Entity Extraction Agent

AI Toolkit entity_extraction_agent Professional

Extract structured entities from text

Overview

The Entity Extraction Agent extracts structured information from users through natural conversation. The agent actively asks follow-up questions to gather all required information.

How It Works

  1. Analyze Conversation: The agent reviews the conversation to identify what information has been provided
  2. Check Completeness: Determines if all required fields have been collected
  3. Ask Questions: If information is missing, the agent asks the user for it
  4. Extract Data: Once sufficient information is available, extracts structured data matching your schema
  5. Continue: Flow proceeds with the extracted data available

Output Variable

The extracted data is stored in a structured format:

Extracted: {{entity.data.field_name}}
Status: {{entity.status}}

Configuration Fields

Context Hint (Optional) handlebars

Optional context to guide the agent.

Show details

Supports Handlebars syntax:

{{variable_name}}
Entity Schema schema_builder Required

Define the structure of entities to extract.

Show details

How it works:

The AI will work with data matching this schema. Required fields trigger follow-up actions if missing. Field descriptions help the AI understand what each field represents.

Available field types:

  • Text fields
  • Number fields
  • Boolean fields
  • Array fields
  • Object fields
AI Configuration agent_settings

Configure the AI model and behavior.

Show details

Configuration options:

  • AI model selection
  • Temperature (0.0-2.0) - Higher = more creative, Lower = more consistent
  • Conversation context length - Amount of chat history to include
  • Personality instructions - Defines how the AI interacts

Temperature guide:

  • 0.0-0.5: Focused, deterministic, predictable
  • 0.5-1.0: Balanced between creativity and consistency
  • 1.0-2.0: Creative, varied, exploratory
Error Handling error_handling

Configure how the node handles errors.

Show details

Configuration options:

  • Continue on error: If enabled, flow continues through error handle. If disabled, flow terminates.
  • Retry attempts (0-3): Number of times to retry the operation before failing
  • Retry delay (100-1000ms): Time to wait between retry attempts

Use retries for transient errors like network issues. Use "continue on error" to implement fallback logic.

Output Variables

This node stores its output in a variable that can be referenced in subsequent nodes using the {{variable}} syntax.

{{variable}}.status string

Extraction status ("success")

{{variable}}.data object

Extracted entities object (matches defined schema)

{{variable}}.timestamp string

ISO 8601 timestamp

Connection Points

Input
Accepts incoming connections from other nodes
Output
Connects to the next node in the flow

More in AI Toolkit