Skip to main content

Helpers for LLM Interactions

Class for representing a prompt entry.

BasePrompt​

class BasePrompt()

Base class for representing an LLM prompt.

__init__​

def __init__(source: str,
             output_schema: Optional[str] = None,
             *,
             xml_output_schema: Optional[str] = None)

Initialize and substitute constants in the prompt.

substitute_constants​

def substitute_constants(text: str) -> str

Substitute constants in the prompt.

get_prompt_variables​

def get_prompt_variables() -> List[str]

format​

def format(**kwargs) -> "BasePrompt"

escape​

def escape() -> str

Escape single curly braces into double curly braces.

The LLM prompt.

Prompt​

class Prompt(BasePrompt)

Prompt class.

The prompt is passed to the LLM as primary instructions.

format​

def format(**kwargs) -> "Prompt"

Format the prompt using the given keyword arguments.

Instructions to the LLM, to be passed in the prompt.

Instructions​

class Instructions(BasePrompt)

Instructions class.

The instructions are passed to the LLM as secondary input. Different model may use these differently. For example, chat models may receive instructions in the system-prompt.

format​

def format(**kwargs) -> "Instructions"

Format the prompt using the given keyword arguments.

PromptCallableBase​

LLMResponse​

class LLMResponse(ILLMResponse)

Standard information collection from LLM responses to feed the validation loop.

Attributes:

  • output str - The output from the LLM.
  • stream_output Optional[Iterator] - A stream of output from the LLM. Default None.
  • async_stream_output Optional[AsyncIterator] - An async stream of output from the LLM. Default None.
  • prompt_token_count Optional[int] - The number of tokens in the prompt. Default None.
  • response_token_count Optional[int] - The number of tokens in the response. Default None.