Portal Community

AI Nodes

ai-agent

Invokes an Octopus AI Agent to perform a multi-step reasoning task. The agent can use tools, query memory, and return a structured result.

PortTypeDescription
input (main)InTask description and context data
toolsIn (optional)Override tool list for this invocation
memoryIn (optional)Memory context to inject
outputOutAgent result: { result, actions, tokens }
errorOutAgent failure or timeout

openai-llm

Calls OpenAI's completion or chat API directly.

FieldDescription
Credential IDOpenAI API Key credential
Modelgpt-4o, gpt-4-turbo, gpt-3.5-turbo, etc.
System PromptSystem message (expressions supported)
User PromptUser message (expressions supported)
Temperature0.0 (deterministic) to 2.0 (creative)
Max TokensResponse length cap
JSON ModeForce structured JSON output

anthropic-chat

Calls Anthropic's Claude API (claude-3-5-sonnet, claude-3-opus, claude-3-haiku).

Same configuration shape as openai-llm but specific to Anthropic credentials and model names.

Advanced Execution Nodes

sub-workflow

Invokes another ProcessThread as a child workflow, waits for its completion, and receives its result as the output.

FieldDescription
Process IDThe target Process to invoke
Thread IDOptional: specific thread. If omitted, uses the published thread.
Input DataExpression providing the trigger data for the child workflow
TimeoutMaximum wait time for child completion

parallel-fork

Starts multiple downstream branches simultaneously. All branches receive the same input data. Used with parallel-join to merge results.

Output ports: Configurable — add named output ports (branch1, branch2, …)

parallel-join

Waits for all (or a configurable number of) parallel branches to complete, then merges their outputs into a single object before continuing.