Specify an LLM node and its connections using an Association:

Specify the node using LLMFunction and relying on the automatic dependencies resolution:

Specify the node using a template:

Use any valid LLMFunction prompt specification:

Define a "ListableLLMFunction" to thread over its input elements:

Evaluate the graph with LLM generation submitted concurrently:

Compare with the "LLMFunction" behavior; a single LLM generation is submitted with the entire list, returning a single output:

Specify arbitrary Wolfram Language code in the node using an "EvaluationFunction":

Use a pure Function with named Slot and rely on the automatic dependencies resolution:

Specify an arbitrary test function to condition the node evaluation:

The node function is run only if "TestFunction" result is True:

Skipped node returns a Missing[…] object:

Rely on the automatic dependencies resolution for "TestFunction":

Provide input nodes' values to start the graph evaluation:

If a single input is required, it is not necessary to use the Association:

This is equivalent to:

If no input is required, the graph can be evaluated on an empty sequence:

This is equivalent to:

Providing a result for the intermediate nodes will bypass the node function evaluation:

Evaluate output nodes' result of an LLMGraph; they are returned in an Association:

Evaluate a single output node LLMGraph result; it is returned unwrapped:

Request all nodes' results from an LLMGraph evaluation, including input and intermediate nodes:

Request an updated LLMGraph including the computation results:

Request a partially updated LLMGraph; when some dependencies are not satisfied by node initialization, only a subset of the nodes is assigned a result: