87 Repos
Structured data modeling for request and response validation.
Distinguishing note: Focuses on the schema-based modeling aspect rather than the broader API contract.
Explore 87 awesome GitHub repositories matching data & databases · JSON Schema Modeling. Refine with filters or upvote what's useful.
This repository is a collection of guides, notebooks, and recipes for implementing advanced prompting techniques and workflow patterns with large language models. It serves as a prompt engineering guide, an evaluation suite for scoring prompt quality, and a framework for orchestrating agents and integrating external tools. The project provides implementation patterns for building applications with Claude, specifically focusing on coordinating multiple models to split complex tasks between high-reasoning and high-efficiency agents. It includes technical demonstrations for multimodal data proce
Forces model responses to conform to a provided JSON schema using prompt engineering for programmatic compatibility.
jsoncrack.com is a JSON data visualization tool and interactive graph viewer that transforms JSON and other structured data formats into visual tree diagrams. It functions as a data syntax validator and a structured data converter for transforming information between JSON, YAML, XML, and CSV formats. The project includes a JSON schema generator that produces schema definitions and language-specific type definitions based on provided structured data. These capabilities automate type safety and ensure data integrity through schema generation. The tool provides broader capabilities for structur
Generates and validates schema definitions based on structured data to ensure consistency.
The OpenAPI Specification is a formal, vendor-neutral standard for defining the structure, endpoints, and data models of HTTP-based web services. By providing a machine-readable interface definition language, it enables developers to establish clear API contracts that ensure consistency across diverse programming languages and backend systems. This specification promotes a design-first development approach, where interface behavior is defined through static, declarative configuration files rather than imperative code. This structure allows for the automated generation of type-safe client libr
Uses structured data formats to define API request and response shapes for automated validation.
ReDoc is an OpenAPI documentation generator that transforms OpenAPI and Swagger specifications into interactive, three-panel API reference websites. It provides a system for generating these references as standalone static HTML files or as embedded UI components for integration into existing websites and developer portals. The tool organizes API specifications into a responsive layout featuring a navigation sidebar, detailed endpoint descriptions, and language-specific code samples. It supports the visualization of complex data models by mapping schema definitions to human-readable tables and
Transforms OpenAPI schema definitions into human-readable tables and nested object trees for data model visualization.
gbrain is an agent framework and retrieval-augmented generation system that combines a durable task queue, a git-synced vector store, and a knowledge graph engine. It provides a foundation for building AI agents that interact with structured knowledge bases using the Model Context Protocol. The system synchronizes markdown files from a git repository into a database for high-performance semantic retrieval and creates typed edges between data pages by extracting entity references and wikilinks. It uses a database-backed queue to execute persistent background jobs and tool loops, ensuring relia
Defines data types and taxonomies based on the physical structure of the underlying file system.
RapidJSON is a high-performance C++ library used for parsing and generating JSON data. It provides both document object model and stream-based interfaces to transform JSON strings into structured data and vice versa. The library includes a JSON schema validator to verify that documents conform to predefined rules and a Unicode transcoder for converting strings between UTF-8, UTF-16, and UTF-32 encodings. It also supports relaxed parsing for non-standard JSON containing comments or trailing commas. Additional capabilities cover JSON pointer navigation for locating specific values and string s
Provides a schema validator to ensure JSON documents conform to predefined structural rules.
OpenMetadata is an enterprise data catalog, metadata platform, and governance suite that functions as a knowledge graph for data assets. It serves as an AI-ready metadata layer, providing governed context and organizational memory to large language model agents via the Model Context Protocol. The platform distinguishes itself by capturing institutional knowledge, linking conversations, decisions, and remediation notes directly to data assets to preserve tribal knowledge. It integrates AI agents to automate metadata governance, such as suggesting descriptions and identifying sensitive data thr
Defines machine-readable asset structures and ontologies using JSON schemas to ensure metadata interoperability.
Outlines is a guided text generation framework and structured output engine for large language models. It enforces precise structural constraints on model output during the sampling process to ensure the generation of valid data. The framework ensures that model outputs strictly adhere to predefined data models, including JSON schemas, regular expressions, and formal grammars. This enables the conversion of natural language inputs into structured arguments for function calling and the generation of valid JSON for downstream processing. The system manages model orchestration through prompt te
Produces outputs that strictly adhere to schemas or data models to ensure consistency for downstream processing.
Outlines is a guided generation framework designed to enforce structural constraints on large language model output in real time. It serves as a structured output generator that ensures model responses adhere to predefined JSON schemas, regular expressions, or fixed sets of choices to produce predictable and parsable results. The project provides an interface for tool calling by extracting structured function parameters from natural language prompts for programmatic execution. It also includes a prompt templating engine that decouples prompt logic from application code through reusable templa
Forces large language models to generate valid JSON that adheres to a predefined schema.
Quicktype is a multi-language serialization tool and type generator. It converts JSON samples, JSON Schema definitions, and GraphQL schemas into strongly typed data structures and serialization logic across multiple programming languages. The system automates the data serialization workflow by generating boilerplate code to parse and serialize data. It transforms structured input definitions into executable code, providing the necessary encoders and decoders to move data between raw formats and typed objects.
Automatically generates formal schemas by analyzing the structure of provided sample JSON data.
Quicktype is a multi-language model generation engine that converts JSON and GraphQL schemas into type-safe models and serialization code. It functions as a JSON to type generator and a GraphQL type generator, producing strongly typed classes and interfaces across a wide array of target programming languages. The system derives formal schemas from sample data and transforms these definitions into native language objects. This enables the synchronization of shared data models across diverse tech stacks and the development of type-safe interfaces for consuming external APIs. The engine utilize
Derives formal JSON schemas from sample data to enable consistent code generation.
Kratos is a centralized identity and access management server designed to handle user registration, authentication, and profile management. It functions as an identity flow orchestrator, managing the state and security of authentication processes across web, mobile, and command-line interfaces. The system provides a standards-compliant authorization server that issues tokens and manages delegated access for third-party applications and internal services, supporting multi-factor authentication and custom identity schemas to secure user accounts. The project distinguishes itself through a headl
Enforces data validation and consistency for user identity structures using standard schema files.
Instructor is a schema enforcement and validation library designed to transform language model outputs into structured, type-safe data formats. It functions as a validation layer that uses Pydantic to ensure model responses conform to specific data models, acting as a tool for forcing large language models to return data in predefined schemas. The project differentiates itself through a recursive error-feedback loop that automatically retries requests when structural errors occur, passing validation failure messages back to the model to guide corrections. It also includes a streaming parser c
Injects JSON schema instructions into prompts to constrain the model's output format.
jsoneditor is a web-based JSON editor component designed for viewing, editing, and formatting structured data. It provides a user interface for managing JSON through multiple rendering modes, including tree, form, and code views. The project is distinguished by its ability to process and visualize exceptionally large datasets, utilizing virtualized memory management to handle JSON files up to 500 MiB without crashing the browser. It also includes a specialized syntax repair tool to convert malformed text into valid JSON and a data transformer for filtering, sorting, and reshaping documents vi
Verifies that JSON documents adhere to predefined schema rules and provides inline metadata tooltips.
class-validator is a TypeScript class validation library that uses decorators to define constraints and rules for object properties. It functions as a decorator-based schema validator that ensures data integrity and structural correctness through a combination of synchronous checks and promise-based asynchronous rules. The library provides a recursive validation system for checking complex data hierarchies, including nested classes and individual elements within collections. It includes an object property whitelist utility capable of stripping undocumented properties or blocking unknown field
Assigns decorators to specific groups to apply different validation schemas to the same object in different contexts.
Ludwig is a multimodal machine learning platform and low-code framework designed for building, training, and deploying neural networks. It enables the construction of models that process text, images, audio, and tabular data through a unified interface using declarative configuration files rather than custom code. The system features a specialized low-code framework for large language models, supporting supervised fine-tuning, preference alignment, and a constrained decoding tool to force structured data output via logit extraction. It also includes an automated model architecture search to i
Forces language model outputs into specific formats by masking invalid tokens during the sampling process at inference time.
This project provides the core framework and system API layer for the Android operating system. It consists of the fundamental Java and C++ libraries that define system behavior and establish the interface contracts required for system applications and hardware abstraction. The project includes a runtime optimizer used to reduce startup time and improve execution speed by pre-compiling methods and configuring boot images. It also features a software quality toolchain that enforces code formatting, audits commit metadata, and manages API compatibility to ensure stable interface contracts acros
Validates interface compatibility and enforces stable API contracts to ensure consistent system behavior across versions.
Magentic-UI is an agentic UI toolkit and framework that enables large language models to interface with real-time browser environments, operating systems, and virtual machines. It provides a sandbox environment where models can execute instructions to manage local files and run shell commands. The project functions as a web interaction orchestrator and browser automation framework, allowing for the execution of end-to-end web workflows and form completions. It coordinates these actions through a system that translates natural language goals into executable sequences. The toolkit covers sever
Uses structured JSON schemas to define tool capabilities and validate the arguments passed by the model.
HackMyResume is a command-line tool that generates polished résumés and CVs in multiple formats from a single JSON or YAML data source. It validates résumé documents against the FRESH or JSON Resume schema, converts between these two formats, and produces output in HTML, Markdown, LaTeX, MS Word, PDF, plain text, JSON, XML, and YAML. The tool supports custom themes through a plugin architecture, allowing users to apply visual styling via Handlebars templates and register custom helpers for extended template logic. It can merge multiple résumé JSON files into one, overriding generic data with
Validates résumé documents against the FRESH or JSON Resume schema for completeness and correctness.
This project is a comprehensive productivity guide and configuration reference for the VS Code editor. It provides a curated collection of shortcuts, configuration tips, and tutorials designed to improve efficiency and optimize the daily coding workflow. The resource covers advanced AI-assisted development, including the integration of autonomous agents, custom prompt files, and AI-powered coding assistants for task automation and code generation. It also provides specialized guidance on integrated terminal management, such as configuring shell profiles and automating command execution. Addi
Provides guidance on verifying JSON values against schemas for real-time error highlighting.