LangGraph has introduced a Functional API for its platform, now available in Python and JavaScript. This API simplifies the incorporation of features like human-in-the-loop, persistence/memory, and streaming into AI workflows without restructuring existing code. It uses decorators like `entrypoint` and `task` to define workflows and supports both short-term and long-term memory management. The Functional API and Graph API can be mixed within the same project, and built-in observability features help monitor and debug workflows.
Table of contents
Building BlocksHuman-in-the-LoopShort-term memoryLong-term memoryStreamingObservabilityDeploymentGraph API vs. Functional APIConclusionSort: