Ligantic
Knowledge Base
Tutorials
Updates
Search Articles
Login
Free Sign Up
Home
Get Started
Tutorials
How-to guides
Reference
Explanation
Spaces
Schemas
Flows
Experiences
Endpoints
SDK and CLI
Browse documentation
Home
Get Started
Spaces
Schemas
Flows
Experiences
Endpoints
SDK and CLI
Docs
/

AI - Chat Message

Type identifier: ai:llm:chatMessage Category: AI Operations

Description

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).

For exact supported model identifiers and provider-specific capability differences, use AI - Model Reference.

Input Handles

Handle

Type

Description

trigger

control

Triggers the LLM request.

model

string

(Dynamic mode) Runtime model name input.

<variable>

varies

Dynamic handles for each defined variable.

modelParameters.temperature

number

Dynamic Temperature, when supported by the model.

modelParameters.topK

number

Dynamic Top K, when supported by the model.

modelParameters.topP

number

Dynamic Top P, when supported by the model.

modelParameters.maxTokens

number

Dynamic Max Tokens.

modelParameters.stopSequences

string[]

Dynamic Stop Sequences.

thinkingTokensBudget

number

Dynamic thinking token budget.

action:<id>:result

any

Action result when Continue With Result is enabled.

action:<id>:return

control

Returns control from a continuing action.

Output Handles

Handle

Type

Description

responseText

string or Content

The complete response in non-streaming mode.

responseStream

stream of strings

Text chunks in streaming mode, including when Parse to Content is enabled.

responseThinking

string[]

Thinking blocks when the configured model exposes thinking.

action:<id>:trigger

control

Runs the branch for a returned action call.

action:<id>:data

action Schema

Input returned for that action call.

success

control

Non-streaming response and action processing completed.

error

control

Request or response processing failed.

Streaming mode exposes responseStream instead of responseText and success. Use Stream - Collect to process chunks and receive its done signal.

Configuration Options

Model Selection

Option

Type

Default

Description

Model

enum or dynamic string handle

claude-sonnet-5

The LLM model to use, literal or runtime input.

When Model is set to dynamic, the node exposes a model input handle and resolves the model name at runtime.

If the runtime model string is not in the supported model list, the node fails with a clear configuration error.

Available models are listed by provider (OpenAI, Anthropic, Google AI, and Groq) in AI - Model Reference — Chat Message Models. Deprecated model names and their replacements are in AI - Model Reference — Deprecated Models and Fallbacks.

Model Parameters

Parameter

Type

Description

Temperature

number

Randomness in responses (0-2).

Top K

number

Limit token selection to top K candidates.

Top P

number

Nucleus sampling probability.

Max Tokens

number

Maximum response length.

Stop Sequences

string[]

Sequences that stop generation.

Note: Sampling parameters (Temperature, Top K, Top P) are not configurable for adaptive-thinking Claude models (claude-fable-5-1, claude-fable-5, claude-opus-5-5, claude-opus-5, claude-sonnet-5, claude-opus-4-8, claude-opus-4-7) and OpenAI non-chat/reasoning models (gpt-6-astra, gpt-6-sol, gpt-6-luna, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, gpt-5.5, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.1, gpt-5-2025-08-07, gpt-5-mini-2025-08-07, gpt-5-nano-2025-08-07).

Response Options

Option

Type

Default

Description

Parse to Content

boolean

false

Parse Markdown response as Content.

Stream Response

boolean

false

Enable streaming response mode.

Streaming responses buffer up to 64 unread chunks or 1,048,576 UTF-8 bytes, whichever limit is reached first. Reading pauses until chunks are consumed. A single chunk larger than the byte limit fails the stream. These limits do not cap the final accumulated response.

Extended Thinking

For supported models:

Option

Type

Description

Enabled

boolean

Enable extended thinking mode.

Tokens Budget

number

Maximum tokens for thinking.

Adaptive thinking models such as claude-fable-5-1, claude-fable-5, claude-opus-5-5, claude-opus-5, claude-sonnet-5, claude-opus-4-8, and claude-opus-4-7 do not use the Tokens Budget option. Other supported Anthropic models use the configured Tokens Budget.

Auto-Continue

Option

Type

Description

Max Turns

number

Maximum conversation turns for auto-continuation.

Variables

Array of variables that can be used in message templates. Each variable creates a dynamic input handle.

Message Templates

Array of message templates defining the conversation:

Field

Type

Description

Type

"system" | "user" | "assistant"

Message role.

Message Template

string or Content

Template with variable placeholders.

Cached

boolean

Enable prompt caching (Anthropic).

Repeating messages support:

  • Iterate over array variables
  • Create dynamic message sequences

Actions (Tool Use)

Field

Type

Description

Name

string

Action name for the AI to call.

Description

string

Description of what the action does.

Input Schema

schema

Expected input structure.

Force Use

boolean

Force the AI to use this action.

Continue With Result

boolean

Auto-continue after action result.

Behaviour

  1. Resolves all variable values from input handles
  2. Constructs messages from templates with interpolated variables
  3. Sends request to selected LLM provider
  4. Processes response (streaming or complete)
  5. If actions are defined and invoked:

    • Triggers corresponding action handle
    • Waits for action result
    • Optionally continues conversation with result
  6. In non-streaming mode, returns the final response and triggers success

Variable Interpolation

Variables in templates are replaced with actual values:

  • Content variables support rich formatting
  • File variables are passed to vision-capable models
  • Nested object properties accessed via dot notation

Provider-Specific Features

Feature

OpenAI

Anthropic

Google

Groq

Streaming

✓

✓

✓

✓

Vision

✓

✓

✓

✓

Audio

✓

-

-

✓

Thinking

-

✓

-

-

Caching

-

✓

-

-

Examples

Simple Question-Answer

Configuration:

  • Model: claude-haiku-4-5-20251001
  • Variables: Question
  • Messages:

    • System: "You are a helpful assistant."
    • User: {Question}

Structured Extraction With Actions

Configuration:

  • Model: gpt-4o
  • Actions:

    • Name: "extract_data"
    • Schema: Structured output format
    • Force Use: true
  • Continue With Result: false

Streaming Chat Response

Configuration:

  • Model: claude-sonnet-5
  • Stream Response: true

Use stream output with Stream - Collect to process incrementally.

Related pages

AI - Data Extraction
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.
Page not found. It may have moved or may not be published.
Browse documentation