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
  • Path parameters
  • Body parameters
  • ComparisonFilter
  • CompoundFilter
  • RankingOptions
  • Response
  • VectorStoreSearchResultItem
  • VectorStoreSearchResultContentObject
  1. API references
  2. OpenAI-compatible APIs
  3. Vector stores
  4. searchVectorStore

REST: Search vector store

Written by
Yandex Cloud
Updated at December 30, 2025
  • HTTP request
  • Path parameters
  • Body parameters
  • ComparisonFilter
  • CompoundFilter
  • RankingOptions
  • Response
  • VectorStoreSearchResultItem
  • VectorStoreSearchResultContentObject

Search a vector store for relevant chunks based on a query and file attributes filter.

HTTP requestHTTP request

POST https://ai.api.cloud.yandex.net/v1/vector_stores/{vector_store_id}/search

Path parametersPath parameters

Field

Description

vector_store_id

string

Required field. The ID of the vector store to search.

Body parametersBody parameters

Request schema: application/json

{
  "query": "unknown",
  "rewrite_query": "boolean",
  "max_num_results": "integer",
  "filters": "unknown",
  "ranking_options": {
    "ranker": "string",
    "score_threshold": "number"
  }
}

Field

Description

query

Any of string | string

rewrite_query

boolean

Whether to rewrite the natural language query for vector search.

max_num_results

integer

The maximum number of results to return. This number should be between 1 and 50 inclusive.

filters

Any of ComparisonFilter | CompoundFilter

ranking_options

RankingOptions

Ranking options for search.

ComparisonFilterComparisonFilter

A filter used to compare a specified attribute key to a given value using a defined comparison operation.

Field

Description

type

enum

Required field. Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.

  • eq: equals

  • ne: not equal

  • gt: greater than

  • gte: greater than or equal

  • lt: less than

  • lte: less than or equal

  • in: in

  • nin: not in

  • eq

  • ne

  • gt

  • gte

  • lt

  • lte

key

string

Required field. The key to compare against the value.

value

Any of string | number | boolean | unknown

CompoundFilterCompoundFilter

Combine multiple filters using and or or.

Field

Description

type

enum

Required field. Type of operation: and or or.

  • and
  • or

filters[]

unknown

Required field.

RankingOptionsRankingOptions

Ranking options for search.

Field

Description

ranker

enum

Enable re-ranking; set to none to disable, which can help reduce latency.

  • none
  • auto
  • default-2024-11-15

score_threshold

number

ResponseResponse

HTTP Code: 200

OK

Response schema: application/json

{
  "object": "string",
  "search_query": [
    "string"
  ],
  "data": [
    {
      "file_id": "string",
      "filename": "string",
      "score": "number",
      "attributes": "unknown",
      "content": [
        {
          "type": "string",
          "text": "string"
        }
      ]
    }
  ],
  "has_more": "boolean",
  "next_page": "unknown"
}

Field

Description

object

enum

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

  • vector_store.search_results.page

search_query[]

string

Required field. The query used for this search.

data[]

VectorStoreSearchResultItem

Required field.

has_more

boolean

Required field. Indicates if there are more results to fetch.

next_page

Any of string | null

VectorStoreSearchResultItemVectorStoreSearchResultItem

Field

Description

file_id

string

Required field. The ID of the vector store file.

filename

string

Required field. The name of the vector store file.

score

number

Required field. The similarity score for the result.

attributes

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

content[]

VectorStoreSearchResultContentObject

Required field.

VectorStoreSearchResultContentObjectVectorStoreSearchResultContentObject

Field

Description

type

enum

Required field. The type of content.

  • text

text

string

Required field. The text content returned from search.

Was the article helpful?

Previous
retrieveVectorStoreFileContent
Next
Overview
© 2026 Direct Cursus Technology L.L.C.