API Reference

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Vector Stores

List Vector Stores

GET/v5/vector-stores

Create Vector Store

POST/v5/vector-stores/create

Get Vector Store

GET/v5/vector-stores/{vector_store_name}

Configure Vector Store

POST/v5/vector-stores/{vector_store_name}/configure

Drop Vector Store

POST/v5/vector-stores/{vector_store_name}/drop

Upsert Vectors

POST/v5/vector-stores/{vector_store_name}/upsert

Delete Vectors

POST/v5/vector-stores/{vector_store_name}/delete

Count Vectors

POST/v5/vector-stores/{vector_store_name}/count

Query Vectors

POST/v5/vector-stores/{vector_store_name}/query

ModelsExpand Collapse

EmbeddingConfig = EmbeddingConfigModelsAPI { model_deployment_id, type } or EmbeddingConfigBase { embedding_model, type }

One of the following:

EmbeddingConfigModelsAPI object { model_deployment_id, type }

model_deployment_id: string

The ID of the deployment of the created model in the Models API V3.

type: "models_api"

The type of the embedding configuration.

EmbeddingConfigBase object { embedding_model, type }

embedding_model: EmbeddingModelName or string

The name of the base embedding model to use. Either a known base model (EmbeddingModelName) or, in ray-serve deployments with NATIVE_OPENAI_EMBEDDING_GATEWAY enabled, any model id served by the OpenAI-compatible inference proxy (e.g. ‘nomic-embed-text-v1.5’). For fully custom deployments, use type ‘models_api’ with a model_deployment_id.

One of the following:

EmbeddingModelName = "sentence-transformers/all-MiniLM-L12-v2" or "sentence-transformers/multi-qa-distilbert-cos-v1" or "openai/text-embedding-ada-002" or 8 more

One of the following:

"sentence-transformers/all-MiniLM-L12-v2"

"sentence-transformers/multi-qa-distilbert-cos-v1"

"openai/text-embedding-ada-002"

"openai/text-embedding-3-small"

"openai/text-embedding-3-large"

"embed-english-v3.0"

"embed-english-light-v3.0"

"embed-multilingual-v3.0"

"gemini/text-embedding-005"

"gemini/text-multilingual-embedding-002"

"gemini/gemini-embedding-001"

string

type: optional "base"

The type of the embedding configuration.

EmbeddingConfigBase object { embedding_model, type }

embedding_model: EmbeddingModelName or string

The name of the base embedding model to use. Either a known base model (EmbeddingModelName) or, in ray-serve deployments with NATIVE_OPENAI_EMBEDDING_GATEWAY enabled, any model id served by the OpenAI-compatible inference proxy (e.g. ‘nomic-embed-text-v1.5’). For fully custom deployments, use type ‘models_api’ with a model_deployment_id.

One of the following:

EmbeddingModelName = "sentence-transformers/all-MiniLM-L12-v2" or "sentence-transformers/multi-qa-distilbert-cos-v1" or "openai/text-embedding-ada-002" or 8 more

One of the following:

"sentence-transformers/all-MiniLM-L12-v2"

"sentence-transformers/multi-qa-distilbert-cos-v1"

"openai/text-embedding-ada-002"

"openai/text-embedding-3-small"

"openai/text-embedding-3-large"

"embed-english-v3.0"

"embed-english-light-v3.0"

"embed-multilingual-v3.0"

"gemini/text-embedding-005"

"gemini/text-multilingual-embedding-002"

"gemini/gemini-embedding-001"

string

type: optional "base"

The type of the embedding configuration.

EmbeddingConfigModelsAPI object { model_deployment_id, type }

model_deployment_id: string

The ID of the deployment of the created model in the Models API V3.

type: "models_api"

The type of the embedding configuration.

EmbeddingModelName = "sentence-transformers/all-MiniLM-L12-v2" or "sentence-transformers/multi-qa-distilbert-cos-v1" or "openai/text-embedding-ada-002" or 8 more

One of the following:

"sentence-transformers/all-MiniLM-L12-v2"

"sentence-transformers/multi-qa-distilbert-cos-v1"

"openai/text-embedding-ada-002"

"openai/text-embedding-3-small"

"openai/text-embedding-3-large"

"embed-english-v3.0"

"embed-english-light-v3.0"

"embed-multilingual-v3.0"

"gemini/text-embedding-005"

"gemini/text-multilingual-embedding-002"

"gemini/gemini-embedding-001"

TextContent object { text, type }

Text content for documents.

text: string

Text content to be embedded

type: optional "text"

Content type identifier

VectorStore object { id, created_at, embedding_dimensions, 4 more }

Response model for vector store operations.

id: string

The unique identifier of the vector store

created_at: string

Timestamp of creation

formatdate-time

embedding_dimensions: number

Dimensionality of the embedding vectors

name: string

The name of the vector store

updated_at: string

Timestamp of last update

formatdate-time

embedding_config: optional EmbeddingConfig

Embedding configuration identifying the model and its type. None for raw-embedding-only stores.

One of the following:

EmbeddingConfigModelsAPI object { model_deployment_id, type }

model_deployment_id: string

The ID of the deployment of the created model in the Models API V3.

type: "models_api"

The type of the embedding configuration.

