# Jambo

A Python package that converts JSON Schema definitions into Pydantic models automatically, built to simplify generating typed models for AI frameworks such as LangChain and CrewAI.

Jambo turns a JSON Schema document into a working Pydantic model with one function call, handling strings, numbers, booleans, arrays, nested objects, and schema composition keywords such as allOf, anyOf, oneOf, ref, enum and const, along with constraints like minimum, maximum, length and pattern. It requires no configuration beyond the schema itself.

Two APIs are available: a static build call that does not persist any reference cache between calls, and an instance-based API that keeps a reference cache across calls, useful for reusing generated subtypes, inspecting cached models, or sharing a cache between converters through a schema's id property.

It is a Python package installed with pip, under the MIT license.

Website: https://jambo.readthedocs.io/