---
title: "Ask question"
method: POST
path: "/ai/ask"
tags: ["AI"]
---

# Ask question

`POST /ai/ask`

Sends an AI request to supported LLMs and returns an answer specifically focused on the user's question given the provided context.

You can ask a question about a single file, several files, or the entire contents of a Box Hub. To search across and ask questions about everything in a Box Hub, send a single item with `type` set to `hubs` and the Hub's ID as the `id`. Box AI answers the question using the indexed content of all files in that Hub.

Asking questions about a Box Hub requires Box AI for Hubs to be enabled in the Admin Console before the Hub is created, so that its content is indexed.

## Request body

- AiAsk — AI ask request object.
  - `mode` 'multiple_item_qa' | 'single_item_qa', required — Box AI handles text documents with text representations up to 2MB in size, or a maximum of 25 files, whichever comes first. If the text file size exceeds 2MB, the first 2MB of text representation will be processed. Box AI handles image documents with a resolution of 1024 x 1024 pixels, with a maximum of 5 images or 5 pages for multi-page images. If the number of image or image pages exceeds 5, the first 5 images or pages will be processed. If you set mode parameter to `single_item_qa`, the items array can have one element only. Currently Box AI does not support multi-modal requests. If both images and text are sent Box AI will only process the text.
  - `prompt` string, required — The prompt provided by the client to be answered by the LLM. The prompt's length is limited to 10000 characters.
  - `items` AiItemAsk[], required — The items to be processed by the LLM, often files. To search across and ask questions about the contents of a Box Hub, pass a single item with `type` set to `hubs`. See the item `type` property for details.
    - `id` string, required — The ID of the file, or the ID of the Box Hub when `type` is `hubs`.
    - `type` 'file' | 'hubs', required — The type of the item. Use `file` to ask a question about a file, or `hubs` to search across and ask a question about the entire contents of a Box Hub. A `hubs` item must be the only item in the request.
    - `content` string — The content of the item, often the text representation.
  - `dialogue_history` AiDialogueHistory[] — The history of prompts and answers previously passed to the LLM. This provides additional context to the LLM in generating the response.
    - `prompt` string — The prompt previously provided by the client and answered by the LLM.
    - `answer` string — The answer previously provided by the LLM.
    - `created_at` string, date-time — The ISO date formatted timestamp of when the previous answer to the prompt was created.
  - `include_citations` boolean — A flag to indicate whether citations should be returned.
  - `ai_agent` union
    - object — The AI agent to be used to handle the request.
      - `type` 'ai_agent_id', required — The type of AI agent used to handle queries.
      - `id` string, required — The ID of an Agent. This can be a numeric ID for custom agents (for example, `14031`) or a unique identifier for pre-built agents (for example, `enhanced_extract_agent` for the [Enhanced Extract Agent](https://developer.box.com/guides/box-ai/ai-tutorials/extract-metadata-structured#enhanced-extract-agent)).
    - object — The AI agent to be used to handle the request.
      - `type` 'ai_agent_ask', required — The type of AI agent used to handle queries.
      - `long_text` AiAgentLongTextTool — AI agent processor used to handle basic text.
        - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models).
        - `num_tokens_for_completion` integer — The number of tokens for completion.
        - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model.
          - object — AI LLM endpoint params OpenAI object.
            - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
            - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
            - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens.
          - object — AI LLM endpoint params Google object.
            - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**.
            - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection.
            - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
          - object — AI LLM endpoint params AWS object.
            - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
          - object — AI LLM endpoint params IBM object.
            - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
        - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do.
        - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use.
        - `embeddings` object
          - `model` string — The model used for the AI agent for calculating embeddings.
          - `strategy` object
            - `id` string — The strategy used for the AI agent for calculating embeddings.
            - `num_tokens_per_chunk` integer — The number of tokens per chunk.
      - `basic_text` AiAgentBasicTextTool — AI agent processor used to handle basic text.
        - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models).
        - `num_tokens_for_completion` integer — The number of tokens for completion.
        - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model.
          - object — AI LLM endpoint params OpenAI object.
            - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
            - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
            - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens.
          - object — AI LLM endpoint params Google object.
            - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**.
            - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection.
            - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
          - object — AI LLM endpoint params AWS object.
            - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
          - object — AI LLM endpoint params IBM object.
            - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
        - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do.
        - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use.
      - `spreadsheet` AiAgentSpreadsheetTool — The AI agent tool used to handle spreadsheets and tabular data.
        - `model` string — The model used for the AI agent for spreadsheets. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models).
        - `num_tokens_for_completion` integer — The number of tokens for completion.
        - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model.
          - object — AI LLM endpoint params OpenAI object.
            - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
            - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
            - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens.
          - object — AI LLM endpoint params Google object.
            - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**.
            - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection.
            - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
          - object — AI LLM endpoint params AWS object.
            - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
          - object — AI LLM endpoint params IBM object.
            - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
      - `long_text_multi` AiAgentLongTextTool — AI agent processor used to handle basic text.
        - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models).
        - `num_tokens_for_completion` integer — The number of tokens for completion.
        - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model.
          - object — AI LLM endpoint params OpenAI object.
            - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
            - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
            - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens.
          - object — AI LLM endpoint params Google object.
            - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**.
            - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection.
            - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
          - object — AI LLM endpoint params AWS object.
            - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
          - object — AI LLM endpoint params IBM object.
            - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
        - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do.
        - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use.
        - `embeddings` object
          - `model` string — The model used for the AI agent for calculating embeddings.
          - `strategy` object
            - `id` string — The strategy used for the AI agent for calculating embeddings.
            - `num_tokens_per_chunk` integer — The number of tokens per chunk.
      - `basic_text_multi` AiAgentBasicTextTool — AI agent processor used to handle basic text.
        - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models).
        - `num_tokens_for_completion` integer — The number of tokens for completion.
        - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model.
          - object — AI LLM endpoint params OpenAI object.
            - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
            - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
            - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens.
          - object — AI LLM endpoint params Google object.
            - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**.
            - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection.
            - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
          - object — AI LLM endpoint params AWS object.
            - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
          - object — AI LLM endpoint params IBM object.
            - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
        - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do.
        - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use.
      - `basic_image` AiAgentBasicTextTool — AI agent processor used to handle basic text.
        - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models).
        - `num_tokens_for_completion` integer — The number of tokens for completion.
        - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model.
          - object — AI LLM endpoint params OpenAI object.
            - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
            - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
            - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens.
          - object — AI LLM endpoint params Google object.
            - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**.
            - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection.
            - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
          - object — AI LLM endpoint params AWS object.
            - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
          - object — AI LLM endpoint params IBM object.
            - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
        - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do.
        - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use.
      - `basic_image_multi` AiAgentBasicTextTool — AI agent processor used to handle basic text.
        - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models).
        - `num_tokens_for_completion` integer — The number of tokens for completion.
        - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model.
          - object — AI LLM endpoint params OpenAI object.
            - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
            - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
            - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens.
          - object — AI LLM endpoint params Google object.
            - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**.
            - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection.
            - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
          - object — AI LLM endpoint params AWS object.
            - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
          - object — AI LLM endpoint params IBM object.
            - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**.
            - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
            - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
            - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature.
        - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do.
        - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use.

