Getting Started with LangGraph
Building multi-agents application with graph frameworks
Over the last year, LangChain has established itself as one of the most popular AI framework available in the market. This lightweight orchestrator helps developer build LLMs-powered applications with all their related components — vectorDB, memory, prompts, tools and agents. The main feature of LangChain — as the name suggests — is its ability to easily create the so-called chains. A chain is a sequence of components that work together to process user’s input and output using an LLM. A chain can be composed of different types of components, such as prompts, retrievers, processors, and tools. A chain can also be nested within another chain to create more complex applications.
Nevertheless, those chains were lacking the capability of introducing cycles into their runtime, meaning that there is no out-of-the-box framework to enable the LLM to reason over the next best action in a kind of for-loop scenario. Since the concept of multi-agent applications — the ones exhibiting different agents, each having a specific personality and tools to access — is getting real and mainstream (see the rise of libraries projects like AutoGen), LangChain’s developers introduced a new library to make it easier to manage these kind of agentic applications. This new library, introduced in January…