Andrew Ng, announced a new generative AI course on LangChain in the series collaborating with Harrison Chase, founder of LangChain.  

Titled ‘Functions, Tools, and Agents with LangChain,’ developers can update themselves on the fast paced world of LLM and how to use LangChain to work with their models. 

In the earlier courses they explained how to use LangChain to chat and manipulate the data. “In the short time since we created those courses, there have been significant advancements in LLMs and the libraries to support the use as a developer tool,” Andrew Ng said. 

This course was created to update developers on function calling such as OpenAI’s LLM’s calling of other functions, which turns out to be very useful for handling structured data.

While the majority of work is done using formatted data, with function calls or API’s that want specific data in specific formats. The recent updates to training algorithms can now understand and output data like JSON, and in this course, students will get a chance to work with this directly. 

These updates make LLMs more predictable and reliable, as well as being better at understanding when to use tools. This makes it more feasible to build agents that can reason about how to use tools to solve multi step problems. 

Harrison Chase who explained the format of the course said, “In this course, we’ll start by explaining the recent advancements in LLM APIs. Next we’ll go over a new syntax that we at LangChain have introduced called LangChain Expression Language (LCEL) which makes it much easier to compose and customise chains and agents.” 

Students of the course will also explore the popular use cases, like structured data extraction, function calling and building up to a conversational agent. To register for the course you can follow this link. 

Simultaneously, Andrew Ng also announced a course to build Computer Vision models which will be livestreamed on the 6th of November. 

Read: Andrew Ng other courses