Skip to main content
Creates a new conversation within a workspace. A conversation groups related messages together so MemoryLake can extract structured facts from the exchange. You must attach exactly one read-write project via rw_project_ids — this is the project where extracted facts and memory are stored.
Permission required: workspace:conv_create (plus project:mem_add and project:doc_add on the specified project)

Path Parameters

string
required
Workspace identifier

Request Body

string
required
Caller-defined unique identifier. Use this to correlate the conversation with records in your own system.
string
required
Conversation kind: DIRECT (one-on-one) or GROUP (multi-participant).
array
required
Read-write project(s) the conversation reads context from and writes facts to. Exactly one project ID is required.
array
required
IDs of the actors taking part in the conversation. At least one is required: every message is attributed to an actor, and each actor’s memory is built from what they say, so a conversation with no actor can neither tell its participants apart nor build anyone’s memory. Each ID must reference an actor you have already created and bound to this workspace.
string
Display name for the conversation
object
Arbitrary key-value metadata to attach to the conversation

Response

object