💭 About

How many times did someone ask you :

"How do you..."

... and how many times did you make the RTFM (Read the f**king Manual) joke ?

👉 Well that's all this blog post is all about, we're going to:

1. 🎁 Provide a cli tool that behaves like all other tools to an AI assistant
2. 🦥 Ask it to learn by himself how to use it
3. 🚀 Make it do the job ... locally !

To achieve this we will use :

• 🤖 A core LLM engine : gpt-4
• 💻 A locally running assistant that is able to create an action plan to achieve a goal : Open Interpreter

🎯 What we'll do

This time, thanks to a custom tool I created last week-end :

⏱️ Mobitag Go Hackathon 2024-06-22 week-end 🤓

adriens ・ Jun 23

and ask the AI Assistant to discover the tool and send a custom sms with a custom content to myself with it.

🧑‍🏫 Teach him how to use the tool

🤣 Funniest sms

🔭 Perspectives

The same way we used the --help pattern for cli tool, we can use the OpenAPI to tell an AI how to use an API as a tool.
But keep in mind : the better the documentation, the easier and better integration will be... at almost 0 effort (which is our target to scale automation).

Below some examples of how to achieve this on various frameworks & services :

🤓 For coders :

• 🦙 LlamaIndex : OpenAPI Tool
• 🦜 Langchain : OpenAPI tool

⏱️ < 5' demo : build & deploy conversational agents (non-coders)

Least but not last, for non coders Google Vertex AI Agent Builder to build and deploy Agents ... within 5 minutes :