Voyage AI

Voyage AI is a platform that offers high-performance embedding and reranking APIs for AI applications. The Voyage AI connector enables you to generate vector embeddings for text, rerank documents based on relevance to queries, and build AI-powered search and recommendation systems. This connector is particularly useful for applications that need to convert text to embeddings, implement semantic search, build recommendation engines, or improve search relevance through reranking.

Power end-to-end data operations for your Voyage AI API with Nexla. Our bi-directional Voyage AI connector is purpose-built for Voyage AI, making it simple to ingest data, sync it across systems, and deliver it anywhere — all with no coding required. Nexla turns API-sourced data into ready-to-use, reusable data products and makes it easy to send data to Voyage AI or any other destination. With comprehensive monitoring, lineage tracking, and access controls, Nexla keeps your Voyage AI workflows fast, secure, and fully governed.

Features

Type: API

SourceDestination

• Seamless API Integration: Connect to any endpoint as source or destination without coding, with automatic data product creation
• Visual Composition & Chaining: Build complex integrations using visual templates, chain API calls, and compose workflows with data validation and filtering
• API Proxy: Expose curated slices of your data securely with a secure and customizable API proxy that validates and transforms data on the fly
• Request optimization with intelligent batching, retry, and caching to minimize API calls and costs

Prerequisites

Before creating a Voyage AI credential, you'll need to obtain an API key from your Voyage AI account. Voyage AI provides API keys for programmatic access to their embedding and reranking services through the Voyage AI dashboard.

To obtain a Voyage AI API key:

1. Log in to your Voyage AI account at https://www.voyageai.com or navigate to the Voyage AI dashboard.

2. Navigate to your account settings or API dashboard. This is typically accessible from the user menu or dashboard navigation.

3. In the API settings or API Keys section, locate the option to create or manage API keys.

4. Click Create API Key or Generate New Key to create a new API key for your application. You may need to provide a name or description for the API key.

5. Copy the API key immediately after generation, as it may only be displayed once for security purposes. Store it securely, as you'll need it to authenticate API requests.

6. Note your Base URL and API Version. The base URL is typically https://api.voyageai.com and the API version is typically v1. These values may vary depending on your Voyage AI deployment.

Voyage AI API keys are used as Bearer tokens in the Authorization header for all API requests. The API key is sensitive information and should be kept secure. If you've lost your API key, you'll need to generate a new one in your Voyage AI account settings.

For detailed information about Voyage AI API authentication and API key management, refer to the Voyage AI Documentation.

Authenticate

Credentials required

Authentication using a Voyage AI API key via Bearer Token.

Field	Required	Secret	Description
Voyage AI API Key	Yes	Yes	Your secret API key for authenticating with Voyage AI.
Base URL	Yes	No	The base URL for the Voyage AI API.
API Version	Yes	No	Parameter for defining the API version for Voyage API requests
API Version	Yes	No	Embeddings payload to test a connection

Create a credential in Nexla

1. To create a new Voyage AI credential, after selecting the data source/destination type, click the Add Credential tile to open the Add New Credential overlay.

New Credential Overlay – Voyage AI

2. Enter a name for the credential in the Credential Name field and a short, meaningful description in the Credential Description field.

3. In the Voyage AI API Key field, enter the API key that you obtained from your Voyage AI account. This is the secret API key used to authenticate requests to the Voyage AI API.

4. In the Base URL field, enter the base URL for the Voyage AI API. The default value is https://api.voyageai.com, which is the standard base URL for Voyage AI API services.

5. In the API Version field, enter the API version for Voyage AI API requests. The default value is v1.

6. In the API Version field (labeled as "Embeddings payload to test a connection"), enter a sample JSON payload to test the connection. A default payload is provided:

   {
     "input": [
       "Sample text 1",
       "Sample text 2"
     ],
     "model": "voyage-3.5"
   }

   The API key is sensitive information and should be kept secure. If you've lost your API key, you'll need to generate a new one in your Voyage AI account settings. API keys are used as Bearer tokens in the Authorization header for all API requests.

7. Once all of the relevant steps above have been completed, click the Save button at the bottom of the overlay to save the configured credential.

8. The newly added credential will now appear in a tile on the Authenticate screen during data source/destination creation and can be selected for use with a new data source or destination.

Use as a data source

To create a new data flow, navigate to the Integrate section, and click the New Data Flow button. Select the Voyage AI connector tile, then select the credential that will be used to connect to the Voyage AI API, and click Next; or, create a new Voyage AI credential for use in this flow.

Endpoint templates

Nexla provides pre-built templates that can be used to rapidly configure data sources to ingest data from common Voyage AI API endpoints. Select the endpoint from which this source will fetch data from the Endpoint pulldown menu. Available endpoint templates are listed in the expandable boxes below.

Generate Embeddings

This endpoint generates vector embeddings for input text(s) using Voyage AI. Use this endpoint when you need to convert text to embeddings, create vector representations of text, or prepare text for semantic search.

• Enter the input text in the Input field. This is the text you want to convert to embeddings. You can provide a single text string or multiple texts.
• Enter the model name in the Model field. Common models include voyage-3.5, voyage-large-2, or other available Voyage AI models. The default is typically voyage-3.5.

The Generate Embeddings endpoint uses POST requests to send text to the Voyage AI API and returns vector embeddings. The endpoint supports batch processing, allowing you to generate embeddings for multiple texts in a single request. For more information about the Generate Embeddings endpoint, refer to the Voyage AI Embeddings Documentation.

Rerank Documents

This endpoint reranks a list of documents based on relevance to a query using Voyage AI. Use this endpoint when you need to improve search relevance, reorder search results, or find the most relevant documents for a query.

• Enter the query text in the Query field. This is the search query you want to use for reranking documents.
• Enter the documents array in JSON format in the Documents field. This should be an array of document strings to be reranked.
• Enter the model name in the Model field. Common models include rerank-1 or other available Voyage AI reranking models.

The Rerank Documents endpoint uses POST requests to send a query and documents to the Voyage AI API and returns reranked documents with relevance scores. The endpoint helps improve search relevance by reordering documents based on their relevance to the query. For more information about the Rerank Documents endpoint, refer to the Voyage AI Reranker Documentation.

Once the selected endpoint template has been configured, click the Test button to the right of the endpoint selection menu to retrieve a sample of the data that will be fetched. Sample data will be displayed in the Endpoint Test Result panel on the right, allowing you to verify that the source is configured correctly before saving.

Manual configuration

Voyage AI data sources can also be manually configured to ingest data from any valid Voyage AI API endpoint, including endpoints not covered by the pre-built templates, chained API calls, or custom request parameters. Voyage AI API endpoints typically follow the pattern {base_url}/{api_version}/{endpoint}, where {base_url} is typically https://api.voyageai.com and {api_version} is typically v1 — common endpoints include /{api_version}/embeddings for generating embeddings and /{api_version}/rerank for reranking documents. Select the Advanced tab at the top of the configuration screen, and follow the instructions in Connect to Any API to configure the API method, endpoint URL, date/time and lookup macros, path to data, metadata, and request headers.

For Voyage AI API responses, common paths to data include $.data[*] for arrays of embeddings or reranked documents. You do not need to include the Authorization header, as the Bearer token is automatically included from your credential; Content-Type is typically set to application/json.

Once all of the relevant settings have been configured, click the Create button in the upper right corner of the screen to save and create the new Voyage AI data source. Nexla will now begin ingesting data from the configured endpoint and will organize any data that it finds into one or more Nexsets.