
- - type: "object"
- title: "Service Account Key Authentication"
- required:
- - "credentials_json"
- properties:
- auth_type:
- type: "string"
- const: "Service"
- order: 0
- enum:
- - "Service"
- credentials_json:
- title: "Service Account JSON Key"
- type: "string"
- description: "The JSON key of the service account to use for authorization"
- examples:
- - "{ \"type\": \"service_account\", \"project_id\": YOUR_PROJECT_ID,\
- \ \"private_key_id\": YOUR_PRIVATE_KEY, ... }"
- airbyte_secret: true
- start_date:
- order: 1
- type: "string"
- title: "Replication Start Date"
- description: "The date in the format YYYY-MM-DD. Any data before this date\
- \ will not be replicated."
- examples:
- - "2020-06-01"
- pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}$|^$|[\\s\\S]+$"
- format: "date"
- view_id:
- order: 2
- type: "string"
- title: "View ID"
- description: "The ID for the Google Analytics View you want to fetch data\
- \ from. This can be found from the Google Analytics Account Explorer."
- end_date:
- order: 3
- type: "string"
- title: "Replication End Date"
- description: "The date in the format YYYY-MM-DD. Any data after this date\
- \ will not be replicated."
- examples:
- - "2020-06-01"
- pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}$|^$|[\\s\\S]+$"
- format: "date"
- custom_reports:
- order: 4
- type: "string"
- title: "Custom Reports"
- description: "A JSON array describing the custom reports you want to sync\
- \ from Google Analytics. See the docs for more information about the exact format you can use\
- \ to fill out this field."
- window_in_days:
- type: "integer"
- title: "Data request time increment in days"
- description: "The time increment used by the connector when requesting data\
- \ from the Google Analytics API. More information is available in the\
- \ the docs. The bigger this value is, the faster the sync will be,\
- \ but the more likely that sampling will be applied to your data, potentially\
- \ causing inaccuracies in the returned results. We recommend setting this\
- \ to 1 unless you have a hard requirement to make the sync faster at the\
- \ expense of accuracy. The minimum allowed value for this field is 1,\
- \ and the maximum is 364. "
- examples:
- - 30
- - 60
- - 90
- - 120
- - 200
- - 364
- default: 1
- order: 5
- sourceType:
- title: "google-analytics-v4-service-account-only"
- const: "google-analytics-v4-service-account-only"
- enum:
- - "google-analytics-v4-service-account-only"
- order: 0
- type: "string"
- source-google-analytics-v4-service-account-only-update:
- title: "Google Analytics (V4) Spec"
- type: "object"
- required:
- - "view_id"
- - "start_date"
- properties:
- credentials:
- order: 0
- type: "object"
- title: "Credentials"
- description: "Credentials for the service"
- oneOf:
- - type: "object"
- title: "Service Account Key Authentication"
- required:
- - "credentials_json"
- properties:
- auth_type:
- type: "string"
- const: "Service"
- order: 0
- enum:
- - "Service"
- credentials_json:
- title: "Service Account JSON Key"
- type: "string"
- description: "The JSON key of the service account to use for authorization"
- examples:
- - "{ \"type\": \"service_account\", \"project_id\": YOUR_PROJECT_ID,\
- \ \"private_key_id\": YOUR_PRIVATE_KEY, ... }"
- airbyte_secret: true
- start_date:
- order: 1
- type: "string"
- title: "Replication Start Date"
- description: "The date in the format YYYY-MM-DD. Any data before this date\
- \ will not be replicated."
- examples:
- - "2020-06-01"
- pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}$|^$|[\\s\\S]+$"
- format: "date"
- view_id:
- order: 2
- type: "string"
- title: "View ID"
- description: "The ID for the Google Analytics View you want to fetch data\
- \ from. This can be found from the Google Analytics Account Explorer."
- end_date:
- order: 3
- type: "string"
- title: "Replication End Date"
- description: "The date in the format YYYY-MM-DD. Any data after this date\
- \ will not be replicated."
- examples:
- - "2020-06-01"
- pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}$|^$|[\\s\\S]+$"
- format: "date"
- custom_reports:
- order: 4
- type: "string"
- title: "Custom Reports"
- description: "A JSON array describing the custom reports you want to sync\
- \ from Google Analytics. See the docs for more information about the exact format you can use\
- \ to fill out this field."
