> ## Documentation Index
> Fetch the complete documentation index at: https://docs.unstructured.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Embedder node

> Configure an Embedder node to convert chunked document elements into vector embeddings using a supported provider and model, enabling similarity search in vector stores.

*Type*: `embed`

*Subtype*: see [Settings](#settings)

<Warning>
  If you add an embedder node, you must set the workflow's chunker node's `max_characters` setting to a value at or below Unstructured's recommended
  maximum chunk size for your specified embedding model. [Learn more](/concepts/embedding#chunk-sizing-and-embedding-models).
</Warning>

[Learn about the available embedding providers and models](/concepts/embedding).

## Settings

<ParamField body="subtype" type="string" required>
  Embedding provider. Set at the `WorkflowNode` level, outside of `settings`. Allowed values: `azure_openai`, `bedrock`, `ibm`, `togetherai`, `voyageai`.

  <Note>
    The following list applies only to Unstructured **Let's Go** and **Pay-As-You-Go** accounts.

    For Unstructured **Business** accounts, to get your current list of available models, contact your
    Unstructured account administrator or Unstructured sales representative, or email Unstructured Support at
    [support@unstructured.io](mailto:support@unstructured.io).
  </Note>
</ParamField>

<ParamField body="model_name" type="string" required>
  Embedding model to use. For a full list of the models available in Unstructured, see [Available models](/api-reference/workflow/models).
</ParamField>

<RequestExample>
  ```python Python SDK theme={null}
  embedder_workflow_node = WorkflowNode(
      name="Embedder",
      subtype="<subtype>",
      type="embed",
      settings={
          "model_name": "<model-name>"
      }
  )
  ```

  ```json cURL theme={null}
  {
      "name": "Embedder",
      "type": "embed",
      "subtype": "<subtype>",
      "settings": {
          "model_name": "<model-name>"
      }
  }
  ```
</RequestExample>