AI - Data Extraction

Type identifier: ai:dataExtraction Category: AI Operations

Description

The AI - Data Extraction node uses large language models to extract structured data from unstructured text content. It can extract data matching a defined schema, optionally creating Records automatically upon extraction.

Input Handles

Handle	Type	Description
`trigger`	control	Triggers the extraction process.
`content`	`string` or `Content`	The text content to extract data from.

Output Handles

Handle	Type	Description
`extracted`	schema-defined	Extracted data matching the schema (single or array).
`success`	control	Triggered when extraction completes successfully.
`error`	control	Triggered when extraction fails.

Configuration Options

Option	Type	Default	Description
Extract Single	`boolean`	`false`	Extract only one item vs. multiple items.
Additional Instructions	`Content`	-	Extra instructions for the AI model.

Schema Configuration

The extraction schema can be defined in two ways:

Reference Mode:

Option	Type	Description
Schema ID	`string`	Reference to an existing Schema.
Creation on Extraction	`boolean`	Automatically create Records when extracted.

Literal Mode:

Option	Type	Description
Schema Config	schema	Inline schema definition.

Behaviour

Receives unstructured text content
Sends the content, the target schema, and any Additional Instructions to the AI model
If Creation on Extraction is enabled:
- Creates a Record for each extracted item
- Created Records are attributed to the run in the audit history, matching the Object - Create node
Returns extracted data

Extraction Modes

Mode	Description	Output Type
Single	Extract exactly one item	Object
Multiple	Extract all matching items	Array of objects

Examples

Extract Contact Information

Configuration:

Extract Single: false
Schema (reference): "Contact" Schema with name, email, phone

Input:

Please reach out to John Smith at john@example.com or call 555-1234.
You can also contact Sarah at sarah@company.org.

Output:

[
  { "name": "John Smith", "email": "john@example.com", "phone": "555-1234" },
  { "name": "Sarah", "email": "sarah@company.org", "phone": null }
]

Extract With Auto-Creation

Configuration:

Extract Single: false
Schema ID: "product-mention-schema"
Creation on Extraction: true

Use case: Extract product mentions from reviews and automatically create Records.

Custom Extraction Instructions

Configuration:

Additional Instructions:

Focus on extracting only confirmed information.
Mark uncertain values as null.
Use ISO date format for any dates.

AI - Chat Message

The AI - Chat Message node enables conversations with large language models (LLMs) from multiple providers including OpenAI, Anthropic, Google AI, and Groq. It supports dynamic message templates with variable interpolation, streaming responses, extended thinking, and AI actions (tool use).

AI - Model Reference

Canonical model list for AI nodes, including deprecated model fallback mappings.

Object - Create

Creates a new Record in a specified Schema. The created Record can be queried or modified by subsequent nodes in the Flow.

Text - Parse Document to Content

Parses PDF files into structured content. Extracts text with page-level granularity, generates page images, and splits content into chunks.

AI - Data Extraction

Description

Input Handles

Output Handles

Configuration Options

Schema Configuration

Behaviour

Extraction Modes

Examples

Extract Contact Information

Extract With Auto-Creation

Custom Extraction Instructions

Related pages