- window_in_days:
- type: "integer"
- title: "Data request time increment in days"
- description: "The time increment used by the connector when requesting data\
- \ from the Google Analytics API. More information is available in the\
- \ the docs. The bigger this value is, the faster the sync will be,\
- \ but the more likely that sampling will be applied to your data, potentially\
- \ causing inaccuracies in the returned results. We recommend setting this\
- \ to 1 unless you have a hard requirement to make the sync faster at the\
- \ expense of accuracy. The minimum allowed value for this field is 1,\
- \ and the maximum is 364. "
- examples:
- - 30
- - 60
- - 90
- - 120
- - 200
- - 364
- default: 1
- order: 5
source-bamboo-hr:
title: "Bamboo HR Spec"
type: "object"
@@ -22421,7 +22674,7 @@ components:
type: "boolean"
required:
- "filetype"
- - title: "Document File Type Format (Experimental)"
+ - title: "Unstructured Document Format"
type: "object"
properties:
filetype:
@@ -22916,7 +23169,7 @@ components:
type: "boolean"
required:
- "filetype"
- - title: "Document File Type Format (Experimental)"
+ - title: "Unstructured Document Format"
type: "object"
properties:
filetype:
@@ -23099,70 +23352,6 @@ components:
required:
- "streams"
- "credentials"
- source-punk-api:
- title: "Punk Api Spec"
- type: "object"
- required:
- - "brewed_before"
- - "brewed_after"
- - "sourceType"
- properties:
- id:
- title: "Beers with specific ID"
- type: "string"
- description: "To extract specific data with Unique ID"
- examples:
- - 1
- - 22
- brewed_before:
- title: "Brewed before data to get incremental reads"
- type: "string"
- description: "To extract specific data with Unique ID"
- pattern: "^[0-9]{2}-[0-9]{4}$"
- examples:
- - "MM-YYYY"
- brewed_after:
- title: "Brewed after data to get incremental reads"
- type: "string"
- description: "To extract specific data with Unique ID"
- pattern: "^[0-9]{2}-[0-9]{4}$"
- examples:
- - "MM-YYYY"
- sourceType:
- title: "punk-api"
- const: "punk-api"
- enum:
- - "punk-api"
- order: 0
- type: "string"
- source-punk-api-update:
- title: "Punk Api Spec"
- type: "object"
- required:
- - "brewed_before"
- - "brewed_after"
- properties:
- id:
- title: "Beers with specific ID"
- type: "string"
- description: "To extract specific data with Unique ID"
- examples:
- - 1
- - 22
- brewed_before:
- title: "Brewed before data to get incremental reads"
- type: "string"
- description: "To extract specific data with Unique ID"
- pattern: "^[0-9]{2}-[0-9]{4}$"
- examples:
- - "MM-YYYY"
- brewed_after:
- title: "Brewed after data to get incremental reads"
- type: "string"
- description: "To extract specific data with Unique ID"
- pattern: "^[0-9]{2}-[0-9]{4}$"
- examples:
- - "MM-YYYY"
source-tiktok-marketing:
title: "TikTok Marketing Source Spec"
type: "object"
@@ -23262,8 +23451,10 @@ components:
order: 3
type: "integer"
include_deleted:
- title: "Include Deleted Data in Reports"
- description: "Set to active if you want to include deleted data in reports."
+ title: "Include Deleted Data in Reports and Ads, Ad Groups and Campaign\
+ \ streams."
+ description: "Set to active if you want to include deleted data in report\
+ \ based streams and Ads, Ad Groups and Campaign streams."
default: false
order: 4
type: "boolean"
@@ -23371,8 +23562,10 @@ components:
order: 3
type: "integer"
include_deleted:
- title: "Include Deleted Data in Reports"
- description: "Set to active if you want to include deleted data in reports."
+ title: "Include Deleted Data in Reports and Ads, Ad Groups and Campaign\
+ \ streams."
+ description: "Set to active if you want to include deleted data in report\
+ \ based streams and Ads, Ad Groups and Campaign streams."
default: false
order: 4
type: "boolean"
@@ -23383,7 +23576,6 @@ components:
- "aws_key_id"
- "aws_secret_key"
- "aws_region_name"
- - "start_date"
- "sourceType"
properties:
aws_key_id:
@@ -23406,6 +23598,7 @@ components:
description: "The default AWS Region to use, for example, us-west-1 or us-west-2.\
\ When specifying a Region inline during client initialization, this property\
\ is named region_name."
+ default: "us-east-1"
start_date:
type: "string"
title: "Start Date"
@@ -23413,9 +23606,30 @@ components:
\ is available for last 90 days only. Format: YYYY-MM-DD."
examples:
- "2021-01-01"
- default: "1970-01-01"
pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}$"
format: "date"
+ lookup_attributes_filter:
+ title: "Filter applied while fetching records based on AttributeKey and\
+ \ AttributeValue which will be appended on the request body"
+ type: "object"
+ required:
+ - "attribute_key"
+ - "attribute_value"
+ properties:
+ attribute_key:
+ type: "string"
+ title: "Attribute Key from the response to filter"
+ examples:
+ - "EventName"
+ default: "EventName"
+ x-speakeasy-param-sensitive: true
+ attribute_value:
+ type: "string"
+ title: "Corresponding value to the given attribute key"
+ examples:
+ - "ListInstanceAssociations"
+ - "ConsoleLogin"
+ default: "ListInstanceAssociations"
sourceType:
title: "aws-cloudtrail"
const: "aws-cloudtrail"
@@ -23430,7 +23644,6 @@ components:
- "aws_key_id"
- "aws_secret_key"
- "aws_region_name"
- - "start_date"
properties:
aws_key_id:
type: "string"
@@ -23450,6 +23663,7 @@ components:
description: "The default AWS Region to use, for example, us-west-1 or us-west-2.\
\ When specifying a Region inline during client initialization, this property\
\ is named region_name."
