types: EmbedRequestInput: discriminated: false docs: > A single text string, or a list of texts as a list of strings. Currently, we have two constraints on the list:

The maximum length of the list is 128.
The total number of tokens in the list is at most 320K for `voyage-2`, and 120K for `voyage-large-2`, `voyage-finance-2`, `voyage-multilingual-2`, `voyage-law-2`, and `voyage-code-2`.

source: openapi: openapi/openapi.yml inline: true EmbedRequestInputType: enum: - query - document docs: > Type of the input text. Defaults to `null`. Other options: `query`, `document`. inline: true source: openapi: openapi/openapi.yml EmbedRequestOutputDtype: enum: - float - int8 - uint8 - binary - ubinary docs: > The data type for the embeddings to be returned. Defaults to `float`. Other options: `int8`, `uint8`, `binary`, `ubinary`. `float` is supported for all models. `int8`, `uint8`, `binary`, and `ubinary` are supported by `voyage-3-large` and `voyage-code-3`. Please see our guide for more details about output data types. inline: true source: openapi: openapi/openapi.yml EmbedResponseDataItem: properties: object: type: optional docs: The object type, which is always "embedding". embedding: type: optional> docs: > Each embedding is a vector represented as an array of `float` numbers when `output_dtype` is set to `float` and as an array of integers for all other values of `output_dtype` (`int8`, `uint8`, `binary`, and `ubinary`). The length of this vector varies depending on the specific model, `output_dimension`, and `output_dtype`. index: type: optional docs: > An integer representing the index of the embedding within the list of embeddings. source: openapi: openapi/openapi.yml inline: true EmbedResponseUsage: properties: total_tokens: type: optional docs: The total number of tokens used for computing the embeddings. source: openapi: openapi/openapi.yml inline: true EmbedResponse: properties: object: type: optional docs: The object type, which is always "list". data: type: optional> docs: An array of embedding objects. model: type: optional docs: Name of the model. usage: optional source: openapi: openapi/openapi.yml RerankResponseDataItem: properties: index: type: optional docs: The index of the document in the input list. relevance_score: type: optional docs: The relevance score of the document with respect to the query. document: type: optional docs: > The document string. Only returned when return_documents is set to true. source: openapi: openapi/openapi.yml inline: true RerankResponseUsage: properties: total_tokens: type: optional docs: The total number of tokens used for computing the reranking. source: openapi: openapi/openapi.yml inline: true RerankResponse: properties: object: type: optional docs: The object type, which is always "list". data: type: optional> docs: > An array of the reranking results, sorted by the descending order of relevance scores. model: type: optional docs: Name of the model. usage: optional source: openapi: openapi/openapi.yml MultimodalEmbedRequestInputsItemContentItem: properties: type: type: string docs: > Specifies the type of the piece of the content. Allowed values are `text`, `image_url`, or `image_base64`. text: type: optional docs: Only present when type is `text`. The value should be a text string. image_base64: type: optional docs: > Only present when type is `image_base64`. The value should be a Base64-encoded image in the data URL format `data:[];base64,`. Currently supported mediatypes are: `image/png`, `image/jpeg`, `image/webp`, and `image/gif`. image_url: type: optional docs: > Only present when `type` is `image_url`. The value should be a URL linking to the image. We support PNG, JPEG, WEBP, and GIF images. source: openapi: openapi/openapi.yml inline: true MultimodalEmbedRequestInputsItem: properties: content: optional> source: openapi: openapi/openapi.yml inline: true MultimodalEmbedRequestInputType: enum: - query - document docs: > Type of the input text. Defaults to `null`. Other options: `query`, `document`.

When input_type is null, the embedding model directly converts your input data into numerical vectors. For retrieval/search purposes—where an input (called a "query") is used to search for relevant pieces of information (referred to as "documents")—we recommend specifying whether your inputs are intended as queries or documents by setting input_type to query or document, respectively. In these cases, Voyage prepends a prompt to your input before vectorizing it, helping the model create more effective vectors tailored for retrieval/search tasks. Since inputs can be multimodal, queries and documents can be text, images, or an interleaving of both modalities. Embeddings generated with and without the input_type argument are compatible.
For transparency, the following prompts are prepended to your input.

