hey! Once I finish the "Agentic patterns from scratch" series yes! that's what I had in mind - Medium Posts + UA-cam Videos about production-ready RecSys 😃
Hey! So previously I was taking into account the whole history of messages. Problem? You may end up with too many tokens for the LLM window. What I did at the end was to limit the chat history to just two messages (the previous reflection and generation completions), and the results were very similar (and much faster).
In my ReAct multiple agent system, the time it takes to obtain the final answer using tools can be quite long, leading to a poor user experience. In your system, how long does the process of calling the choose tool -> execute tool -> get final answer take in each round,, and how many times does the LLM (Large Language Model) need to be called?
It depends on the task, if you go to the third video of the series, you'll see the ReAct agent I implemented from scratch, using three tools. The problem it has to solve is very simple, but maybe it will give you an overall idea of the time it takes.
Great explanation, thank you
thanks! 🙏
Great Explanation! Welldone.
Glad you liked it!
Amazing and thanks for sharing this
Anytime! Thanks for the kind words 😍 I'm already working on the second episode! 🦾
🚀
🔥🔥🔥
Hey Miguel, can you please create a tutorial on production ready recommender system?
hey! Once I finish the "Agentic patterns from scratch" series yes! that's what I had in mind - Medium Posts + UA-cam Videos about production-ready RecSys 😃
Great content, thank you!
Question for you, what tool did you use to draw your diagrams, those are rich and love the fonts you used.
thanks!! It's Excalidraw 🙂
When you loop on (generate then reflect), you basically are not taking into account the last reflection (critique) of last loop, no?
Hey! So previously I was taking into account the whole history of messages. Problem? You may end up with too many tokens for the LLM window. What I did at the end was to limit the chat history to just two messages (the previous reflection and generation completions), and the results were very similar (and much faster).
In my ReAct multiple agent system, the time it takes to obtain the final answer using tools can be quite long, leading to a poor user experience. In your system, how long does the process of calling the choose tool -> execute tool -> get final answer take in each round,, and how many times does the LLM (Large Language Model) need to be called?
It depends on the task, if you go to the third video of the series, you'll see the ReAct agent I implemented from scratch, using three tools. The problem it has to solve is very simple, but maybe it will give you an overall idea of the time it takes.