+ default: "us-east-1"
start_date:
type: "string"
title: "Start Date"
@@ -23457,9 +23671,29 @@ components:
\ is available for last 90 days only. Format: YYYY-MM-DD."
examples:
- "2021-01-01"
- default: "1970-01-01"
pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}$"
format: "date"
+ lookup_attributes_filter:
+ title: "Filter applied while fetching records based on AttributeKey and\
+ \ AttributeValue which will be appended on the request body"
+ type: "object"
+ required:
+ - "attribute_key"
+ - "attribute_value"
+ properties:
+ attribute_key:
+ type: "string"
+ title: "Attribute Key from the response to filter"
+ examples:
+ - "EventName"
+ default: "EventName"
+ attribute_value:
+ type: "string"
+ title: "Corresponding value to the given attribute key"
+ examples:
+ - "ListInstanceAssociations"
+ - "ConsoleLogin"
+ default: "ListInstanceAssociations"
source-jira:
title: "Jira Spec"
type: "object"
@@ -29451,6 +29685,68 @@ components:
airbyte_secret: true
type: "string"
x-speakeasy-param-sensitive: true
+ credentials:
+ title: "Authentication"
+ description: "Credentials for connecting to the Facebook Marketing API"
+ type: "object"
+ oneOf:
+ - title: "Authenticate via Facebook Marketing (Oauth)"
+ type: "object"
+ properties:
+ auth_type:
+ title: "Auth Type"
+ default: "Client"
+ const: "Client"
+ enum:
+ - "Client"
+ type: "string"
+ client_id:
+ title: "Client ID"
+ description: "Client ID for the Facebook Marketing API"
+ airbyte_secret: true
+ type: "string"
+ client_secret:
+ title: "Client Secret"
+ description: "Client Secret for the Facebook Marketing API"
+ airbyte_secret: true
+ type: "string"
+ access_token:
+ title: "Access Token"
+ description: "The value of the generated access token. From your App’\
+ s Dashboard, click on \"Marketing API\" then \"Tools\". Select permissions\
+ \ ads_management, ads_read, read_insights, business_management.\
+ \ Then click on \"Get token\". See the docs for more information."
+ airbyte_secret: true
+ type: "string"
+ x-speakeasy-param-sensitive: true
+ required:
+ - "client_id"
+ - "client_secret"
+ - "auth_type"
+ - title: "Service Account Key Authentication"
+ type: "object"
+ properties:
+ auth_type:
+ title: "Auth Type"
+ default: "Service"
+ const: "Service"
+ enum:
+ - "Service"
+ type: "string"
+ access_token:
+ title: "Access Token"
+ description: "The value of the generated access token. From your App’\
+ s Dashboard, click on \"Marketing API\" then \"Tools\". Select permissions\
+ \ ads_management, ads_read, read_insights, business_management.\
+ \ Then click on \"Get token\". See the docs for more information."
+ airbyte_secret: true
+ type: "string"
+ x-speakeasy-param-sensitive: true
+ required:
+ - "access_token"
+ - "auth_type"
start_date:
title: "Start Date"
description: "The date from which you'd like to replicate data for all incremental\
@@ -29590,7 +29886,6 @@ components:
- "adset_end"
- "adset_id"
- "adset_name"
- - "adset_start"
- "age_targeting"
- "attribution_setting"
- "auction_bid"
@@ -29947,6 +30242,66 @@ components:
order: 1
airbyte_secret: true
type: "string"
+ credentials:
+ title: "Authentication"
+ description: "Credentials for connecting to the Facebook Marketing API"
+ type: "object"
+ oneOf:
+ - title: "Authenticate via Facebook Marketing (Oauth)"
+ type: "object"
+ properties:
+ auth_type:
+ title: "Auth Type"
+ default: "Client"
+ const: "Client"
+ enum:
+ - "Client"
+ type: "string"
+ client_id:
+ title: "Client ID"
+ description: "Client ID for the Facebook Marketing API"
+ airbyte_secret: true
+ type: "string"
+ client_secret:
+ title: "Client Secret"
+ description: "Client Secret for the Facebook Marketing API"
+ airbyte_secret: true
+ type: "string"
+ access_token:
+ title: "Access Token"
+ description: "The value of the generated access token. From your App’\
+ s Dashboard, click on \"Marketing API\" then \"Tools\". Select permissions\
+ \ ads_management, ads_read, read_insights, business_management.\
+ \ Then click on \"Get token\". See the docs for more information."
