AI agent capability text generation request

API version 2024.0 The AI agent to be used to generate text.

type

string

example: ai_agent_text_genThe type of AI agent used for generating text.Value is always ai_agent_text_gen

access_state

string

example: enabledThe state of the AI Agent capability. Possible values are: enabled and disabled.

basic_gen

object

AI agent basic tool used to generate text.

Show child attributes

content_template

string

example: ---{content}---How the content should be included in a request to the LLM. Input for {content} is optional, depending on the use.

embeddings

object

Show child attributes

model

string

example: azure__openai__text_embedding_ada_002The model used for the AI agent for calculating embeddings.

strategy

object

Show child attributes

string

example: basicThe strategy used for the AI agent for calculating embeddings.

num_tokens_per_chunk

integer

example: 64The number of tokens per chunk.

is_custom_instructions_included

boolean

example: falseTrue if system message contains custom instructions placeholder, false otherwise.

llm_endpoint_params

AI LLM endpoint params AWS/AI LLM endpoint params Google/AI LLM endpoint params IBM/AI LLM endpoint params OpenAIobject

The parameters for the LLM endpoint specific to a model.

model

string

example: azure__openai__gpt_4o_miniThe model used for the AI agent for basic text. For specific model values, see the available models list.

num_tokens_for_completion

integer

example: 8400The number of tokens for completion.

prompt_template

string

example: \{user_question\}The prompt template contains contextual information of the request and the user prompt.When using the prompt_template parameter, you must include input for {user_question}. Inputs for {current_date} and {content} are optional, depending on the use.

system_message

string

example: You are a helpful travel assistant specialized in budget travelSystem messages aim at helping the LLM understand its role and what it is supposed to do. The input for {current_date} is optional, depending on the use.

custom_instructions

string

example: This is a custom instructionCustom instructions for the AI agent.

description

string

example: This is ASK AgentThe description of the AI agent.

suggested_questions

stringarray

example: ["What is in this file?","What are the main highlights of this document?"]Suggested questions for the AI agent. If null, suggested question will be generated. If empty, no suggested questions will be displayed.

{
  "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"
  },
  "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?"
  ]
}