Deepset Search Session API
The search_session API from Deepset — 2 operation(s) for search_session.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
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.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/deepset:deepset-search-session-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API 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 Specification
openapi: 3.2.0
info:
description: deepset API description
title: Haystack Enterprise Platform Search Session API
version: 1.0.0
servers:
- description: deepset Europe
url: https://api.cloud.deepset.ai
- description: deepset US
url: https://api.us.deepset.ai
tags:
- name: search_session
paths:
/api/v1/workspaces/{workspace_name}/search_sessions:
get:
description: Returns all search sessions. Search sessions are used in chat as chat history.
operationId: get_search_sessions_api_v1_workspaces__workspace_name__search_sessions_get
parameters:
- description: Type the name of the workspace.
in: path
name: workspace_name
required: true
schema:
description: Type the name of the workspace.
title: Workspace Name
type: string
- description: The number of entries to display. Leaving this field empty keeps the default, and max 10 results are returned.
in: query
name: limit
required: false
schema:
default: 10
description: The number of entries to display. Leaving this field empty keeps the default, and max 10 results are returned.
maximum: 100
title: Limit
type: integer
- description: Enter an ID if you want to see all entries before this ID. To use this option, clear the `page_number` parameter first.
in: query
name: before
required: false
schema:
anyOf:
- format: uuid
type: string
- type: 'null'
description: Enter an ID if you want to see all entries before this ID. To use this option, clear the `page_number` parameter first.
title: Before
- description: Enter an ID if you want to see all entries after this ID. To use this option, clear the `page_number` parameter first.
in: query
name: after
required: false
schema:
anyOf:
- format: uuid
type: string
- type: 'null'
description: Enter an ID if you want to see all entries after this ID. To use this option, clear the `page_number` parameter first.
title: After
- description: The number of the page you want to see.
in: query
name: page_number
required: false
schema:
anyOf:
- minimum: 1
type: integer
- type: 'null'
description: The number of the page you want to see.
title: Page Number
- description: 'The OData filter you want to use to in your query. It supports exact match and `AND` operations. For example, to filter for a metadata `category:news` and `published_date` greater than or equal to January 1 2025, here''s what the URL could look like: ''url = "https://api.cloud.deepset.ai/api/v1/workspaces/production/files?limit=10&filter=category eq ''news'' and published_date ge ''2025-01-01'' "''. OData filters only work with cursor-based pagination (leave the `page_number` field blank to enable it).To learn more about the OData filter syntax, see: [Querying Data](https://www.odata.org/getting-started/basic-tutorial/#queryData).'
in: query
name: filter
required: false
schema:
anyOf:
- type: string
- type: 'null'
description: 'The OData filter you want to use to in your query. It supports exact match and `AND` operations. For example, to filter for a metadata `category:news` and `published_date` greater than or equal to January 1 2025, here''s what the URL could look like: ''url = "https://api.cloud.deepset.ai/api/v1/workspaces/production/files?limit=10&filter=category eq ''news'' and published_date ge ''2025-01-01'' "''. OData filters only work with cursor-based pagination (leave the `page_number` field blank to enable it).To learn more about the OData filter syntax, see: [Querying Data](https://www.odata.org/getting-started/basic-tutorial/#queryData).'
title: Filter
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/PaginatedSearchSessions'
description: Successful Response
'422':
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
description: Validation Error
security:
- HTTPBearer: []
summary: Get Search Sessions
tags:
- search_session
x-deepset-permissions:
action: read
asset: search_history
asset_description: Access to search history
type: workspace
post:
description: Creates a search session you can later use in chat as chat history.
operationId: create_search_session_api_v1_workspaces__workspace_name__search_sessions_post
parameters:
- description: Type the name of the workspace.
in: path
name: workspace_name
required: true
schema:
description: Type the name of the workspace.
title: Workspace Name
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/SearchSessionPostBody'
required: true
responses:
'201':
content:
application/json:
schema:
$ref: '#/components/schemas/SearchSessionPostResponse'
description: Successful Response
'422':
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
description: Validation Error
security:
- HTTPBearer: []
summary: Create Search Session
tags:
- search_session
x-deepset-permissions:
action: read
asset: pipelines
asset_description: Access to individual pipeline details
type: workspace
/api/v1/workspaces/{workspace_name}/search_sessions/{search_session_id}:
delete:
description: Delete a search session together with its search history.
operationId: delete_search_session_api_v1_workspaces__workspace_name__search_sessions__search_session_id__delete
parameters:
- description: The ID of the search session you want to delete.
in: path
name: search_session_id
required: true
schema:
description: The ID of the search session you want to delete.
format: uuid
title: Search Session Id
type: string
- description: Type the name of the workspace.
in: path
name: workspace_name
required: true
schema:
description: Type the name of the workspace.
title: Workspace Name
type: string
responses:
'204':
description: We are processing your request to delete search session data.
'404':
description: Returned if search session id to be deleted is not found.
'422':
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
description: Validation Error
security:
- HTTPBearer: []
summary: Delete Search Session
tags:
- search_session
x-deepset-permissions:
action: write
asset: pipelines
asset_description: Access to individual pipeline details
type: workspace
components:
schemas:
SearchSessionPostBody:
properties:
pipeline_id:
description: Unique identifier of a pipeline.
format: uuid
title: Pipeline ID
type: string
required:
- pipeline_id
title: SearchSessionPostBody
type: object
ValidationError:
properties:
ctx:
title: Context
type: object
input:
title: Input
loc:
items:
anyOf:
- type: string
- type: integer
title: Location
type: array
msg:
title: Message
type: string
type:
title: Error Type
type: string
required:
- loc
- msg
- type
title: ValidationError
type: object
SearchSessionGetResponse:
properties:
deployment_id:
anyOf:
- format: uuid
type: string
- type: 'null'
description: The ID of the deployment this search session belongs to. Set instead of the pipeline ID for sessions created against a deployment.
title: Deployment ID
pipeline_id:
anyOf:
- format: uuid
type: string
- type: 'null'
description: Unique identifier of a pipeline.
title: Pipeline ID
search_history:
anyOf:
- $ref: '#/components/schemas/SearchSessionSearchHistoryEntry'
- type: 'null'
description: Query request.
title: Query Request
search_session_id:
description: The ID of the search session you want to use for chat.
format: uuid
title: Search Session ID
type: string
title:
anyOf:
- type: string
- type: 'null'
title: Title of the search session
required:
- search_session_id
title: SearchSessionGetResponse
type: object
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
title: Detail
type: array
title: HTTPValidationError
type: object
PaginatedSearchSessions:
properties:
has_more:
description: Indicates if there are more results to show.
title: Has more results
type: boolean
search_sessions:
description: A list of all search sessions with their details.
items:
$ref: '#/components/schemas/SearchSessionGetResponse'
title: Search Sessions
type: array
total:
description: The total number of results matching your query.
title: Total number of results
type: integer
required:
- search_sessions
- has_more
- total
title: PaginatedSearchSessions
type: object
SearchSessionSearchHistoryEntry:
properties:
created_at:
description: Specifies when the search query was run.
title: Created At
type: string
query:
description: The search query.
title: Query
type: string
search_history_id:
description: Unique identifier of the search.
format: uuid
title: Search history ID
type: string
required:
- search_history_id
- query
- created_at
title: SearchSessionSearchHistoryEntry
type: object
SearchSessionPostResponse:
properties:
search_session_id:
description: The ID of the search session you want to use for chat.
format: uuid
title: Search Session ID
type: string
required:
- search_session_id
title: SearchSessionPostResponse
type: object
securitySchemes:
HTTPBearer:
scheme: bearer
type: http