Let's build an LLM agent in Python, step-by-step โ๐งต

Because Large Language Models alone are not enough to accurately answer complex tasks that require
-> External information that was not present in the training dataset used to fit the LLM paramaters
or
-> Many reasoning steps
"Create a plot with Python of the number of games won by the Golden State Warriors in each of the last 2 NBA seasons."
The response you get is
โ A tool to retrieve external data needed for the task
and
โ The reasoning capabilities to decide when and how to use the tool, to answer the user query.
And this is what agents are all about.
All the source code is in this repository โโโ
github.com/Paulescu/plot-โฆ
This step is super-simple thanks to a library like @langchain, which provides an implementation of the ReAct agent logic.
react-lm.github.io
Moving from agent prototypes to production-ready agents is all about polishing rough edges, and ensuring the agent has access to the right tools.
๐๐๐ฒ๐ฟ๐ ๐ฆ๐ฎ๐๐๐ฟ๐ฑ๐ฎ๐ you will get an email with hands-on content to build real-world ML apps.
โโโ
paulabartabajo.substack.com







