> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/integrations/catalog/voyage-ai.md).

# Voyage AI

Create text, multimodal, and contextualized embeddings, rerank documents, and run batch inference.

## Connectors

Choose the connector that matches your authentication method. The options below use the names shown in StackAI.

| Connector | Authentication |
| --------- | -------------- |
| Voyage AI | API Key        |

### Voyage AI

Connect to Voyage AI for embeddings, reranking, and batch inference.

#### Set up in Voyage AI

1. Prepare the Voyage AI account or service that the workflow will access. Grant access to the required resources and operations.
2. **API Key:** Create a secret key in the Voyage AI dashboard, then paste it here.

#### Set up in StackAI

1. Open **Settings → Connections**, add a connection, and select **Voyage AI**.
2. Enter the credentials and connection details in the fields below.
3. Save the connection and check its connection status. Select this saved connection when configuring an action or feature that uses it.

**Connection fields**

| StackAI field | Required | What to enter                                                                                                                    |
| ------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------- |
| API Key       | Yes      | Create a secret key in the Voyage AI dashboard, then paste it here. [Provider instructions](https://dash.voyageai.com/api-keys). |

### Verify the connection

Check that the connection is healthy. Then run a read operation against a resource the connected account can access. A successful connection check confirms authentication; it does not guarantee permission for every action.

If access is denied, check the credential or OAuth permissions, the selected account or environment, and access to the specific resource. Update expired credentials or reconnect after permissions change.

## Use an action

1. Add the required **Voyage AI** action to the workflow.
2. Select a connection when the action requests one.
3. Complete the required fields. Use the reference picker when a value comes from another workflow step.
4. Run the workflow and inspect the action’s output. Check the result before using it in a later step.

## Actions

### Create Text Embeddings

Convert text into Voyage AI vector embeddings.

#### Inputs

| Field                | Type            | Required | Description                                                                                                                                  |
| -------------------- | --------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
| Texts                | array           | Yes      | Texts to convert into vector embeddings.                                                                                                     |
| Model                | string          | No       | Voyage text embedding model to use. Default: voyage-4-large.                                                                                 |
| Input Type           | select (string) | No       | Whether these texts are documents or search queries. Available values: Document, Query. Default: document.                                   |
| Truncate Long Inputs | boolean         | No       | Trim inputs that exceed the model context limit. Default: true.                                                                              |
| Output Dimension     | integer         | No       | Optional vector dimension supported by the selected model.                                                                                   |
| Output Data Type     | select (string) | No       | Numeric representation used for each vector. Available values: Float, Signed 8-bit, Unsigned 8-bit, Binary, Unsigned binary. Default: float. |

#### Outputs

| Field        | Type    | Description                                   |
| ------------ | ------- | --------------------------------------------- |
| Embeddings   | array   | Vectors in the same order as the input texts. |
| Model        | string  | Model that generated the vectors.             |
| Total Tokens | integer | Tokens processed by Voyage AI.                |
| Dimensions   | integer | Number of values in each vector.              |

### Rerank Documents

Order documents by relevance to a query.

#### Inputs

| Field                | Type    | Required | Description                                                     |
| -------------------- | ------- | -------- | --------------------------------------------------------------- |
| Query                | string  | Yes      | Search query used to score relevance.                           |
| Documents            | array   | Yes      | Documents to order by relevance.                                |
| Model                | string  | No       | Voyage reranking model to use. Default: rerank-2.5.             |
| Maximum Results      | integer | No       | Maximum number of ranked documents to return.                   |
| Truncate Long Inputs | boolean | No       | Trim inputs that exceed the model context limit. Default: true. |

#### Outputs

| Field            | Type          | Description                                    |
| ---------------- | ------------- | ---------------------------------------------- |
| Ranked Documents | object\_array | Documents ordered from most to least relevant. |
| Model            | string        | Model used to rank the documents.              |
| Total Tokens     | integer       | Tokens processed by Voyage AI.                 |

### Create Multimodal Embeddings

Embed interleaved text, images, and videos.

