API Reference

Vector Stores

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Search vector store

vector_stores.search(vector_store_id, **kwargs) -> Page<VectorStoreSearchResponse { attributes, content, file_id, 2 more } >

POST/vector_stores/{vector_store_id}/search

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

ParametersExpand Collapse

vector_store_id: String

query: String | Array[String]

A query string for a search

Accepts one of the following:

String

Array[String]

filters: ComparisonFilter { key, type, value } | CompoundFilter { filters, type }

A filter to apply based on file attributes.

Accepts one of the following:

class ComparisonFilter { key, type, value }

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

key: String

The key to compare against the value.

type: :eq | :ne | :gt | 3 more

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

Accepts one of the following:

:eq

:ne

:gt

:gte

:lt

:lte

value: String | Float | bool | Array[String | Float]

The value to compare against the attribute key; supports string, number, or boolean types.

Accepts one of the following:

String

Float

bool

Array[String | Float]

Accepts one of the following:

String

Float

class CompoundFilter { filters, type }

Combine multiple filters using and or or.

filters: Array[ComparisonFilter { key, type, value } | untyped]

Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.

Accepts one of the following:

class ComparisonFilter { key, type, value }

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

key: String

The key to compare against the value.

type: :eq | :ne | :gt | 3 more

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

Accepts one of the following:

:eq

:ne

:gt

:gte

:lt

:lte

value: String | Float | bool | Array[String | Float]

The value to compare against the attribute key; supports string, number, or boolean types.

Accepts one of the following:

String

Float

bool

Array[String | Float]

Accepts one of the following:

String

Float

untyped

type: :and | :or

Type of operation: and or or.

Accepts one of the following:

:and

:or

max_num_results: Integer

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

minimum1

maximum50

ranking_options: { ranker, score_threshold}

Ranking options for search.

ranker: :none | :auto | :"default-2024-11-15"

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

Accepts one of the following:

:none

:auto

:"default-2024-11-15"

score_threshold: Float

minimum0

maximum1

rewrite_query: bool

Whether to rewrite the natural language query for vector search.

ReturnsExpand Collapse

class VectorStoreSearchResponse { attributes, content, file_id, 2 more }

attributes: Hash[Symbol, String | Float | bool]

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.

Accepts one of the following:

String

Float

bool

content: Array[{ text, type}]

Content chunks from the file.

text: String

The text content returned from search.

type: :text

The type of content.

file_id: String

The ID of the vector store file.

filename: String

The name of the vector store file.

score: Float

The similarity score for the result.

minimum0

maximum1

Search vector store

Ruby

HTTP

TypeScript

Python

Java

Go

Ruby

require "openai"

openai = OpenAI::Client.new(api_key: "My API Key")

page = openai.vector_stores.search("vs_abc123", query: "string")

puts(page)

200 example

{
  "data": [
    {
      "attributes": {
        "foo": "string"
      },
      "content": [
        {
          "text": "text",
          "type": "text"
        }
      ],
      "file_id": "file_id",
      "filename": "filename",
      "score": 0
    }
  ],
  "has_more": true,
  "next_page": "next_page",
  "object": "vector_store.search_results.page",
  "search_query": [
    "string"
  ]
}

Returns Examples

200 example

{
  "data": [
    {
      "attributes": {
        "foo": "string"
      },
      "content": [
        {
          "text": "text",
          "type": "text"
        }
      ],
      "file_id": "file_id",
      "filename": "filename",
      "score": 0
    }
  ],
  "has_more": true,
  "next_page": "next_page",
  "object": "vector_store.search_results.page",
  "search_query": [
    "string"
  ]
}