For query, the prompt is "Represent the query for retrieving supporting documents: ".
For document, the prompt is "Represent the query for retrieving supporting documents: ".

inline: true source: openapi: openapi/openapi.yml MultimodalEmbedResponseDataItem: properties: object: type: optional docs: The object type, which is always "embedding". embedding: type: optional> docs: > The embedding vector consists of a list of floating-point numbers. The length of this vector varies depending on the specific model. index: type: optional docs: > An integer representing the index of the embedding within the list of embeddings. source: openapi: openapi/openapi.yml inline: true MultimodalEmbedResponseUsage: properties: total_tokens: type: optional docs: The total number of tokens used for computing the embeddings. source: openapi: openapi/openapi.yml inline: true MultimodalEmbedResponse: properties: object: type: optional docs: The object type, which is always "list". data: type: optional> docs: An array of embedding objects. model: type: optional docs: Name of the model. usage: optional source: openapi: openapi/openapi.yml service: auth: false base-path: '' endpoints: embed: path: /embeddings method: POST auth: true docs: >- Voyage embedding endpoint receives as input a string (or a list of strings) and other arguments such as the preferred model name, and returns a response containing a list of embeddings. source: openapi: openapi/openapi.yml display-name: Embeddings request: name: EmbedRequest body: properties: input: type: EmbedRequestInput docs: > A single text string, or a list of texts as a list of strings. Currently, we have two constraints on the list:

The maximum length of the list is 128.
The total number of tokens in the list is at most 320K for `voyage-2`, and 120K for `voyage-large-2`, `voyage-finance-2`, `voyage-multilingual-2`, `voyage-law-2`, and `voyage-code-2`.

docs: > Type of the input text. Defaults to `null`. Other options: `query`, `document`. truncation: type: optional docs: > Whether to truncate the input texts to fit within the context length. Defaults to `true`.

If `true`, over-length input texts will be truncated to fit within the context length, before vectorized by the embedding model.
If `false`, an error will be raised if any given text exceeds the context length.

encoding_format: type: optional> docs: > Format in which the embeddings are encoded. We support two options:

If not specified (defaults to `null`): the embeddings are represented as lists of floating-point numbers;
`base64`: the embeddings are compressed to [base64](https://docs.python.org/3/library/base64.html) encodings.

output_dimension: type: optional docs: > The number of dimensions for resulting output embeddings. Defaults to `null`. output_dtype: type: optional docs: > The data type for the embeddings to be returned. Defaults to `float`. Other options: `int8`, `uint8`, `binary`, `ubinary`. `float` is supported for all models. `int8`, `uint8`, `binary`, and `ubinary` are supported by `voyage-3-large` and `voyage-code-3`. Please see our guide for more details about output data types. content-type: application/json response: docs: Success type: EmbedResponse status-code: 200 examples: - name: Success request: input: input model: model response: body: object: object data: - object: object embedding: - 1.1 index: 1 model: model usage: total_tokens: 1 code-samples: - language: shell code: |- curl --request POST \ --url https://api.voyageai.com/v1/embeddings \ --header "Authorization: Bearer $VOYAGE_API_KEY" \ --header "content-type: application/json" \ --data ' { "input": [ "Sample text 1", "Sample text 2" ], "model": "voyage-large-2" } ' rerank: path: /rerank method: POST auth: true docs: > Voyage reranker endpoint receives as input a query, a list of documents, and other arguments such as the model name, and returns a response containing the reranking results. source: openapi: openapi/openapi.yml display-name: Reranker request: name: RerankRequest body: properties: query: type: string docs: > The query as a string. The query can contain a maximum of 1000 tokens for `rerank-lite-1` and 2000 tokens for `rerank-1`. documents: docs: > The documents to be reranked as a list of strings.

The number of documents cannot exceed 1000.
The sum of the number of tokens in the query and the number of tokens in any single document cannot exceed 4000 for `rerank-lite-1` and 8000 for `rerank-1`.
he total number of tokens, defined as "the number of query tokens × the number of documents + sum of the number of tokens in all documents", cannot exceed 300K for `rerank-lite-1` and 100K for `rerank-1`. Please see our FAQ.

type: list model: type: string docs: > Name of the model. Recommended options: `rerank-lite-1`, `rerank-1`. top_k: type: optional docs: > The number of most relevant documents to return. If not specified, the reranking results of all documents will be returned. return_documents: type: optional docs: > Whether to return the documents in the response. Defaults to `false`.

If `false`, the API will return a list of {"index", "relevance_score"} where "index" refers to the index of a document within the input list.
If `true`, the API will return a list of {"index", "document", "relevance_score"} where "document" is the corresponding document from the input list.

truncation: type: optional docs: > Whether to truncate the input to satisfy the "context length limit" on the query and the documents. Defaults to `true`.

If `true`, the query and documents will be truncated to fit within the context length limit, before processed by the reranker model.
If `false`, an error will be raised when the query exceeds 1000 tokens for `rerank-lite-1` and 2000 tokens for `rerank-1`, or the sum of the number of tokens in the query and the number of tokens in any single document exceeds 4000 for `rerank-lite-1` and 8000 for `rerank-1`.

content-type: application/json response: docs: Success type: RerankResponse status-code: 200 examples: - name: Success request: query: query documents: - documents model: model response: body: object: object data: - index: 1 relevance_score: 1.1 document: document model: model usage: total_tokens: 1 code-samples: - language: shell code: |- curl --request POST \ --url https://api.voyageai.com/v1/rerank \ --header "Authorization: Bearer $VOYAGE_API_KEY" \ --header "content-type: application/json" \ --data ' { "query": "Sample query", "documents": [ "Sample document 1", "Sample document 2" ], "model": "rerank-lite-1" } ' multimodal-embed: path: /multimodalembeddings method: POST auth: true docs: >- The Voyage multimodal embedding endpoint returns vector representations for a given list of multimodal inputs consisting of text, images, or an interleaving of both modalities. source: openapi: openapi/openapi.yml display-name: Multimodal embeddings request: name: MultimodalEmbedRequest body: properties: inputs: docs: > A list of multimodal inputs to be vectorized. A single input in the list is a dictionary containing a single key "content", whose value represents a sequence of text and images.

