Loading video player...
We’re releasing a new LangChain Academy course,
LangChain Essentials, where you can learn the basics of LangChain in an hour.
LangChain is the best way to get started with generative AI. LangChain has had
pre-built agents from very early in its development. Together with the community,
we’ve learned from production use-cases and identified the essential components
an agent needs. The `create_agent` abstraction captures these qualities in their simplest form.
In this course, you’ll learn to build agents with the create_agent abstraction. The pre-built
agent is a ReAct-style agent, where the LLM reasons and then acts using tools, in a loop.
This architecture has proven to be both simple and powerful. We wanted the agent to be easily
scalable and resilient in the event of failures, while also allowing for a human-in-the-loop in
situations where you’d want human intervention. To achieve this, we built on top of LangGraph.
A challenge in building any abstraction is balancing flexibility with the benefits of being a
pre-built abstraction. This agent can dynamically select prompts and models, while optional
middleware enables customization only when you need it—using pre-built or custom implementations.
In the course, you’ll learn to use many features of the
create_agent abstraction as you build an increasingly sophisticated agent.
You’ll also use many of the building blocks in LangChain, including messages, tools,
and models. I hope that you can take the time to learn more about LangChain in this course.
In our newest LangChain Academy course, LangChain Essentials, you can learn the basics of LangChain in less than an hour in either Python or TypeScript. LangChain is the best way to get started with generative AI. LangChain has had pre-built agents from very early in its development. Together with the community, we’ve learned from production use-cases and identified the essential components an agent needs. The `create_agent` abstraction captures these qualities in their simplest form. In the course, you’ll learn to use many features of the create_agent abstraction as you build an increasingly sophisticated agent. You’ll also use many of the building blocks in LangChain, including messages, tools, and models. Enroll for free: https://bit.ly/4howDno Learn more about LangChain: https://bit.ly/3L1cjfG