Create Embeddings
mistral.embeddings
ActionAI & modelsconnection required
Calls the Mistral AI API with the connection's credentials.
Turn one string or a list of strings into embedding vectors with a Mistral embedding model such as mistral-embed.
Connection
- Required
- Yes — the node will not save without one
- Auth type
- API key
- Providers
- Mistral AI
- Secret shape
- {"api_key": "…"} — a Mistral API key
- Config it needs
- base_url, default_model
- Resolved by
- config.connection_id, else node.connection_id
Configuration
2 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 |
|---|---|---|---|---|---|
input The text to embed. A JSON array of strings, or an expression that evaluates to a list, embeds the whole batch in one call. | string | Yes | — | — | The quick brown fox. |
model Embedding model; defaults to mistral-embed when left blank. | string | No | mistral-embed | — | — |
Example configuration
Every value below is the contract’s own example or default — nothing invented.
{
"input": "The quick brown fox.",
"model": "mistral-embed"
}Output
One shape.
result
| Field | Type | Example |
|---|---|---|
embeddings One vector of floats per input, in input order. | array | — |
count How many vectors were returned. | number | — |
dimensions Length of each vector. | number | — |
model The embedding model that ran. | string | — |
total_tokens Tokens billed for the batch. | number | — |
{
"count": 0,
"dimensions": 0,
"embeddings": [],
"model": "",
"total_tokens": 0
}See Create Embeddings run in a workflow.
In a technical demo we add the Mistral AI connection, drop the node on the canvas and let Workflow Health pre-flight it before the first real run.