4 repository-uri
Awesome GitHub RepositoriesLLM Structured Output Generators
Produces validated Pydantic model instances from natural language descriptions using LLM inference.
Distinct from Type-Safe Code Generators: Distinct from Type-Safe Code Generators: generates structured data models from natural language via LLM, not from interface definition files.
Explore 4 awesome GitHub repositories matching software engineering & architecture · LLM Structured Output Generators. Refine with filters or upvote what's useful.
Awesome LLM Structured Output Generators GitHub Repositories
Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
- strands-agents/sdk-python
strands-agents/sdk-python
6,176Vezi pe GitHubThis is an open-source Python SDK for building and orchestrating production-grade AI agents. It provides a unified framework for creating conversational agents that can use tools, maintain state, and coordinate across multiple language model providers including OpenAI, Anthropic, Google, Amazon Bedrock, and locally-hosted models. The SDK supports multi-agent orchestration through graphs, teams, and swarms, allowing several specialized agents to collaborate on complex tasks. Agents can be composed as callable tools that other agents invoke, and the framework includes policy handlers that inspe
Produces validated, schema-conforming responses using Pydantic models and native tool calling.
Python - prefecthq/marvin
PrefectHQ/marvin
6,170Vezi pe GitHuban ambient intelligence library
Produces validated Pydantic model instances from natural language descriptions using LLM inference.
Python - samchon/typia
samchon/typia
5,837Vezi pe GitHubTypia is a compile-time code generator that transforms TypeScript type annotations into runtime validation, serialization, and schema functions without requiring decorators or separate schema files. It generates optimized validation and serialization code during TypeScript compilation, producing dedicated functions for each type that eliminate runtime schema objects for faster execution. The project extends this core capability into several integrated areas. It generates fully typed client SDKs from NestJS controller source code, keeping server and client types synchronized automatically. It
Generates a bundled JSON schema, parser, coercer, and validator for LLM structured output requests.
Go - 1rgs/jsonformer
1rgs/jsonformer
4,930Vezi pe GitHubJsonformer este un generator de text constrâns și un enforcer de schemă care forțează modelele de limbaj să producă JSON sintactic corect. Acesta acționează ca un validator și formator, asigurându-se că output-ul unui model AI respectă strict o schemă structurală predefinită. Sistemul realizează acest lucru prin restricționarea token-urilor pe care un model de limbaj le poate genera și inserarea de caractere structurale fixe în fluxul de output. Acest proces garantează că datele rezultate respectă schema JSON specificată pentru o integrare programatică fiabilă. Proiectul acoperă capabilități largi în constrângerea output-ului, generarea de JSON structurat și crearea de interfețe fiabile între modelele de limbaj și software.
Transforms raw language model generation into structured JSON by inserting fixed tokens and restricting content.
Jupyter Notebook