The value of "content" is a list of dictionaries, each representing a single piece of text or image. The dictionaries have four possible keys:
1. type: Specifies the type of the piece of the content. Allowed values are text, image_url, or image_base64.
2. text: Only present when type is text. The value should be a text string.
3. image_base64: Only present when type is image_base64. The value should be a Base64-encoded image in the data URL format data:[<mediatype>];base64,<data>. Currently supported mediatypes are: image/png, image/jpeg, image/webp, and image/gif.
4. image_url: Only present when type is image_url. The value should be a URL linking to the image. We support PNG, JPEG, WEBP, and GIF images.

Note: Only one of the keys, image_base64 or image_url, should be present in each dictionary for image data. Consistency is required within a request, meaning each request should use either image_base64 or image_url exclusively for images, not both.

Example payload where inputs contains an image as a URL

The inputs list contains a single input, which consists of a piece of text and an image (which is provided via a URL).


                      {
                        "inputs": [
                          {   
                            "content": [
                              {   
                                "type": "text",
                                "text": "This is a banana."
                              },  
                              {   
                                "type": "image_url",
                                "image_url": "https://raw.githubusercontent.com/voyage-ai/voyage-multimodal-3/refs/heads/main/images/banana.jpg"
                              }   
                            ]   
                          }   
                        ],  
                        "model": "voyage-multimodal-3"
                      }

Example payload where inputs contains a Base64 image

Below is an equivalent example to the one above where the image content is a Base64 image instead of a URL. (Base64 images can be lengthy, so the example only shows a shortened version.)

  
                      {
                        "inputs": [
                          {   
                            "content": [
                              {   
                                "type": "text",
                                "text": "This is a banana."
                              },  
                              {   
                                "type": "image_base64",
                                "image_base64": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAA..."
                              }   
                            ]   
                          }   
                        ],  
                        "model": "voyage-multimodal-3"
                      }

type: list model: type: string docs: > Name of the model. Currently, the only supported model is `voyage-multimodal-3`. input_type: type: optional docs: > Type of the input text. Defaults to `null`. Other options: `query`, `document`.

When input_type is null, the embedding model directly converts your input data into numerical vectors. For retrieval/search purposes—where an input (called a "query") is used to search for relevant pieces of information (referred to as "documents")—we recommend specifying whether your inputs are intended as queries or documents by setting input_type to query or document, respectively. In these cases, Voyage prepends a prompt to your input before vectorizing it, helping the model create more effective vectors tailored for retrieval/search tasks. Since inputs can be multimodal, queries and documents can be text, images, or an interleaving of both modalities. Embeddings generated with and without the input_type argument are compatible.
For transparency, the following prompts are prepended to your input.

For query, the prompt is "Represent the query for retrieving supporting documents: ".
For document, the prompt is "Represent the query for retrieving supporting documents: ".

truncation: type: optional docs: > Whether to truncate the input texts to fit within the context length. Defaults to `true`.

If `true`, over-length input texts will be truncated to fit within the context length, before vectorized by the embedding model.
If `false`, an error will be raised if any given text exceeds the context length.

encoding_format: type: optional> docs: > Format in which the embeddings are encoded. We support two options:

If not specified (defaults to `null`): the embeddings are represented as lists of floating-point numbers;
`base64`: the embeddings are compressed to [base64](https://docs.python.org/3/library/base64.html) encodings.

content-type: application/json response: docs: Success type: MultimodalEmbedResponse status-code: 200 examples: - name: Success request: inputs: - {} model: model response: body: object: object data: - object: object embedding: - 1.1 index: 1 model: model usage: total_tokens: 1 code-samples: - language: shell code: |- curl -X POST https://api.voyageai.com/v1/multimodalembeddings \ -H "Authorization: Bearer $VOYAGE_API_KEY" \ -H "content-type: application/json" \ -d ' { "inputs": [ { "content": [ { "type": "text", "text": "This is a banana." }, { "type": "image_url", "image_url": "https://raw.githubusercontent.com/voyage-ai/voyage-multimodal-3/refs/heads/main/images/banana.jpg" } ] } ], "model": "voyage-multimodal-3" }' source: openapi: openapi/openapi.yml