Create Conversation

client.conversations.create(, ?): Conversation { id, agent_id, created_at, 5 more }

post/v1/conversations/

Create a new conversation for an agent.

ParametersExpand Collapse

params: ConversationCreateParams { agent_id, summary }

agent_id: string

Query param: The agent ID to create a conversation for

summary?: string | null

Body param: A summary of the conversation.

ReturnsExpand Collapse

Conversation { id, agent_id, created_at, 5 more }

Represents a conversation on an agent for concurrent messaging.

id: string

The unique identifier of the conversation.

agent_id: string

The ID of the agent this conversation belongs to.

created_at?: string | null

The timestamp when the object was created.

formatdate-time

created_by_id?: string | null

The id of the user that made this object.

in_context_message_ids?: Array<string>

The IDs of in-context messages for the conversation.

last_updated_by_id?: string | null

The id of the user that made this object.

summary?: string | null

A summary of the conversation.

updated_at?: string | null

The timestamp when the object was last updated.

formatdate-time

Create Conversation

import Letta from '@letta-ai/letta-client';

const client = new Letta({
  apiKey: process.env['LETTA_API_KEY'], // This is the default and can be omitted
});

const conversation = await client.conversations.create({ agent_id: 'agent_id' });

console.log(conversation.id);

{
  "id": "id",
  "agent_id": "agent_id",
  "created_at": "2019-12-27T18:11:19.117Z",
  "created_by_id": "created_by_id",
  "in_context_message_ids": [
    "string"
  ],
  "last_updated_by_id": "last_updated_by_id",
  "summary": "summary",
  "updated_at": "2019-12-27T18:11:19.117Z"
}

Returns Examples

{
  "id": "id",
  "agent_id": "agent_id",
  "created_at": "2019-12-27T18:11:19.117Z",
  "created_by_id": "created_by_id",
  "in_context_message_ids": [
    "string"
  ],
  "last_updated_by_id": "last_updated_by_id",
  "summary": "summary",
  "updated_at": "2019-12-27T18:11:19.117Z"
}