Structured Data Python Packages

partial-json-parser

Parse partial JSON generated by LLM

baml-py

The programming language for agents

langextract

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

autogluon-core

Fast and Accurate ML in 3 Lines of Code

autogluon-features

Fast and Accurate ML in 3 Lines of Code

autogluon-tabular

Fast and Accurate ML in 3 Lines of Code

streamlit-pdf-viewer

Streamlit PDF viewer

autogluon-common

Fast and Accurate ML in 3 Lines of Code

autogluon-timeseries

Fast and Accurate ML in 3 Lines of Code

autogluon

Fast and Accurate ML in 3 Lines of Code

autogluon-multimodal

Fast and Accurate ML in 3 Lines of Code

context-dev

Context.dev Python SDK: scrape any URL to LLM-ready markdown, crawl sites, search the web and extract structured JSON with one API key.

autogluon-text

Fast and Accurate ML in 3 Lines of Code

autogluon-vision

Fast and Accurate ML in 3 Lines of Code

autogluon-cloud

Train and deploy ML models in the cloud

gcf-python

GCF Python implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

relbench

RelBench: Relational Deep Learning Benchmark

autogluon-extra

Fast and Accurate ML in 3 Lines of Code

autogluon-mxnet

Fast and Accurate ML in 3 Lines of Code

exstruct

Conversion from Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines, and autonomous Excel reading/writing by AI agents via CLI and MCP integration.

schemarouter

Typed capability routing and governed execution for AI agents across APIs, tools, and data systems.

scovant-core

Open-source, evidence-first scanner for passive AI agent readiness signals on websites.

autogluon-eda

Fast and Accurate ML in 3 Lines of Code

sluicer

Turn any web page, or a whole site, into structured data, with no model in the loop: every record a page declares with where each value came from, fields learnt from one example and checked on every page, crawls, feeds and archives.