Trellis is an open-source framework for programmatically orchestrating LLM workflows as Directed Acyclic Graphs (DAGs) in Python. We’ve intentionally designed it to give developers as much control as possible, and we’ve written documentation to make it incredibly easy to get started.
Trellis is composed of only three abstractions: Node
, DAG
, and LLM
.
Node
is an abstract class with only one method required to implement.Node
s. It is the primary abstraction for orchestrating LLM workflows. When you
add edges between Node
s, you can specify a transformation function to reuse Node
s and connect any two Node
s.
Trellis verifies the data flowing between Nodes
in a DAG
to ensure the flow of data is validated.Trellis is an open-source framework for programmatically orchestrating LLM workflows as Directed Acyclic Graphs (DAGs) in Python. We’ve intentionally designed it to give developers as much control as possible, and we’ve written documentation to make it incredibly easy to get started.
Trellis is composed of only three abstractions: Node
, DAG
, and LLM
.
Node
is an abstract class with only one method required to implement.Node
s. It is the primary abstraction for orchestrating LLM workflows. When you
add edges between Node
s, you can specify a transformation function to reuse Node
s and connect any two Node
s.
Trellis verifies the data flowing between Nodes
in a DAG
to ensure the flow of data is validated.