+ airbyte_secret: true
+ type: "string"
+ required:
+ - "client_id"
+ - "client_secret"
+ - "auth_type"
+ - title: "Service Account Key Authentication"
+ type: "object"
+ properties:
+ auth_type:
+ title: "Auth Type"
+ default: "Service"
+ const: "Service"
+ enum:
+ - "Service"
+ type: "string"
+ access_token:
+ title: "Access Token"
+ description: "The value of the generated access token. From your App’\
+ s Dashboard, click on \"Marketing API\" then \"Tools\". Select permissions\
+ \ ads_management, ads_read, read_insights, business_management.\
+ \ Then click on \"Get token\". See the docs for more information."
+ airbyte_secret: true
+ type: "string"
+ required:
+ - "access_token"
+ - "auth_type"
start_date:
title: "Start Date"
description: "The date from which you'd like to replicate data for all incremental\
@@ -30086,7 +30441,6 @@ components:
- "adset_end"
- "adset_id"
- "adset_name"
- - "adset_start"
- "age_targeting"
- "attribution_setting"
- "auction_bid"
@@ -30405,7 +30759,6 @@ components:
required:
- "account_ids"
source-recruitee:
- title: "Recruitee Spec"
type: "object"
required:
- "api_key"
@@ -30413,18 +30766,20 @@ components:
- "sourceType"
properties:
api_key:
- title: "API Key"
type: "string"
+ title: "API Key"
+ airbyte_secret: true
description: "Recruitee API Key. See here."
- airbyte_secret: true
+ order: 0
x-speakeasy-param-sensitive: true
company_id:
- title: "Company ID"
type: "integer"
+ title: "Company ID"
description: "Recruitee Company ID. You can also find this ID on the Recruitee API\
\ tokens page."
+ order: 1
sourceType:
title: "recruitee"
const: "recruitee"
@@ -30433,24 +30788,25 @@ components:
order: 0
type: "string"
source-recruitee-update:
- title: "Recruitee Spec"
type: "object"
required:
- "api_key"
- "company_id"
properties:
api_key:
- title: "API Key"
type: "string"
+ title: "API Key"
+ airbyte_secret: true
description: "Recruitee API Key. See here."
- airbyte_secret: true
+ order: 0
company_id:
- title: "Company ID"
type: "integer"
+ title: "Company ID"
description: "Recruitee Company ID. You can also find this ID on the Recruitee API\
\ tokens page."
+ order: 1
source-survey-sparrow:
type: "object"
required:
@@ -33431,18 +33787,18 @@ components:
- "client_secret"
- "refresh_token"
source-sendinblue:
- title: "Sendinblue Spec"
type: "object"
required:
- "api_key"
- "sourceType"
properties:
api_key:
- title: "API Key"
type: "string"
+ title: "API Key"
+ airbyte_secret: true
description: "Your API Key. See here."
- airbyte_secret: true
+ order: 0
x-speakeasy-param-sensitive: true
sourceType:
title: "sendinblue"
@@ -33452,17 +33808,17 @@ components:
order: 0
type: "string"
source-sendinblue-update:
- title: "Sendinblue Spec"
type: "object"
required:
- "api_key"
properties:
api_key:
- title: "API Key"
type: "string"
+ title: "API Key"
+ airbyte_secret: true
description: "Your API Key. See here."
- airbyte_secret: true
+ order: 0
source-github:
title: "GitHub Source Spec"
type: "object"
@@ -33954,6 +34310,46 @@ components:
type: "string"
title: "Engine"
description: "Engine name to connect to."
+ source-clazar:
+ type: "object"
+ required:
+ - "client_id"
+ - "client_secret"
+ - "sourceType"
+ properties:
+ client_id:
+ type: "string"
+ order: 0
+ title: "Client ID"
+ airbyte_secret: true
+ client_secret:
+ type: "string"
+ order: 1
+ title: "Client secret"
+ airbyte_secret: true
+ sourceType:
+ title: "clazar"
+ const: "clazar"
+ enum:
+ - "clazar"
+ order: 0
+ type: "string"
+ source-clazar-update:
+ type: "object"
+ required:
+ - "client_id"
+ - "client_secret"
+ properties:
+ client_id:
+ type: "string"
+ order: 0
+ title: "Client ID"
+ airbyte_secret: true
+ client_secret:
+ type: "string"
+ order: 1
+ title: "Client secret"
+ airbyte_secret: true
source-outreach:
title: "Source Outreach Spec"
type: "object"
@@ -36285,31 +36681,22 @@ components:
default: false
order: 3
source-paystack:
- title: "Paystack Source Spec"
type: "object"
required:
- - "secret_key"
- "start_date"
+ - "secret_key"
- "sourceType"
properties:
- secret_key:
- type: "string"
- title: "Secret Key"
- pattern: "^(s|r)k_(live|test)_[a-zA-Z0-9]+$"
- description: "The Paystack API key (usually starts with 'sk_live_'; find\
- \ yours here)."
- airbyte_secret: true
- x-speakeasy-param-sensitive: true
start_date:
type: "string"
title: "Start Date"
+ format: "date-time"
pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}Z$"
description: "UTC date and time in the format 2017-01-25T00:00:00Z. Any\
\ data before this date will not be replicated."
examples:
- "2017-01-25T00:00:00Z"
- format: "date-time"
+ order: 0
lookback_window_days:
type: "integer"
title: "Lookback Window (in days)"
@@ -36318,6 +36705,17 @@ components:
description: "When set, the connector will always reload data from the past\
\ N days, where N is the value set here. This is useful if your data is\
\ updated after creation."
+ order: 1
+ secret_key:
+ type: "string"
+ title: "Secret Key"
+ pattern: "^(s|r)k_(live|test)_[a-zA-Z0-9]+$"
+ description: "The Paystack API key (usually starts with 'sk_live_'; find\
+ \ yours here)."
+ airbyte_secret: true
+ order: 2
+ x-speakeasy-param-sensitive: true
sourceType:
title: "paystack"
const: "paystack"
@@ -36326,29 +36724,21 @@ components:
order: 0
type: "string"
source-paystack-update:
- title: "Paystack Source Spec"
type: "object"
required:
- - "secret_key"
- "start_date"
+ - "secret_key"
properties:
- secret_key:
- type: "string"
- title: "Secret Key"
- pattern: "^(s|r)k_(live|test)_[a-zA-Z0-9]+$"
- description: "The Paystack API key (usually starts with 'sk_live_'; find\
- \ yours here)."
- airbyte_secret: true
start_date:
type: "string"
title: "Start Date"
+ format: "date-time"
pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}Z$"
description: "UTC date and time in the format 2017-01-25T00:00:00Z. Any\
\ data before this date will not be replicated."
examples:
- "2017-01-25T00:00:00Z"
- format: "date-time"
+ order: 0
lookback_window_days:
type: "integer"
title: "Lookback Window (in days)"
@@ -36357,6 +36747,16 @@ components:
description: "When set, the connector will always reload data from the past\
\ N days, where N is the value set here. This is useful if your data is\
\ updated after creation."
+ order: 1
+ secret_key:
+ type: "string"
+ title: "Secret Key"
+ pattern: "^(s|r)k_(live|test)_[a-zA-Z0-9]+$"
+ description: "The Paystack API key (usually starts with 'sk_live_'; find\
+ \ yours here)."
+ airbyte_secret: true
+ order: 2
source-redshift:
title: "Redshift Source Spec"
type: "object"
@@ -40593,7 +40993,6 @@ components:
examples:
- "2022-08"
- "1851-01"
- format: "date"
order: 1
end_date:
type: "string"
@@ -40603,7 +41002,6 @@ components:
examples:
- "2022-08"
- "1851-01"
- format: "date"
order: 2
period:
type: "integer"
@@ -40650,7 +41048,6 @@ components:
examples:
- "2022-08"
- "1851-01"
- format: "date"
order: 1
end_date:
type: "string"
@@ -40660,7 +41057,6 @@ components:
examples:
- "2022-08"
- "1851-01"
- format: "date"
order: 2
period:
type: "integer"
@@ -45965,8 +46361,8 @@ components:
type: "string"
warehouse:
title: "Warehouse"
- description: "Enter the name of the warehouse that you want to sync\
- \ data into"
+ description: "Enter the name of the warehouse that you want to use as\
+ \ a compute cluster"
order: 3
examples:
- "AIRBYTE_WAREHOUSE"
@@ -46402,8 +46798,8 @@ components:
type: "string"
warehouse:
title: "Warehouse"
- description: "Enter the name of the warehouse that you want to sync\
- \ data into"
+ description: "Enter the name of the warehouse that you want to use as\
+ \ a compute cluster"
order: 3
examples:
- "AIRBYTE_WAREHOUSE"
@@ -46750,47 +47146,6 @@ components:
> docs for details."
default: true
order: 6
- encryption:
- title: "Encryption"
- type: "object"
- description: "How to encrypt the staging data"
- default:
- encryption_type: "none"
- oneOf:
- - title: "No encryption"
- description: "Staging data will be stored in plaintext."
- type: "object"
- required:
- - "encryption_type"
- properties:
- encryption_type:
- type: "string"
- const: "none"
- enum:
- - "none"
- default: "none"
- - title: "AES-CBC envelope encryption"
- description: "Staging data will be encrypted using AES-CBC envelope\
- \ encryption."
- type: "object"
- required:
- - "encryption_type"
- properties:
- encryption_type:
- type: "string"
- const: "aes_cbc_envelope"
- enum:
- - "aes_cbc_envelope"
- default: "aes_cbc_envelope"
- key_encrypting_key:
- type: "string"
- title: "Key"
- description: "The key, base64-encoded. Must be either 128, 192,\
- \ or 256 bits. Leave blank to have Airbyte generate an ephemeral\
- \ key for each sync."
