Nodes

Workflow Nodes

Available node types for building workflows.

---

Overview

Workflow nodes are the building blocks of automation:

Category	Purpose
Control	Start, end, flow control
AI	Text, image, audio, document AI
Integration	API calls, external systems
Logic	Conditions, loops, branching
Human	Human-in-the-loop tasks

---

Control Nodes

Start Node

Entry point for workflow execution:

Start Node:
  trigger: api | schedule | event | manual
  input_schema:
    type: object
    properties:
      document: { type: string }
  validation:
    - required: document

End Node

Complete workflow and return output:

End Node:
  output_schema:
    type: object
    properties:
      result: { type: string }
      status: { type: string }
  output_mapping:
    result: "{{ai_node.output}}"
    status: "completed"

---

AI Nodes

Text-to-Text

Generate, transform, or analyze text:

Text-to-Text Node:
  model: gpt-4
  prompt: |
    Summarize the following text in 3 bullet points:

    {{input.text}}
  temperature: 0.7
  max_tokens: 500
  output_variable: summary

Use cases:

• Text summarization
• Content generation
• Translation
• Classification
• Entity extraction

Text-to-Image

Generate images from text prompts:

Text-to-Image Node:
  model: dall-e-3
  prompt: "{{input.image_description}}"
  size: 1024x1024
  quality: standard
  output_variable: generated_image

Use cases:

• Marketing visuals
• Product mockups
• Creative content

Image-to-Text

Extract text or descriptions from images:

Image-to-Text Node:
  model: gpt-4-vision
  image: "{{input.image_url}}"
  prompt: |
    Describe the contents of this image in detail.
    Extract any visible text.
  output_variable: image_analysis

Use cases:

• Image description
• OCR
• Visual QA
• Content moderation

Audio-to-Text

Transcribe audio to text:

Audio-to-Text Node:
  model: whisper-1
  audio: "{{input.audio_url}}"
  language: auto
  timestamps: true
  output_variable: transcription

Use cases:

• Meeting transcription
• Voice note processing
• Podcast transcription
• Call center analytics

Doc Intelligence

Extract structured data from documents:

Doc Intelligence Node:
  document: "{{input.document_url}}"
  extraction_schema:
    - field: invoice_number
      type: string
    - field: amount
      type: number
    - field: line_items
      type: array
  ocr_model: default
  output_variable: extracted_data

Use cases:

• Invoice processing
• Form extraction
• Contract analysis
• Receipt processing

Agentic App Node

Call Agent Platform applications:

Agentic App Node:
  app_id: "customer-support-bot"
  input:
    query: "{{input.customer_question}}"
    context: "{{input.customer_info}}"
  output_variable: agent_response

---

Integration Nodes

API Node

Call external APIs:

API Node:
  method: POST
  url: "https://api.example.com/orders"
  headers:
    Authorization: "Bearer {{env.API_KEY}}"
    Content-Type: "application/json"
  body:
    order_id: "{{input.order_id}}"
    action: "update_status"
  timeout: 30s
  retry:
    count: 3
    delay: 1s
  output_variable: api_response

Function Node

Run custom code:

Function Node:
  runtime: python3.9
  code: |
    def handler(input, context):
        # Process data
        result = input['value'] * 2
        return {'doubled': result}
  input:
    value: "{{previous_node.output}}"
  output_variable: function_result

Supported runtimes:

• Python 3.9+
• Node.js 18+

DocSearch Node

Search document repositories:

DocSearch Node:
  source: search_ai_app
  query: "{{input.search_query}}"
  filters:
    document_type: "policy"
  top_k: 5
  output_variable: search_results

---

Logic Nodes

Condition Node

Branch based on conditions:

Condition Node:
  conditions:
    - name: high_value
      expression: "{{amount}} > 10000"
      next: high_value_path
    - name: medium_value
      expression: "{{amount}} > 1000"
      next: medium_value_path
  default: standard_path

Loop Node

Iterate over collections:

Loop Node:
  collection: "{{input.items}}"
  item_variable: current_item
  max_iterations: 100
  parallel: false
  body:
    - node: process_item
    - node: store_result

Split Node

Execute parallel branches:

Split Node:
  branches:
    - name: email_notification
      nodes: [send_email]
    - name: slack_notification
      nodes: [send_slack]
    - name: update_database
      nodes: [db_update]
  wait_for_all: true

Merge Node

Combine parallel results:

Merge Node:
  inputs:
    - branch: email_notification
      variable: email_result
    - branch: slack_notification
      variable: slack_result
  output_variable: merged_results

---

Human Node

Route tasks to humans:

Human Node:
  task_type: review | approval | input | classification
  title: "Review AI Extraction"
  instructions: |
    Review the extracted data and correct any errors.
  assignees:
    - role: reviewer
    - user: [e-mail]
  fields:
    - name: invoice_number
      type: text
      value: "{{ai_extract.invoice_number}}"
      editable: true
    - name: amount
      type: number
      value: "{{ai_extract.amount}}"
      editable: true
    - name: approved
      type: boolean
      default: false
  timeout:
    duration: 24h
    action: escalate
  escalation:
    assignees:
      - role: supervisor

Task Types

Type	Description
Review	Review and edit AI output
Approval	Approve or reject
Input	Provide missing information
Classification	Categorize or label

---

Utility Nodes

Delay Node

Pause execution:

Delay Node:
  duration: 5m
  # Or wait until specific time
  until: "{{input.scheduled_time}}"

Variable Node

Set or transform variables:

Variable Node:
  operations:
    - set: formatted_date
      value: "{{format_date(input.date, 'YYYY-MM-DD')}}"
    - set: full_name
      value: "{{input.first_name}} {{input.last_name}}"

Log Node

Add logging for debugging:

Log Node:
  level: info | debug | warn | error
  message: "Processing order {{order_id}}"
  data:
    - order_id
    - customer_email

---

Error Handling

Try-Catch Pattern

Error Handling:
  try:
    - node: api_call
    - node: process_response
  catch:
    - condition: "{{error.type}} == 'timeout'"
      action: retry
      max_retries: 3
    - condition: "{{error.type}} == 'validation'"
      action: route_to_human
    - default:
      action: fail_workflow
      message: "{{error.message}}"

Retry Configuration

Retry:
  enabled: true
  max_attempts: 3
  delay: exponential
  initial_delay: 1s
  max_delay: 30s
  retryable_errors:
    - timeout
    - rate_limit
    - server_error

---

Related

• Workflows
• Inbox
• Model Hub