Embedder node - Unstructured

embedder_workflow_node = WorkflowNode(
    name="Embedder",
    subtype="<subtype>",
    type="embed",
    settings={
        "model_name": "<model-name>"
    }
)

{
    "name": "Embedder",
    "type": "embed",
    "subtype": "<subtype>",
    "settings": {
        "model_name": "<model-name>"
    }
}

Type: embed Subtype: see Settings

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.

Learn about the available embedding providers and models.

Settings

subtype

string

required

Embedding provider. Set at the WorkflowNode level, outside of settings. Allowed values: azure_openai, bedrock, ibm, togetherai, voyageai.

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 request support.

model_name

string

required

Embedding model to use. For a full list of the models available in Unstructured, see Available models.

embedder_workflow_node = WorkflowNode(
    name="Embedder",
    subtype="<subtype>",
    type="embed",
    settings={
        "model_name": "<model-name>"
    }
)

{
    "name": "Embedder",
    "type": "embed",
    "subtype": "<subtype>",
    "settings": {
        "model_name": "<model-name>"
    }
}

Chunk by Table Merging LLM extraction

​Settings

Settings