A model-agnostic Ruby Generative AI DSL and framework. Provides base classes for building Generators, Actions, Tasks, and Agents that can be used to build AI powered applications in Ruby.
New output adapter to return an object with named string attributes. This is useful for when you want to extract a few different types of strings from a text or want to construct an object based on a prompt.
For example, say you have a product with some attributes and you want to generate a short description, long description, key features, and target audience. Or have a blog post and want to extract the key ideas, major points, summary, and followup questions.
As part of this change we've also introduced some post-processing for results where you can optionally add materialize_result(raw_results) to your output_adapter and return a better formatted object or attribute to your generator.
swerner
commented
2 months ago
New output adapter to return an object with named string attributes. This is useful for when you want to extract a few different types of strings from a text or want to construct an object based on a prompt.
For example, say you have a product with some attributes and you want to generate a short description, long description, key features, and target audience. Or have a blog post and want to extract the key ideas, major points, summary, and followup questions.
As part of this change we've also introduced some post-processing for results where you can optionally add
materialize_result(raw_results)to your output_adapter and return a better formatted object or attribute to your generator.