text-embeddings

For the complete MongoDB documentation index, see www.mongodb.com/docs/llms.txt

<!-- Tab options on this page. Append to the .md URL to filter: ?tabs=<id,...> select specific tabs (e.g. ?tabs=nodejs,shell) ?allTabs=true include every tab (no param) default: one tab per tabset

Available tabs: other tabs: single-string, list-strings -->

Text Embeddings

Voyage AI's text embedding models convert your text into high-dimensional vectors that capture semantic meaning. The models are inherently multilingual, meaning semantic similarity of texts is irrespective of language. Use the following models to power your AI search applications with state-of-the-art retrieval accuracy.

Available Models

Voyage AI provides the following text embedding models:

General Purpose Models

Domain-Specific Models

Open Models

Older Models

The following older models are still accessible from our API, but we recommend using the new models above for better quality and efficiency.

Our latest models perform better than the legacy models in all aspects, such as quality, context length, latency, and throughput.

Tutorials

For tutorials on using text embeddings, see the following resources:

• [Quick Start](https://www.mongodb.com/docs/voyageai/quickstart.md#std-label-voyage-quickstart

• [Semantic Search with Voyage AI Embeddings](https://www.mongodb.com/docs/voyageai/tutorials/semantic-search.md#std-label-voyage-semantic-search

• [Retrieval-Augmented Generation (RAG) with Voyage AI](https://www.mongodb.com/docs/voyageai/tutorials/rag.md#std-label-voyage-rag

Usage

You can access Voyage text embeddings in Python through the voyageai package. Install the voyageai package, set up the API key, and use the voyageai.Client.embed() function to vectorize your inputs.

voyageai.Client.embed(
    texts: List[str],
    model: str,
    input_type: Optional[str] = None,
    truncation: Optional[bool] = None,
    output_dimension: Optional[int] = None,
    output_dtype: Optional[str] = "float"
)

Parameters

View the parameters for the embed method.

Response

View the response for the embed method.

This method returns an EmbeddingsObject, which contains the following attributes:

Example

import voyageai

vo = voyageai.Client()
## This will automatically use the environment variable VOYAGE_API_KEY.
## Alternatively, you can use vo = voyageai.Client(api_key="<model-api-key>")

texts = [
    "The Mediterranean diet emphasizes fish, olive oil, and vegetables, believed to reduce chronic diseases.",
    "Photosynthesis in plants converts light energy into glucose and produces essential oxygen.",
    "20th-century innovations, from radios to smartphones, centered on electronic advancements.",
    "Rivers provide water, irrigation, and habitat for aquatic species, vital for ecosystems.",
    "Apple's conference call to discuss fourth fiscal quarter results and business updates is scheduled for Thursday, November 2, 2023 at 2:00 p.m. PT / 5:00 p.m. ET.",
    "Shakespeare's works, like 'Hamlet' and 'A Midsummer Night's Dream,' endure in literature."
]

## Embed the documents
result = vo.embed(texts, model="voyage-4-large", input_type="document")
print(result.embeddings)

You can access Voyage text embeddings in JavaScript or TypeScript through HTTP requests using the Fetch API or other HTTP clients.

Example

const apiKey = process.env.VOYAGE_API_KEY;
const url = "https://ai.mongodb.com/v1/embeddings";

const headers = {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json"
};

const data = {
    input: [
        "The Mediterranean diet emphasizes fish, olive oil, and vegetables, believed to reduce chronic diseases.",
        "Photosynthesis in plants converts light energy into glucose and produces essential oxygen.",
        "20th-century innovations, from radios to smartphones, centered on electronic advancements.",
        "Rivers provide water, irrigation, and habitat for aquatic species, vital for ecosystems.",
        "Apple's conference call to discuss fourth fiscal quarter results and business updates is scheduled for Thursday, November 2, 2023 at 2:00 p.m. PT / 5:00 p.m. ET.",
        "Shakespeare's works, like 'Hamlet' and 'A Midsummer Night's Dream,' endure in literature."
    ],
    model: "voyage-4-large",
    input_type: "document"
};

const response = await fetch(url, {
    method: "POST",
    headers: headers,
    body: JSON.stringify(data)
});

const result = await response.json();

You can access Voyage text embeddings in Java by sending HTTP requests using the built-in HttpClient or other HTTP libraries.

Example

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

String apiKey = System.getenv("VOYAGE_API_KEY");
String url = "https://ai.mongodb.com/v1/embeddings";

String jsonBody = """
    {
        "input": [
            "The Mediterranean diet emphasizes fish, olive oil, and vegetables, believed to reduce chronic diseases.",
            "Photosynthesis in plants converts light energy into glucose and produces essential oxygen.",
            "20th-century innovations, from radios to smartphones, centered on electronic advancements.",
            "Rivers provide water, irrigation, and habitat for aquatic species, vital for ecosystems.",
            "Apple's conference call to discuss fourth fiscal quarter results and business updates is scheduled for Thursday, November 2, 2023 at 2:00 p.m. PT / 5:00 p.m. ET.",
            "Shakespeare's works, like 'Hamlet' and 'A Midsummer Night's Dream,' endure in literature."
        ],
        "model": "voyage-4-large",
        "input_type": "document"
    }
    """;

HttpClient client = HttpClient.newHttpClient();
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create(url))
    .header("Authorization", "Bearer " + apiKey)
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(jsonBody))
    .build();

HttpResponse<String> response = client.send(request,
    HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

You can access Voyage text embeddings in Go by sending HTTP requests using the standard net/http package.

Example

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io"
    "net/http"
    "os"
)

func main() {
    apiKey := os.Getenv("VOYAGE_API_KEY")
    url := "https://ai.mongodb.com/v1/embeddings"

    texts := []string{
        "The Mediterranean diet emphasizes fish, olive oil, and vegetables, believed to reduce chronic diseases.",
        "Photosynthesis in plants converts light energy into glucose and produces essential oxygen.",
        "20th-century innovations, from radios to smartphones, centered on electronic advancements.",
        "Rivers provide water, irrigation, and habitat for aquatic species, vital for ecosystems.",
        "Apple's conference call to discuss fourth fiscal quarter results and business updates is scheduled for Thursday, November 2, 2023 at 2:00 p.m. PT / 5:00 p.m. ET.",
        "Shakespeare's works, like 'Hamlet' and 'A Midsummer Night's Dream,' endure in literature.",
    }

    requestBody := map[string]interface{}{
        "input":      texts,
        "model":      "voyage-4-large",
        "input_type": "document",
    }

    jsonData, _ := json.Marshal(requestBody)

    req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
    req.Header.Set("Authorization", "Bearer "+apiKey)
    req.Header.Set("Content-Type", "application/json")

    client := &http.Client{}
    resp, _ := client.Do(req)
    defer resp.Body.Close()

    body, _ := io.ReadAll(resp.Body)
    fmt.Println(string(body))
}

You can access Voyage text embeddings with cURL by sending a POST request to the endpoint https://ai.mongodb.com/v1/embeddings.

Example

Embed a single string

curl \
  --request POST 'https://ai.mongodb.com/v1/embeddings' \
  --header "Authorization: Bearer $VOYAGE_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "input": "Sample text",
    "model": "voyage-4-large",
    "input_type": "document"
  }'