Box Developer Documentation
Log in
Latest version

Create AI agent

post
https://api.box.com/2.0
/ai_agents

This endpoint is in the version 2024.0. No changes are required to continue using it. For more details, see Box API versioning.

Creates an AI agent. At least one of the following capabilities must be provided: ask, text_gen, extract.

Request

bearer [ACCESS_TOKEN]
application/json

Request Body

stringin bodyrequired
"ai_agent"

The type of agent used to handle queries.

Value is always ai_agent

stringin bodyrequired
"enabled"

The state of the AI Agent. Possible values are: enabled, disabled, and enabled_for_selected_users.

The entity with type and ID [ Group (Base) / User (Base) ] arrayin bodyoptional

List of allowed users or groups.

AI agent capability ask request objectin body

The AI agent to be used to handle queries.

AI agent capability extract request objectin body

The AI agent to be used for metadata extraction.

stringin bodyoptional
"https://cdn01.boxcdn.net/app-assets/aistudio/avatars/logo_analytics.svg"

The icon reference of the AI Agent. It should have format of the URL https://cdn01.boxcdn.net/app-assets/aistudio/avatars/<file_name> where possible values of file_name are: logo_boxAi.png,logo_stamp.png,logo_legal.png,logo_finance.png,logo_config.png,logo_handshake.png,logo_analytics.png,logo_classification.png.

stringin bodyrequired
"My AI Agent"

The name of the AI Agent.

AI agent capability text generation request objectin body

The AI agent to be used to generate text.

Response

application/jsonAI agent (Full)

Definition of created AI agent.

application/jsonClient error

An unexpected client error.

application/jsonClient error

An unexpected server error.

post
Create AI agent
You can now try out some of our APIs live, right here in the documentation.
Log in

Request Example

Learn more about Box SDK versioning strategy.


Node/TypeScript v10
await client.aiStudio.createAiAgent({
  name: agentName,
  accessState: 'enabled',
  ask: new AiStudioAgentAsk({ accessState: 'enabled', description: 'desc1' }),
} satisfies CreateAiAgentInput);
Python v10
client.ai_studio.create_ai_agent(
    agent_name,
    "enabled",
    ask=AiStudioAgentAsk(access_state="enabled", description="desc1"),
)
.NET v10
await client.AiStudio.CreateAiAgentAsync(requestBody: new CreateAiAgent(name: agentName, accessState: "enabled") { Ask = new AiStudioAgentAsk(accessState: "enabled", description: "desc1") });
Swift v10
try await client.aiStudio.createAiAgent(requestBody: CreateAiAgent(name: agentName, accessState: "enabled", ask: AiStudioAgentAsk(accessState: "enabled", description: "desc1")))
Java v10
client.getAiStudio().createAiAgent(new CreateAiAgent.Builder(agentName, "enabled").ask(new AiStudioAgentAsk("enabled", "desc1")).build())