- airbyte_secret: true
- x-speakeasy-param-sensitive: true
- order: 7
raw_data_schema:
type: "string"
description: "The schema to write raw tables into (default: airbyte_internal)."
@@ -47123,46 +47478,6 @@ components:
> docs for details."
default: true
order: 6
- encryption:
- title: "Encryption"
- type: "object"
- description: "How to encrypt the staging data"
- default:
- encryption_type: "none"
- oneOf:
- - title: "No encryption"
- description: "Staging data will be stored in plaintext."
- type: "object"
- required:
- - "encryption_type"
- properties:
- encryption_type:
- type: "string"
- const: "none"
- enum:
- - "none"
- default: "none"
- - title: "AES-CBC envelope encryption"
- description: "Staging data will be encrypted using AES-CBC envelope\
- \ encryption."
- type: "object"
- required:
- - "encryption_type"
- properties:
- encryption_type:
- type: "string"
- const: "aes_cbc_envelope"
- enum:
- - "aes_cbc_envelope"
- default: "aes_cbc_envelope"
- key_encrypting_key:
- type: "string"
- title: "Key"
- description: "The key, base64-encoded. Must be either 128, 192,\
- \ or 256 bits. Leave blank to have Airbyte generate an ephemeral\
- \ key for each sync."
- airbyte_secret: true
- order: 7
raw_data_schema:
type: "string"
description: "The schema to write raw tables into (default: airbyte_internal)."
@@ -48366,7 +48681,7 @@ components:
order: 1
warehouse:
description: "Enter the name of the warehouse that you want to sync data into"
+ >warehouse that you want to use as a compute cluster"
examples:
- "AIRBYTE_WAREHOUSE"
type: "string"
@@ -48556,7 +48871,7 @@ components:
order: 1
warehouse:
description: "Enter the name of the warehouse that you want to sync data into"
+ >warehouse that you want to use as a compute cluster"
examples:
- "AIRBYTE_WAREHOUSE"
type: "string"
@@ -55486,372 +55801,6 @@ components:
type: "boolean"
default: false
description: "Add file extensions to the output file."
- destination-langchain:
- title: "Langchain Destination Config"
- type: "object"
- properties:
- processing:
- title: "ProcessingConfigModel"
- type: "object"
- properties:
- chunk_size:
- title: "Chunk size"
- description: "Size of chunks in tokens to store in vector store (make\
- \ sure it is not too big for the context if your LLM)"
- maximum: 8191
- type: "integer"
- chunk_overlap:
- title: "Chunk overlap"
- description: "Size of overlap between chunks in tokens to store in vector\
- \ store to better capture relevant context"
- default: 0
- type: "integer"
- text_fields:
- title: "Text fields to embed"
- description: "List of fields in the record that should be used to calculate\
- \ the embedding. All other fields are passed along as meta fields.\
- \ The field list is applied to all streams in the same way and non-existing\
- \ fields are ignored. If none are defined, all fields are considered\
- \ text fields. When specifying text fields, you can access nested\
- \ fields in the record by using dot notation, e.g. `user.name` will\
- \ access the `name` field in the `user` object. It's also possible\
- \ to use wildcards to access all fields in an object, e.g. `users.*.name`\
- \ will access all `names` fields in all entries of the `users` array."
- always_show: true
- examples:
- - "text"
- - "user.name"
- - "users.*.name"
- type: "array"
- items:
- type: "string"
- required:
- - "chunk_size"
- - "text_fields"
- group: "processing"
- embedding:
- title: "Embedding"
- description: "Embedding configuration"
- group: "embedding"
- type: "object"
- oneOf:
- - title: "OpenAI"
- type: "object"
- properties:
- mode:
- title: "Mode"
- default: "openai"
- const: "openai"
- enum:
- - "openai"
- type: "string"
- openai_key:
- title: "OpenAI API key"
- airbyte_secret: true
- type: "string"
- x-speakeasy-param-sensitive: true
- required:
- - "openai_key"
- description: "Use the OpenAI API to embed text. This option is using the\
- \ text-embedding-ada-002 model with 1536 embedding dimensions."
- - title: "Fake"
- type: "object"
- properties:
- mode:
- title: "Mode"
- default: "fake"
- const: "fake"
- enum:
- - "fake"
- type: "string"
- description: "Use a fake embedding made out of random vectors with 1536\
- \ embedding dimensions. This is useful for testing the data pipeline\
- \ without incurring any costs."
- indexing:
- title: "Indexing"
- description: "Indexing configuration"
- group: "indexing"
- type: "object"
- oneOf:
- - title: "Pinecone"
- type: "object"
- properties:
- mode:
- title: "Mode"
- default: "pinecone"
- const: "pinecone"
- enum:
- - "pinecone"
- type: "string"
- pinecone_key:
- title: "Pinecone API key"
- airbyte_secret: true
- type: "string"
- x-speakeasy-param-sensitive: true
- pinecone_environment:
- title: "Pinecone environment"
- description: "Pinecone environment to use"
- type: "string"
- index:
- title: "Index"
- description: "Pinecone index to use"
- type: "string"
- required:
- - "pinecone_key"
- - "pinecone_environment"
- - "index"
- description: "Pinecone is a popular vector store that can be used to store\
- \ and retrieve embeddings. It is a managed service and can also be queried\
- \ from outside of langchain."
