Skip to main content

​
mellea.backends.formatter

Abstract interfaces for Formatters.

​
Classes

​
Formatter

A Formatter converts Components into strings and parses ModelOutputThunks into Components (or CBlocks). Methods:

​
print

print(self, c: Component | CBlock) -> str
Renders a component for input to a model.

​
parse

parse(self, source_component: Component | CBlock, result: ModelOutputThunk) -> ModelOutputThunk
Parses the output from a model and sets the parsed_repr of the result ModelOutputThunk. Returns the ModelOutputThunk that was passed in.

​
to_chat_messages

to_chat_messages(self, cs: list[Component | CBlock]) -> list[Message]
Helper method that converts a linearized chat history into a list of messages. The purpose of this helper is to prepare a sequence of Messages for input to a chat endpoint.

​
TemplateFormatter

Formatter that uses jinja2 templates. Methods:

​
parse

parse(self, source_component: Component | CBlock, result: ModelOutputThunk) -> ModelOutputThunk
Parses the output and updates the result’s parsed_repr. 
print(self, c: Component | CBlock) -> str
Uses a jinja2 template to pretty-print components.

​
FormatterBackend

FormatterBackends support legacy model types. The mellea library was designed to support generative computing with spanned attention over generative programming primitives. In the ideal world, context management is handled via span scope-relations and all generative programming primitives are baked into the model via fine-tuning. I.e., the model’s instruction tuning is done in terms of generative programming primitives, and the model is then prompted with the same set of templates that were used for that tuning. Today, most models do not yet support spans and even those that do are not properly tuned to leverage generative programming primitives. The mellea library supports these legacy models primarily through prompt engineering surfaced via FormatterBackends. A FormatterBackend is a backend that uses hand-engineered prompts for rendering generative programming primitives to a model and parsing responses from the model back into mellea. By default, a FormatterBackend uses jinja2 templates for pretty-printing, and relies on the user’s ad-hoc logic for parsing.
⌘I