Response Example

{
  "id": "1234567890",
  "type": "ai_agent",
  "access_state": "enabled",
  "allowed_entities": [
    {
      "id": "11446498",
      "type": "user"
    }
  ],
  "ask": {
    "type": "ai_agent_ask",
    "access_state": "enabled",
    "basic_image": {
      "is_custom_instructions_included": false,
      "llm_endpoint_params": {
        "type": "openai_params",
        "frequency_penalty": 1.5,
        "presence_penalty": 1.5,
        "stop": "<|im_end|>",
        "temperature": 0,
        "top_p": 1
      },
      "model": "azure__openai__gpt_4o_mini",
      "num_tokens_for_completion": 8400,
      "prompt_template": "It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.",
      "system_message": "You are a helpful travel assistant specialized in budget travel",
      "warnings": [
        "MODEL_INACTIVE"
      ]
    },
    "basic_image_multi": {
      "is_custom_instructions_included": false,
      "llm_endpoint_params": {
        "type": "openai_params",
        "frequency_penalty": 1.5,
        "presence_penalty": 1.5,
        "stop": "<|im_end|>",
        "temperature": 0,
        "top_p": 1
      },
      "model": "azure__openai__gpt_4o_mini",
      "num_tokens_for_completion": 8400,
      "prompt_template": "It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.",
      "system_message": "You are a helpful travel assistant specialized in budget travel",
      "warnings": [
        "MODEL_INACTIVE"
      ]
    },
    "basic_text": {
      "is_custom_instructions_included": false,
      "llm_endpoint_params": {
        "type": "openai_params",
        "frequency_penalty": 1.5,
        "presence_penalty": 1.5,
        "stop": "<|im_end|>",
        "temperature": 0,
        "top_p": 1
      },
      "model": "azure__openai__gpt_4o_mini",
      "num_tokens_for_completion": 8400,
      "prompt_template": "It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.",
      "system_message": "You are a helpful travel assistant specialized in budget travel",
      "warnings": [
        "MODEL_INACTIVE"
      ]
    },
    "basic_text_multi": {
      "is_custom_instructions_included": false,
      "llm_endpoint_params": {
        "type": "openai_params",
        "frequency_penalty": 1.5,
        "presence_penalty": 1.5,
        "stop": "<|im_end|>",
        "temperature": 0,
        "top_p": 1
      },
      "model": "azure__openai__gpt_4o_mini",
      "num_tokens_for_completion": 8400,
      "prompt_template": "It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.",
      "system_message": "You are a helpful travel assistant specialized in budget travel",
      "warnings": [
        "MODEL_INACTIVE"
      ]
    },
    "custom_instructions": "This is a custom instruction",
    "description": "This is ASK Agent",
    "long_text": {
      "embeddings": {
        "model": "azure__openai__text_embedding_ada_002",
        "strategy": {
          "id": "basic",
          "num_tokens_per_chunk": 64
        }
      },
      "is_custom_instructions_included": false,
      "llm_endpoint_params": {
        "type": "openai_params",
        "frequency_penalty": 1.5,
        "presence_penalty": 1.5,
        "stop": "<|im_end|>",
        "temperature": 0,
        "top_p": 1
      },
      "model": "azure__openai__gpt_4o_mini",
      "num_tokens_for_completion": 8400,
      "prompt_template": "It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.",
      "system_message": "You are a helpful travel assistant specialized in budget travel",
      "warnings": [
        "MODEL_INACTIVE"
      ]
    },
    "long_text_multi": {
      "embeddings": {
        "model": "azure__openai__text_embedding_ada_002",
        "strategy": {
          "id": "basic",
          "num_tokens_per_chunk": 64
        }
      },
      "is_custom_instructions_included": false,
      "llm_endpoint_params": {
        "type": "openai_params",
        "frequency_penalty": 1.5,
        "presence_penalty": 1.5,
        "stop": "<|im_end|>",
        "temperature": 0,
        "top_p": 1
      },
      "model": "azure__openai__gpt_4o_mini",
      "num_tokens_for_completion": 8400,
      "prompt_template": "It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.",
      "system_message": "You are a helpful travel assistant specialized in budget travel",
      "warnings": [
        "MODEL_INACTIVE"
      ]
    },
    "spreadsheet": {
      "llm_endpoint_params": {
        "type": "openai_params",
        "frequency_penalty": 1.5,
        "presence_penalty": 1.5,
        "stop": "<|im_end|>",
        "temperature": 0,
        "top_p": 1
      },
      "model": "azure__openai__gpt_4o_mini",
      "num_tokens_for_completion": 8400,
      "warnings": [
        "MODEL_INACTIVE"
      ]
    },
    "suggested_questions": [
      "What is in this file?",
      "What are the main highlights of this document?"
    ]
  },
  "created_at": "2022-01-01T00:00:00Z",
  "created_by": {
    "id": "11446498",
    "type": "user"
  },
  "extract": {
    "type": "ai_agent_extract",
    "access_state": "enabled",
    "basic_image": {
      "is_custom_instructions_included": false,
      "llm_endpoint_params": {
        "type": "openai_params",
        "frequency_penalty": 1.5,
        "presence_penalty": 1.5,
        "stop": "<|im_end|>",
        "temperature": 0,
        "top_p": 1
      },
      "model": "azure__openai__gpt_4o_mini",
      "num_tokens_for_completion": 8400,
      "prompt_template": "It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.",
      "system_message": "You are a helpful travel assistant specialized in budget travel",
      "warnings": [
        "MODEL_INACTIVE"
      ]
    },
    "basic_text": {
      "is_custom_instructions_included": false,
      "llm_endpoint_params": {
        "type": "openai_params",
        "frequency_penalty": 1.5,
        "presence_penalty": 1.5,
        "stop": "<|im_end|>",
        "temperature": 0,
        "top_p": 1
      },
      "model": "azure__openai__gpt_4o_mini",
      "num_tokens_for_completion": 8400,
      "prompt_template": "It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.",
      "system_message": "You are a helpful travel assistant specialized in budget travel",
      "warnings": [
        "MODEL_INACTIVE"
      ]
    },
    "custom_instructions": "This is a custom instruction",
    "description": "This is ASK Agent",
    "long_text": {
      "embeddings": {
        "model": "azure__openai__text_embedding_ada_002",
        "strategy": {
          "id": "basic",
          "num_tokens_per_chunk": 64
        }
      },
      "is_custom_instructions_included": false,
      "llm_endpoint_params": {
        "type": "openai_params",
        "frequency_penalty": 1.5,
        "presence_penalty": 1.5,
        "stop": "<|im_end|>",
        "temperature": 0,
        "top_p": 1
      },
      "model": "azure__openai__gpt_4o_mini",
      "num_tokens_for_completion": 8400,
      "prompt_template": "It is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.",
      "system_message": "You are a helpful travel assistant specialized in budget travel",
      "warnings": [
        "MODEL_INACTIVE"
      ]
    }
  },
  "icon_reference": "https://cdn01.boxcdn.net/app-assets/aistudio/avatars/logo_analytics.svg",
  "modified_at": "2022-01-01T00:00:00Z",
  "modified_by": {
    "id": "11446498",
    "type": "user"
  },
  "name": "This is my Agent",
  "origin": "CUSTOM",
  "text_gen": {
    "type": "ai_agent_text_gen",
    "access_state": "enabled",
    "basic_gen": {
      "content_template": "---{content}---",
      "embeddings": {
        "model": "azure__openai__text_embedding_ada_002",
        "strategy": {
          "id": "basic",
          "num_tokens_per_chunk": 64
        }
      },
      "is_custom_instructions_included": false,
      "llm_endpoint_params": {
        "type": "openai_params",
        "frequency_penalty": 1.5,
        "presence_penalty": 1.5,
        "stop": "<|im_end|>",
        "temperature": 0,
        "top_p": 1
      },
      "model": "azure__openai__gpt_4o_mini",
      "num_tokens_for_completion": 8400,
      "prompt_template": "It is `{current_date}`, and I have $8000 and want to spend a week in the Azores. `{user_question}`",
      "system_message": "You are a helpful travel assistant specialized in budget travel",
      "warnings": [
        "MODEL_INACTIVE"
      ]
    },
    "custom_instructions": "This is a custom instruction",
    "description": "This is ASK Agent",
    "suggested_questions": [
      "What is in this file?",
      "What are the main highlights of this document?"
    ]
  }
}