Box Developer Documentation
Log in
Latest version

Get AI agent default configuration

get
https://api.box.com/2.0
/ai_agent_default

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

Get the AI agent default config

Related Guides

Request

bearer [ACCESS_TOKEN]
application/json

Query Parameters

stringin queryoptional
ja

The ISO language code to return the agent config for. If the language is not supported the default agent config is returned.

stringin queryrequired
ask

The mode to filter the agent config to return.

Value is one of ask,text_gen,extract,extract_structured

stringin queryoptional
azure__openai__gpt_4o_mini

The model to return the default agent config for.

Response

application/jsonAI agent for question requests/AI agent for extract requests/AI agent for structured extract request/AI agent for text generation requests

A successful response including the default agent configuration. This response can be one of the following four objects:

  • AI agent for questions
  • AI agent for text generation
  • AI agent for freeform metadata extraction
  • AI agent for structured metadata extraction. The response depends on the agent configuration requested in this endpoint.
application/jsonClient error

An unexpected server error.

application/jsonClient error

An unexpected error.

get
Get AI agent default configuration
You can now try out some of our APIs live, right here in the documentation.
Log in

Request Example

cURL
curl -L GET "https://api.box.com/2.0/ai_agent_default?mode=text_gen" \
     -H 'Authorization: Bearer <ACCESS_TOKEN>'
TypeScript Gen
await client.ai.getAiAgentDefaultConfig({
  mode: 'ask' as GetAiAgentDefaultConfigQueryParamsModeField,
  language: 'en-US',
} satisfies GetAiAgentDefaultConfigQueryParams);
Python Gen
client.ai.get_ai_agent_default_config(GetAiAgentDefaultConfigMode.ASK, language="en-US")
.NET Gen
await client.Ai.GetAiAgentDefaultConfigAsync(queryParams: new GetAiAgentDefaultConfigQueryParams(mode: GetAiAgentDefaultConfigQueryParamsModeField.Ask) { Language = "en-US" });
Swift Gen (Beta)
try await client.ai.getAiAgentDefaultConfig(queryParams: GetAiAgentDefaultConfigQueryParams(mode: GetAiAgentDefaultConfigQueryParamsModeField.ask, language: "en-US"))
Java
BoxAIAgentConfig config = BoxAI.getAiAgentDefaultConfig(
    api,
    BoxAIAgent.Mode.ASK,
    "en",
    "openai__gpt_3_5_turbo"
);
Python
config = client.get_ai_agent_default_config(
    mode='text_gen',
    language='en',
    model='openai__gpt_3_5_turbo'
)
print(config)
Node
client.ai.getAiAgentDefaultConfig({
    mode: 'ask',
    language: 'en',
    model:'openai__gpt_3_5_turbo'
}).then(response => {
    /* response -> {
        "type": "ai_agent_ask",
        "basic_text": {
            "llm_endpoint_params": {
            "type": "openai_params",
            "frequency_penalty": 1.5,
            "presence_penalty": 1.5,
            "stop": "<|im_end|>",
            "temperature": 0,
            "top_p": 1
            },
            "model": "openai__gpt_3_5_turbo",
            "num_tokens_for_completion": 8400,
            "prompt_template": "It is `{current_date}`, and I have $8000 and want to spend a week in the Azores. What should I see?",
            "system_message": "You are a helpful travel assistant specialized in budget travel"
        },
        ...
    } */
});

Response Example

{
  "type": "ai_agent_ask",
  "basic_text": {
    "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"
  },
  "basic_text_multi": {
    "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"
  },
  "long_text": {
    "embeddings": {
      "model": "azure__openai__text_embedding_ada_002",
      "strategy": {
        "id": "basic",
        "num_tokens_per_chunk": 64
      }
    },
    "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"
  },
  "long_text_multi": {
    "embeddings": {
      "model": "azure__openai__text_embedding_ada_002",
      "strategy": {
        "id": "basic",
        "num_tokens_per_chunk": 64
      }
    },
    "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"
  }
}