- - title: "DocArrayHnswSearch"
- type: "object"
- properties:
- mode:
- title: "Mode"
- default: "DocArrayHnswSearch"
- const: "DocArrayHnswSearch"
- enum:
- - "DocArrayHnswSearch"
- type: "string"
- destination_path:
- title: "Destination Path"
- description: "Path to the directory where hnswlib and meta data files\
- \ will be written. The files will be placed inside that local mount.\
- \ All files in the specified destination directory will be deleted\
- \ on each run."
- examples:
- - "/local/my_hnswlib_index"
- type: "string"
- required:
- - "destination_path"
- description: "DocArrayHnswSearch is a lightweight Document Index implementation\
- \ provided by Docarray that runs fully locally and is best suited for\
- \ small- to medium-sized datasets. It stores vectors on disk in hnswlib,\
- \ and stores all other data in SQLite."
- - title: "Chroma (local persistance)"
- type: "object"
- properties:
- mode:
- title: "Mode"
- default: "chroma_local"
- const: "chroma_local"
- enum:
- - "chroma_local"
- type: "string"
- destination_path:
- title: "Destination Path"
- description: "Path to the directory where chroma files will be written.\
- \ The files will be placed inside that local mount."
- examples:
- - "/local/my_chroma_db"
- type: "string"
- collection_name:
- title: "Collection Name"
- description: "Name of the collection to use."
- default: "langchain"
- type: "string"
- required:
- - "destination_path"
- description: "Chroma is a popular vector store that can be used to store\
- \ and retrieve embeddings. It will build its index in memory and persist\
- \ it to disk by the end of the sync."
- destinationType:
- title: "langchain"
- const: "langchain"
- enum:
- - "langchain"
- order: 0
- type: "string"
- required:
- - "processing"
- - "embedding"
- - "indexing"
- - "destinationType"
- groups:
- - id: "processing"
- title: "Processing"
- - id: "embedding"
- title: "Embedding"
- - id: "indexing"
- title: "Indexing"
- destination-langchain-update:
- title: "Langchain Destination Config"
- type: "object"
- properties:
- processing:
- title: "ProcessingConfigModel"
- type: "object"
- properties:
- chunk_size:
- title: "Chunk size"
- description: "Size of chunks in tokens to store in vector store (make\
- \ sure it is not too big for the context if your LLM)"
- maximum: 8191
- type: "integer"
- chunk_overlap:
- title: "Chunk overlap"
- description: "Size of overlap between chunks in tokens to store in vector\
- \ store to better capture relevant context"
- default: 0
- type: "integer"
- text_fields:
- title: "Text fields to embed"
- description: "List of fields in the record that should be used to calculate\
- \ the embedding. All other fields are passed along as meta fields.\
- \ The field list is applied to all streams in the same way and non-existing\
- \ fields are ignored. If none are defined, all fields are considered\
- \ text fields. When specifying text fields, you can access nested\
- \ fields in the record by using dot notation, e.g. `user.name` will\
- \ access the `name` field in the `user` object. It's also possible\
- \ to use wildcards to access all fields in an object, e.g. `users.*.name`\
- \ will access all `names` fields in all entries of the `users` array."
- always_show: true
- examples:
- - "text"
- - "user.name"
- - "users.*.name"
- type: "array"
- items:
- type: "string"
- required:
- - "chunk_size"
- - "text_fields"
- group: "processing"
- embedding:
- title: "Embedding"
- description: "Embedding configuration"
- group: "embedding"
- type: "object"
- oneOf:
- - title: "OpenAI"
- type: "object"
- properties:
- mode:
- title: "Mode"
- default: "openai"
- const: "openai"
- enum:
- - "openai"
- type: "string"
- openai_key:
- title: "OpenAI API key"
- airbyte_secret: true
- type: "string"
- required:
- - "openai_key"
- description: "Use the OpenAI API to embed text. This option is using the\
- \ text-embedding-ada-002 model with 1536 embedding dimensions."
- - title: "Fake"
- type: "object"
- properties:
- mode:
- title: "Mode"
- default: "fake"
- const: "fake"
- enum:
- - "fake"
- type: "string"
- description: "Use a fake embedding made out of random vectors with 1536\
- \ embedding dimensions. This is useful for testing the data pipeline\
- \ without incurring any costs."
