Yandex Cloud
Search
Contact UsTry it for free
  • Customer Stories
  • Documentation
  • Blog
  • All Services
  • System Status
  • Marketplace
    • Featured
    • Infrastructure & Network
    • Data Platform
    • AI for business
    • Security
    • DevOps tools
    • Serverless
    • Monitoring & Resources
  • All Solutions
    • By industry
    • By use case
    • Economics and Pricing
    • Security
    • Technical Support
    • Start testing with double trial credits
    • Cloud credits to scale your IT product
    • Gateway to Russia
    • Cloud for Startups
    • Center for Technologies and Society
    • Yandex Cloud Partner program
    • Price calculator
    • Pricing plans
  • Customer Stories
  • Documentation
  • Blog
© 2026 Direct Cursus Technology L.L.C.
Yandex AI Studio
  • About Yandex AI Studio
  • Getting started with Model Gallery
  • Yandex Workflows
  • Switching from the AI Assistant API to Responses API
  • Compatibility with OpenAI
    • Overview
    • API authentication
        • Overview
        • listVectorStores
        • createVectorStore
        • getVectorStore
        • modifyVectorStore
        • deleteVectorStore
        • createVectorStoreFileBatch
        • getVectorStoreFileBatch
        • listFilesInVectorStoreBatch
        • listVectorStoreFiles
        • createVectorStoreFile
        • getVectorStoreFile
        • deleteVectorStoreFile
        • updateVectorStoreFileAttributes
        • retrieveVectorStoreFileContent
        • searchVectorStore
  • Quotas and limits
  • Pricing policy
  • Access management
  • Audit Trails events
  • Public materials
  • Release notes
  • Terms and definitions

In this article:

  • HTTP request
  • Body parameters
  • VectorStoreExpirationAfter
  • AutoChunkingStrategyRequestParam
  • StaticChunkingStrategyRequestParam
  • StaticChunkingStrategy
  • Response
  • FileCounts
  • VectorStoreExpirationAfter
  1. API references
  2. OpenAI-compatible APIs
  3. Vector stores
  4. createVectorStore

REST: Create vector store

Written by
Yandex Cloud
Updated at December 30, 2025
  • HTTP request
  • Body parameters
  • VectorStoreExpirationAfter
  • AutoChunkingStrategyRequestParam
  • StaticChunkingStrategyRequestParam
  • StaticChunkingStrategy
  • Response
  • FileCounts
  • VectorStoreExpirationAfter

Create a vector store.

HTTP requestHTTP request

POST https://ai.api.cloud.yandex.net/v1/vector_stores

Body parametersBody parameters

Request schema: application/json

{
  "file_ids": [
    "string"
  ],
  "name": "string",
  "description": "string",
  "expires_after": {
    "anchor": "string",
    "days": "integer"
  },
  "chunking_strategy": {
    "<anyOf>": [
      {
        "description": "string",
        "name": "string",
        "parameters": "object"
      },
      {
        "type": "string",
        "static": {
          "max_chunk_size_tokens": "integer",
          "chunk_overlap_tokens": "integer"
        }
      }
    ]
  },
  "metadata": "unknown"
}

Field

Description

file_ids[]

string

name

string

The name of the vector store.

description

string

A description for the vector store. Can be used to describe the vector store's purpose.

expires_after

VectorStoreExpirationAfter

Required field. The expiration policy for a vector store.

chunking_strategy

Any of AutoChunkingStrategyRequestParam | StaticChunkingStrategyRequestParam

metadata

Any of object (map<string, string>) | null

VectorStoreExpirationAfterVectorStoreExpirationAfter

The expiration policy for a vector store.

Field

Description

anchor

enum

Required field. Anchor timestamp after which the expiration policy applies.
Supported anchors: last_active_at.''

  • last_active_at

days

integer

Required field. The number of days after the anchor time that the vector store will expire.

AutoChunkingStrategyRequestParamAutoChunkingStrategyRequestParam

Schema reference for server-to-client Realtime events. Servers emit JSON messages where the type field selects the event schema.

Field

Description

description

string

A description of what the function does, used by the model to choose when and how to call the function.

name

string

Required field. The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

parameters

object

The parameters the functions accepts, described as a JSON Schema object.

StaticChunkingStrategyRequestParamStaticChunkingStrategyRequestParam

Customize your own chunking strategy by setting chunk size and chunk overlap.

Field

Description

type

enum

Required field. Always static.

  • static

static

StaticChunkingStrategy

Required field.

StaticChunkingStrategyStaticChunkingStrategy

Field

Description

max_chunk_size_tokens

integer

Required field. The maximum number of tokens in each chunk. The default value is 800. The minimum value is 100 and the maximum value is 4096.

chunk_overlap_tokens

integer

Required field. The number of tokens that overlap between chunks. The default value is 400. Note that the overlap must not exceed half of max_chunk_size_tokens.

ResponseResponse

HTTP Code: 200

OK

Response schema: application/json

{
  "id": "string",
  "object": "string",
  "created_at": "integer",
  "name": "string",
  "usage_bytes": "integer",
  "file_counts": {
    "in_progress": "integer",
    "completed": "integer",
    "failed": "integer",
    "cancelled": "integer",
    "total": "integer"
  },
  "status": "string",
  "expires_after": {
    "anchor": "string",
    "days": "integer"
  },
  "expires_at": "unknown",
  "last_active_at": "unknown",
  "metadata": "unknown"
}

A vector store is a collection of processed files can be used by the file_search tool.

Field

Description

id

string

Required field. The identifier, which can be referenced in API endpoints.

object

enum

Required field. The object type, which is always vector_store.

  • vector_store

created_at

integer

Required field. The Unix timestamp (in seconds) for when the vector store was created.

name

string

Required field. The name of the vector store.

usage_bytes

integer

Required field. The total number of bytes used by the files in the vector store.

file_counts

FileCounts

Required field.

status

enum

Required field. The status of the vector store, which can be either expired, in_progress, or completed. A status of completed indicates that the vector store is ready for use.

  • expired
  • in_progress
  • completed

expires_after

VectorStoreExpirationAfter

Required field. The expiration policy for a vector store.

expires_at

Any of integer | null

last_active_at

Any of integer | null

metadata

Any of object (map<string, string>) | null

FileCountsFileCounts

Field

Description

in_progress

integer

Required field. The number of files that are currently being processed.

completed

integer

Required field. The number of files that have been successfully processed.

failed

integer

Required field. The number of files that have failed to process.

cancelled

integer

Required field. The number of files that were cancelled.

total

integer

Required field. The total number of files.

VectorStoreExpirationAfterVectorStoreExpirationAfter

The expiration policy for a vector store.

Field

Description

anchor

enum

Required field. Anchor timestamp after which the expiration policy applies.
Supported anchors: last_active_at.''

  • last_active_at

days

integer

Required field. The number of days after the anchor time that the vector store will expire.

Was the article helpful?

Previous
listVectorStores
Next
getVectorStore
© 2026 Direct Cursus Technology L.L.C.