Building LLM Agents with Tool Use

Tool use is a method whichs allows developers to connect Cohere's Command models to external tools like search engines, APIs, databases, and other software tools. Just like how Retrieval-Augmented Generation (RAG) allows a model to use an external data source to improve factual generation, tool use is a capability that allows retrieving data from multiple sources. But it goes beyond simply retrieving information and is able to use software tools to execute code, or even create entries in a CRM system.

In this video, we'll see how we can use two tools to create a simple data analyst agent that is able to search the web and run code in a python interpreter. This agent uses Cohere's Command R+ mode and Langchain.

Find the code here at Colab:

[mailmahee]

Fantastic, thanks for the explanation Jay! Relevant for several use-cases...

[RakeshGupta-ftcc]

Does the agent use an LLM to determine the steps? Can you cover these internal details?

[SerranoAcademy]

Great video on LLM tool use, thanks Jay!

[connor-shorten]

Love this explanation! Incredible work as always!

[abdeljalilelmajjodi]

thank you Jay for this beautiful explanation

[sanesanyo]

Hi Jay, great video. What if the user wants to also provide his/her own data and ask questions related to that, which might also require outside world knowledge (this web search as a tool might still be useful)?

[moabdelmoez]

@Jay, Thank you for the explanation. I found the Colab link is not working, Can you share the updated link, please?

[liorbalmas]

Can Tools work only with Langchain?
If not, a more general example would be nice..

[mehmetbakideniz]

would be better if you could explain the code line by line instead of just mentioning briefly what they are doing. Great video otherwise. I learn alot from your videos.