ai.embed

Operation: ai.embed
Category: ai
Tags: embedding, vector

Generate vector embeddings from text using an AI provider

Runtime

Type: AI Provider (routed via provider registry)
Timeout: 300s
Retries: 3 (ExponentialWithJitter)

Inputs

Name	Type	Required	Default	Description
text	String	Yes	—	Text to embed

Outputs

Name	Type	Description
embedding	JSON	Embedding vector
model	String	Model used for embedding

Usage

TypeScript

import { WorkflowBuilder } from "@fabric-platform/sdk";

const workflow = new WorkflowBuilder("my-workflow")
  .node("ai-embed", "ai_invoke", (n) =>
    n.config({
      operation: "ai.embed",
      // ... node-specific config
    })
  )
  .build();

Python

from fabric_platform import FabricClient

fabric = FabricClient(api_key="fab_xxx")

wf_id = fabric.upsert_workflow("my-workflow", nodes=[
    {
        "key": "ai-embed",
        "kind": "ai_invoke",
    },
])

Rust

use fabric_sdk::FabricClient;

let client = FabricClient::new("http://localhost:3001", api_key)?;

let wf_id = client.upsert_workflow("my-workflow", serde_json::json!({
    "nodes": [{
        "key": "ai-embed",
        "kind": "ai_invoke"
    }]
})).await?;

curl

curl -X POST http://localhost:3001/v1/workflow-definitions \
  -H "Authorization: Bearer $FABRIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-workflow",
    "nodes": [{
      "key": "ai-embed",
      "kind": "ai_invoke"
    }]
  }'

Example

{
  "key": "embed-text",
  "operation": "ai.embed",
  "config": { "model": "text-embedding-3-large" },
  "inputs": [{ "name": "text", "path": "$context.document_text" }],
  "outputs": [{ "name": "embedding", "path": "$context.vector" }]
}

Common Errors

ai.embed requires input text

Cause: The text input is empty or not bound

Fix: Bind the text input to an upstream node output that produces a non-empty string