2 Repos
Metadata attached to schemas to influence LLM generation behavior.
Distinct from Schema Metadata Annotations: Distinct from database schema metadata: specifically targets modifiers that control how an AI model handles specific values.
Explore 2 awesome GitHub repositories matching data & databases · Model Behavioral Annotations. Refine with filters or upvote what's useful.
Epoxy is an Android library for building complex RecyclerView screens using a model-driven approach. It generates RecyclerView adapter models at compile time from annotated custom views, data binding layouts, or view holders, eliminating the manual boilerplate typically associated with view holders and adapters. The library provides a diffing engine that automatically compares model lists and applies minimal updates with animations for insertions, removals, and moves. The library distinguishes itself through its controller-based model building, where a controller class with a buildModels meth
Creates RecyclerView models using Kotlin data classes and property delegates without annotation processing.
BAML is a prompt engineering framework and LLM client generator that defines AI prompts as type-safe functions. It serves as a structured data extraction tool and workflow orchestrator, transforming unstructured model responses into strongly typed objects using a custom schema language and alignment algorithms. The project distinguishes itself by using a compiler to generate language-specific boilerplate code for API communication and output parsing. It features a dedicated environment for designing complex prompt templates with conditional logic and reusable snippets, and employs genetic alg
Attaches metadata or behavioral modifiers to fields to control how the AI model processes specific values.