Structured Text Generation

Resource list for generating JSON using LLMs via function calling, tools, CFG. Libraries, Models, Notebooks, etc.

BAML is a language that helps you get structured data from LLMs, with the best DX possible. Works with all languages. Check out the promptfiddle.com playground

Efficient, Flexible and Portable Structured Generation

Experimental Code for StructuredRAG: Structured Outputs in Retrieval-Augmented Generation

Query language for blending SQL logic and LLM reasoning across structured + unstructured data. [Findings of ACL 2024]

Extract structured data from local or remote LLM models

TensorRT-LLM server with Structured Outputs (JSON) built with Rust

Structured Generation Evals

A guide to structured generation using constrained decoding

Speculative grammar backtracking algorithm for LLM decoding conforming to some lark context-free grammar (CFG)

Word alignment of multilingual sentences using structured generation

Mistral AI Fine-tuning Hackathon

A gentle tutorial on structured generation using Anthropic and Pydantic

Examples of code that use Outlines to enable structured text generation for LLMs running on Modal

A fiction machine inspired by Borges

Progressively extracts structured information from multi-turn user chats using pydantic schemas and LLMs