Skip to main content
Add these nodes with the pipeline builder: pipeline.add(name="...").<node>(...). Each entry lists the node’s configuration parameters. See the Pipeline reference for add, run, and lifecycle methods.

agent — Agent

Agent
Platform docs: Agent
Parameters
bool
required
AcceptsAgent
required
str
default:"'gpt-5.4'"
Any
default:"{}"
dict
default:"{}"
dict
default:"{}"
str
default:"'openai'"

create_skill — Create Skill

Create a new skill with a name, description, and content
Parameters
str
required
str
required
str
default:"''"

file_save — File Save

Save a file on the VectorShift platform (under the ‘Files’ tab).
Platform docs: File Save
Parameters
AcceptsFileList
required
str
required

get_skill — Get Skill

Retrieve the full content of a skill by its ID
Parameters
Any | ListType | list[Any]
required

list_objects — List Objects

List VectorShift objects accessible to the current user
Parameters
bool
default:"True"
int
default:"0"
str
required
One of: agent, knowledge_base, pipeline, prompt, table, transformation
int
default:"0"
bool
default:"False"

pipeline — Pipeline

{{collection.pipelines}}
Platform docs: Pipeline
Parameters
AcceptsPipeline
default:"{}"

share_object — Share Object

Share a VectorShift object with another user
Parameters
str
default:"'knowledge_base'"
One of: knowledge_base
AcceptsKnowledgeBase
str
default:"''"
Enter the name of the organization of the user (leave blank if not part of org)
str
required
Enter the username or email of the user you want to share with

text — Text

Accepts Text from upstream nodes and allows you to write additional text / concatenate different texts to pass to downstream nodes.
Parameters
str
required

transformation — Transformation

Use Python code to create a custom node