Embed
cohere.embed
ActionAI & modelsconnection required
Calls the Cohere API POST /v2/embed.
Generate embedding vectors for text with Cohere (feed into a vector store).
Connection
- Required
- Yes — the node will not save without one
- Auth type
- API key
- Providers
- Cohere
- Secret shape
- the Cohere API key
- Resolved by
- config.connection_id, else node.connection_id
Configuration
3 fields, 1 required. A dotted path is a nested object and name[] an array of objects — the editor renders the same tree.
| Field | Type | Required | Default | Constraints | Example |
|---|---|---|---|---|---|
texts Text(s) to embed (string or JSON array). Supports {{ }}. | array | Yes | — | array of string | — |
model Embed model; blank leaves it out of the call. | string | No | embed-english-v3.0 | — | — |
input_type Embedding purpose. | string | No | search_document | one of "search_document", "search_query", "classification", "clustering" | — |
Example configuration
Every value below is the contract’s own example or default — nothing invented.
{
"input_type": "search_document",
"model": "embed-english-v3.0"
}Output
One shape.
result
| Field | Type | Example |
|---|---|---|
embeddings | array | — |
count | number | — |
{
"count": 0,
"embeddings": []
}Related Cohere nodes
See Embed run in a workflow.
In a technical demo we add the Cohere connection, drop the node on the canvas and let Workflow Health pre-flight it before the first real run.