- indexing:
- title: "Indexing"
- description: "Indexing configuration"
- group: "indexing"
- type: "object"
- oneOf:
- - title: "Pinecone"
- type: "object"
- properties:
- mode:
- title: "Mode"
- default: "pinecone"
- const: "pinecone"
- enum:
- - "pinecone"
- type: "string"
- pinecone_key:
- title: "Pinecone API key"
- airbyte_secret: true
- type: "string"
- pinecone_environment:
- title: "Pinecone environment"
- description: "Pinecone environment to use"
- type: "string"
- index:
- title: "Index"
- description: "Pinecone index to use"
- type: "string"
- required:
- - "pinecone_key"
- - "pinecone_environment"
- - "index"
- description: "Pinecone is a popular vector store that can be used to store\
- \ and retrieve embeddings. It is a managed service and can also be queried\
- \ from outside of langchain."
- - title: "DocArrayHnswSearch"
- type: "object"
- properties:
- mode:
- title: "Mode"
- default: "DocArrayHnswSearch"
- const: "DocArrayHnswSearch"
- enum:
- - "DocArrayHnswSearch"
- type: "string"
- destination_path:
- title: "Destination Path"
- description: "Path to the directory where hnswlib and meta data files\
- \ will be written. The files will be placed inside that local mount.\
- \ All files in the specified destination directory will be deleted\
- \ on each run."
- examples:
- - "/local/my_hnswlib_index"
- type: "string"
- required:
- - "destination_path"
- description: "DocArrayHnswSearch is a lightweight Document Index implementation\
- \ provided by Docarray that runs fully locally and is best suited for\
- \ small- to medium-sized datasets. It stores vectors on disk in hnswlib,\
- \ and stores all other data in SQLite."
- - title: "Chroma (local persistance)"
- type: "object"
- properties:
- mode:
- title: "Mode"
- default: "chroma_local"
- const: "chroma_local"
- enum:
- - "chroma_local"
- type: "string"
- destination_path:
- title: "Destination Path"
- description: "Path to the directory where chroma files will be written.\
- \ The files will be placed inside that local mount."
- examples:
- - "/local/my_chroma_db"
- type: "string"
- collection_name:
- title: "Collection Name"
- description: "Name of the collection to use."
- default: "langchain"
- type: "string"
- required:
- - "destination_path"
- description: "Chroma is a popular vector store that can be used to store\
- \ and retrieve embeddings. It will build its index in memory and persist\
- \ it to disk by the end of the sync."
- required:
- - "processing"
- - "embedding"
- - "indexing"
- groups:
- - id: "processing"
- title: "Processing"
- - id: "embedding"
- title: "Embedding"
- - id: "indexing"
- title: "Indexing"
destination-yellowbrick:
title: "Yellowbrick Destination Spec"
type: "object"
@@ -57305,6 +57254,8 @@ components:
$ref: "#/components/schemas/source-chargebee"
- title: source-chartmogul
$ref: "#/components/schemas/source-chartmogul"
+ - title: source-clazar
+ $ref: "#/components/schemas/source-clazar"
- title: source-clickhouse
$ref: "#/components/schemas/source-clickhouse"
- title: source-clickup-api
@@ -57325,6 +57276,8 @@ components:
$ref: "#/components/schemas/source-confluence"
- title: source-convex
$ref: "#/components/schemas/source-convex"
+ - title: source-datadog
+ $ref: "#/components/schemas/source-datadog"
- title: source-datascope
$ref: "#/components/schemas/source-datascope"
- title: source-delighted
@@ -57375,12 +57328,12 @@ components:
$ref: "#/components/schemas/source-glassfrog"
- title: source-gnews
$ref: "#/components/schemas/source-gnews"
+ - title: source-goldcast
+ $ref: "#/components/schemas/source-goldcast"
- title: source-google-ads
$ref: "#/components/schemas/source-google-ads"
- title: source-google-analytics-data-api
$ref: "#/components/schemas/source-google-analytics-data-api"
- - title: source-google-analytics-v4-service-account-only
- $ref: "#/components/schemas/source-google-analytics-v4-service-account-only"
- title: source-google-directory
$ref: "#/components/schemas/source-google-directory"
- title: source-google-drive
@@ -57519,8 +57472,6 @@ components:
$ref: "#/components/schemas/source-postmarkapp"
- title: source-prestashop
$ref: "#/components/schemas/source-prestashop"
- - title: source-punk-api
- $ref: "#/components/schemas/source-punk-api"
- title: source-pypi
$ref: "#/components/schemas/source-pypi"
- title: source-qualaroo
@@ -57685,8 +57636,6 @@ components:
$ref: "#/components/schemas/destination-firestore"
- title: destination-gcs
$ref: "#/components/schemas/destination-gcs"
- - title: destination-langchain
- $ref: "#/components/schemas/destination-langchain"
- title: destination-milvus
$ref: "#/components/schemas/destination-milvus"
- title: destination-mongodb
@@ -57833,7 +57782,7 @@ components:
type: oauth2
flows:
clientCredentials:
- tokenUrl: /api/v1/applications/token
+ tokenUrl: /applications/token
scopes: {}
security:
- bearerAuth: []