EmbeddingConfigBase object { embedding_model, type }

embedding_model: EmbeddingModelName or string

The name of the base embedding model to use. Either a known base model (EmbeddingModelName) or, in ray-serve deployments with NATIVE_OPENAI_EMBEDDING_GATEWAY enabled, any model id served by the OpenAI-compatible inference proxy (e.g. ‘nomic-embed-text-v1.5’). For fully custom deployments, use type ‘models_api’ with a model_deployment_id.

One of the following:

EmbeddingModelName = "sentence-transformers/all-MiniLM-L12-v2" or "sentence-transformers/multi-qa-distilbert-cos-v1" or "openai/text-embedding-ada-002" or 8 more

One of the following:

"sentence-transformers/all-MiniLM-L12-v2"

"sentence-transformers/multi-qa-distilbert-cos-v1"

"openai/text-embedding-ada-002"

"openai/text-embedding-3-small"

"openai/text-embedding-3-large"

"embed-english-v3.0"

"embed-english-light-v3.0"

"embed-multilingual-v3.0"

"gemini/text-embedding-005"

"gemini/text-multilingual-embedding-002"

"gemini/gemini-embedding-001"

string

type: optional "base"

The type of the embedding configuration.

indexed_metadata_fields: optional map["string" or "number" or "boolean"]

Dictionary mapping metadata field names to their types

One of the following:

"string"

"number"

"boolean"

VectorStoreDropResponse object { name }

Response for vector store deletion.

name: string

The name of the deleted vector store

VectorStoreUpsertResponse object { failure_count, success_count, failed, succeeded }

Response for batch insert/upsert operations.

failure_count: number

Number of failed documents

success_count: number

Number of successfully processed documents

failed: optional array of object { id, error }

Failed documents with their error messages

id: string

Document ID

error: string

Error message describing why the document failed

succeeded: optional array of string

IDs of successfully processed documents

VectorStoreDeleteResponse object { deleted_count }

Response for delete operation.

deleted_count: number

Number of documents deleted

VectorStoreCountResponse object { count }

Response for count operation.

count: number

Number of documents matching the criteria

VectorStoreQueryResponse object { metadata, vectors }

Response for query operation.

metadata: object { search_type, total_query_time_ms, embedding_config, 4 more }

Query execution metadata

search_type: string

Type of search performed (semantic, lexical, hybrid)

total_query_time_ms: number

Total end-to-end query execution time in milliseconds

embedding_config: optional EmbeddingConfig

Embedding configuration used for query vectorization. None for lexical queries on model-less stores.

One of the following:

EmbeddingConfigModelsAPI object { model_deployment_id, type }

model_deployment_id: string

The ID of the deployment of the created model in the Models API V3.

type: "models_api"

The type of the embedding configuration.

EmbeddingConfigBase object { embedding_model, type }

embedding_model: EmbeddingModelName or string

The name of the base embedding model to use. Either a known base model (EmbeddingModelName) or, in ray-serve deployments with NATIVE_OPENAI_EMBEDDING_GATEWAY enabled, any model id served by the OpenAI-compatible inference proxy (e.g. ‘nomic-embed-text-v1.5’). For fully custom deployments, use type ‘models_api’ with a model_deployment_id.

One of the following:

EmbeddingModelName = "sentence-transformers/all-MiniLM-L12-v2" or "sentence-transformers/multi-qa-distilbert-cos-v1" or "openai/text-embedding-ada-002" or 8 more

One of the following:

"sentence-transformers/all-MiniLM-L12-v2"

"sentence-transformers/multi-qa-distilbert-cos-v1"

"openai/text-embedding-ada-002"

"openai/text-embedding-3-small"

"openai/text-embedding-3-large"

"embed-english-v3.0"

"embed-english-light-v3.0"

"embed-multilingual-v3.0"

"gemini/text-embedding-005"

"gemini/text-multilingual-embedding-002"

"gemini/gemini-embedding-001"

string

type: optional "base"

The type of the embedding configuration.

embedding_time_ms: optional number

Time spent generating embeddings in milliseconds (None for lexical queries)

index_query_time_ms: optional number

Time spent querying the vector index (OpenSearch) in milliseconds

reranking_model: optional string

Reranking model used (None if reranking not enabled)

reranking_time_ms: optional number

Time spent reranking results in milliseconds (None if reranking not enabled)

vectors: array of object { id, score, content, 2 more }

Array of matching documents

id: string

Document ID

score: number

Similarity score indicating relevance

content: optional TextContent { text, type }

Text content for documents.

text: string

Text content to be embedded

type: optional "text"

Content type identifier

metadata: optional map[unknown]

Key-value metadata

vector: optional array of number

Embedding vector (if requested)

Vector StoresVectors

List Vectors

GET/v5/vector-stores/{vector_store_name}/vectors

Get Vector

GET/v5/vector-stores/{vector_store_name}/vectors/{vector_id}

ModelsExpand Collapse

VectorDocument object { id, content, metadata, vector }

A document returned from direct lookups (get/list operations).

id: string

Document ID

content: optional TextContent { text, type }

Text content for documents.

text: string

Text content to be embedded

type: optional "text"

Content type identifier

metadata: optional map[unknown]

Key-value metadata

vector: optional array of number

Embedding vector (if requested)