## Response `200`

A successful response including the answer from the LLM.

- AiResponseFull — AI response.
  - `answer` string, required — The answer provided by the LLM.
  - `created_at` string, date-time, required — The ISO date formatted timestamp of when the answer to the prompt was created.
  - `completion_reason` string — The reason the response finishes.
  - `ai_agent_info` AiAgentInfo — The information on the models and processors used in the request.
    - `models` object[] — The models used for the request.
      - `name` string — The name of the model used for the request.
      - `provider` string — The provider that owns the model used for the request.
      - `supported_purpose` string — The supported purpose utilized by the model used for the request.
    - `processor` string — The processor used for the request.
  - `citations` AiCitation[] — The citations of the LLM's answer reference.
    - `content` string — The specific content from where the answer was referenced.
    - `id` string — The id of the item.
    - `type` 'file' — The type of the item.
    - `name` string — The name of the item.

## Other responses

- `204` — No content is available to answer the question. This is returned when the request item is a hub, but content in the hubs is not indexed. To ensure content in the hub is indexed, make sure Box AI for Hubs in the Admin Console was enabled before hub creation.
- `500` — An unexpected server error.
- `default` — An unexpected error.

---

[API](https://skmtc.net/box/apis/platform-api.md) · [All operations](https://skmtc.net/box/apis/platform-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/box/platform-api/revisions/ba8f087e1a4d/schema)