#### Inputs

| Field                | Type            | Required | Description                                                                                                 |
| -------------------- | --------------- | -------- | ----------------------------------------------------------------------------------------------------------- |
| Multimodal Inputs    | object\_array   | Yes      | Groups of interleaved text, image, or video content to embed.                                               |
| Model                | string          | No       | Voyage multimodal embedding model to use. Default: voyage-multimodal-3.5.                                   |
| Input Type           | select (string) | No       | Whether these inputs are documents or search queries. Available values: Document, Query. Default: document. |
| Truncate Long Inputs | boolean         | No       | Trim inputs that exceed the model context limit. Default: true.                                             |

#### Outputs

| Field        | Type    | Description                                       |
| ------------ | ------- | ------------------------------------------------- |
| Embeddings   | array   | Vectors aligned with the multimodal input groups. |
| Model        | string  | Model that generated the vectors.                 |
| Total Tokens | integer | Tokens processed by Voyage AI.                    |

### Create Contextualized Chunk Embeddings

Embed chunks using context from their full document.

#### Inputs

| Field                 | Type            | Required | Description                                                                                                                                  |
| --------------------- | --------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
| Document Chunk Groups | array           | Yes      | Ordered chunk groups, one inner list per document.                                                                                           |
| Model                 | string          | No       | Voyage contextualized embedding model to use. Default: voyage-context-4.                                                                     |
| Input Type            | select (string) | No       | Whether the groups contain document chunks or individual queries. Available values: Document, Query. Default: document.                      |
| Output Dimension      | integer         | No       | Optional vector dimension supported by the model.                                                                                            |
| Output Data Type      | select (string) | No       | Numeric representation used for each vector. Available values: Float, Signed 8-bit, Unsigned 8-bit, Binary, Unsigned binary. Default: float. |

#### Outputs

| Field                     | Type          | Description                                           |
| ------------------------- | ------------- | ----------------------------------------------------- |
| Contextualized Embeddings | object\_array | Chunk vectors grouped and ordered by source document. |
| Model                     | string        | Model that generated the vectors.                     |
| Total Tokens              | integer       | Tokens processed by Voyage AI.                        |

### Create Batch Embedding Job

Start a batch inference job from a JSONL file previously uploaded through Voyage's Files API.

#### Inputs

| Field                     | Type            | Required | Description                                                                                                                                         |
| ------------------------- | --------------- | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------- |
| Input File ID             | string          | Yes      | Voyage JSONL file ID created through the external Files upload API.                                                                                 |
| Batch Endpoint            | select (string) | No       | Voyage operation used for every request in the file. Available values: Text Embeddings, Contextualized Embeddings, Rerank. Default: /v1/embeddings. |
| Shared Request Parameters | object          | Yes      | Parameters applied to every request in the batch.                                                                                                   |
| Metadata                  | object          | No       | Optional labels stored with the batch job.                                                                                                          |

#### Outputs

| Field          | Type   | Description                                  |
| -------------- | ------ | -------------------------------------------- |
| Batch ID       | string | Voyage identifier for the new batch.         |
| Status         | string | Initial processing state of the batch.       |
| Endpoint       | string | Operation used by the batch.                 |
| Input File ID  | string | Source JSONL file used by the batch.         |
| Output File ID | string | Result file ID when processing finishes.     |
| Error File ID  | string | Failed-request file ID when available.       |
| Request Counts | object | Total, completed, and failed request counts. |

## Important behavior

Actions that create, update, send, or delete data can change the connected service. Review their inputs before running them. A retry can repeat an operation; consider this when configuring retries for actions that change data.

The catalog lists the fields and capabilities available in the supplied provider definition. Availability can also depend on your deployment and organization’s Feature Access settings.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/integrations/catalog/voyage-ai.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
