Join BoxWorks 2024 to discover what's possible with content and AI!

AI agent for extract requests

The AI agent to be used for extraction.

type string

exampleai_agent_extract

The type of AI agent to be used for extraction.

Value is always ai_agent_extract

basic_text object

AI agent tool used to handle basic text.

basic_text.llm_endpoint_params AI LLM endpoint params Google / AI LLM endpoint params OpenAI / AI LLM endpoint params AWS object

The parameters for the LLM endpoint specific to OpenAI / Google models.

basic_text.model string

exampleazure__openai__gpt_3_5_turbo_16k

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

basic_text.num_tokens_for_completion integer

example8400min1

The number of tokens for completion.

basic_text.prompt_template string

pattern(\{user_question\}[\s\S]*?\{content\}|\{content\}[\s\S]*?\{user_question\})exampleIt is `{current_date}`, consider these travel options `{content}` and answer the `{user_question}`.max length10000

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_text.system_message string

exampleYou are a helpful travel assistant specialized in budget travel

System messages try to help the LLM "understand" its role and what it is supposed to do.

long_text object

AI agent tool used to to handle longer text.

long_text.embeddings object

embeddings.model string

exampleopenai__text_embedding_ada_002

The model used for the AI agent for calculating embeddings.

embeddings.strategy object

strategy.id string

examplebasic

The strategy used for the AI agent for calculating embeddings.

strategy.num_tokens_per_chunk integer

example64min1

The number of tokens per chunk.

long_text.llm_endpoint_params AI LLM endpoint params Google / AI LLM endpoint params OpenAI / AI LLM endpoint params AWS object

The parameters for the LLM endpoint specific to OpenAI / Google models.

long_text.model string

exampleazure__openai__gpt_3_5_turbo_16k

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

long_text.num_tokens_for_completion integer

example8400min1

The number of tokens for completion.

long_text.prompt_template string

long_text.system_message string

exampleYou are a helpful travel assistant specialized in budget travel

System messages try to help the LLM "understand" its role and what it is supposed to do.

Response Example

{
  "type": "ai_agent_extract",
  "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_3_5_turbo_16k",
    "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": "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_3_5_turbo_16k",
    "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"
  }
}