🧠Agents

AI that can take actions based on live data!

Overview

Agents are how you can create complex prompt-chains and interact with live data, API's, and enhance your Prompts with RAG. This feature is under active development, but there's already enough there to bring value to our Beamers, so we thought we'd give y'all access.

Agents function very similar to Prompts, and since they have the same inputs and outputs as a Prompt can even be swapped in your application with very little work. You send variables and messages and then we respond with a new ChatMessage.

Every Agent is expecting the last step to be a Prompt, in order to support streaming in responses to your users.

Every Agent can be accessed via the API with it's AI, or distributed via the Solo Agent features, accessed in the Sidebar Menu (check out the next section for details).

Get a chat completion from an agent

This endpoint processes a chat interaction with a specified agent. It supports both streaming and non-streaming operations based on the provided parameters.

POSThttps://api.easybeam.ai/v1/agent/{id}

Authorization

BearerAuth

Path parameters

id*string

Unique identifier for the agent

Example: "agent-abcde"

Body

application/json

Payload containing the chat details and parameters for processing the agent interaction

variablesobject

Variables for the agent

chatIdnullable string

Identifier for the chat session

Example: "chat-12345"

messagesarray of ChatMessage (object)

List of messages in the chat

streamboolean

Whether to stream the response

Example: true

userIdnullable string

ID of the user interacting with the agent

Example: "user-67890"

consolidateStreamnullable boolean

Whether to consolidate the stream

Example: true

userSecretsobject

User-specific secrets for the agent

Response

200400401

Agent interaction successful

Body

application/json

newMessageChatMessage (object)

chatIdstring

Identifier for the chat session.

Example: "chat-67890"

streamFinishednullable boolean

Indicates if the streaming has finished.

Example: false

Request

JavaScriptCurlPythonHTTP

const response = await fetch('https://api.easybeam.ai/v1/agent/{id}', {
    method: 'POST',
    headers: {
      "Authorization": "Bearer JWT",
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "variables": {
        "keyA": "valueA",
        "keyB": "valueB"
      },
      "chatId": "chat-12345",
      "messages": [
        {
          "content": "Can you help me with this task?",
          "role": "USER",
          "createdAt": "2024-04-27T13:00:00Z",
          "id": "msg-3"
        }
      ],
      "stream": false,
      "userId": "user-67890",
      "consolidateStream": true,
      "userSecrets": {}
    }),
});
const data = await response.json();

Response

200400401

{
  "newMessage": {
    "content": "Hello, how can I assist you today?",
    "role": "USER",
    "providerId": "openai",
    "createdAt": "2024-04-27T12:34:56Z",
    "id": "msg-1",
    "inputTokens": 150.5,
    "outputTokens": 200.75
  },
  "chatId": "chat-67890",
  "streamFinished": false
}