This is super cool, another good framework to try & explore. Thanks for sharing. Your explanation is clear and to the point especially not wasting time by typing the code.
I am glad you find it exciting, too! It’s basically one of the most exciting frameworks to come out in 2024. it’s so cool to see a trend towards simplicity. In my opinion, frameworks will shift from DSLs to idiomatic language constructs. And Pydantic is leading the way. Thanks for chiming in 😁👍🎄🎁
@@AngusLou Great question. While not an expert, I can share from experience that CrewAI is more established and it uses domain-specific structures to build and configure agents. PydanticAI is newer and it relies on idiomatic Python code, aiming to simplify the agent management process. Perhaps others, with more experience, can also chime in.
Thanks for the support. More complicated demos are on the way. As an introduction, I wanted to keep it simple and show how easy it is to create an agent. 🕵️♂️
Thanks, they are coming online as soon as the coding exercise are complete and fully tested. Thanks for the nudge. Happy new 2025 - may this year be the year of learning 😁🎁🎄
@@AIwithsameer-y6l no, PydanticAI can be used with any model that supports agents, including the open source Llama 🦙 models. If you want to use OpenAI model, only then you’ll need a paid plan.
Hi This is great but i hope this is your first but not the last video. I hope to see how to use tools which is the crux of any AgenticAI framework. I went through the code but i am stuck at how to register tool(python function) with the Agent. It use a class called RunContext. I am not really getting the code.
There will be more videos, including tools. I have all the code examples ready, it’s just a matter of recording, editing and posting. Please stay tuned and thank you for the support!
Thank you so much for this amazing video! Just a quick off-topic question: I have a SafePal wallet with USDT, and I have the seed phrase. (alarm fetch churn bridge exercise tape speak race clerk couch crater letter). What's the best way to send them to Binance?
Many corporate users use Azure-based OpenAI APIs as a way to control access, costs and privacy. I used it as an example of an OpenAI-compatible model passed as a client to PydanticAI. Any other model will do just as fine. Thank you for your comment! 👍
This has nothing to do with agents lol, this is completely normal, sequential, and explicit calling of wrappers of random LLMs. This is what langchain was doing 3 years ago
Ha! Exactly as you said- PydanticAI uses plain Python, making it look like just a wrapper. Stay tuned for future videos where I’ll show how to customise the system prompts, add tools and agent memory. Then, the power of this simple, yet powerful framework will become more visible. Thanks for the comment. Ciao! 😁🎁🎄
Well done and right to the points, thanks
Thank you for the comment. I am glad you found the content useful.
This is super cool, another good framework to try & explore. Thanks for sharing.
Your explanation is clear and to the point especially not wasting time by typing the code.
Hey, thanks for the feedback. I will try to stick to this format, if it helps get the points through easier.
This was well done. Thank you! Standing by for future PydanticAI tutorials from you, please and thank you!
@@MajesticGeek Roger that! Will do my best to get them out in a relatively accelerated schedule 🤞🎄🎁
I like that you start with the simple examples and get more robust. Well organized, valuable content. Thanks! Subscribed!
Thank you for the support. I am glad you found the content helpful. 😄
Exciting! Thanks for the tutorial.
I am glad you find it exciting, too! It’s basically one of the most exciting frameworks to come out in 2024. it’s so cool to see a trend towards simplicity. In my opinion, frameworks will shift from DSLs to idiomatic language constructs. And Pydantic is leading the way. Thanks for chiming in 😁👍🎄🎁
Deserves subscription. Done.
Thank you for the support. I am glad you found the content helpful. Cheers, mate! 😄
thank you so much, it's a very clear explanation.
I am glad you found the content useful. Happy 2025 and may this year be the year of learning 😁🎁🎄
Oh, very interesting, thanks! subscribed!
Thanks for the sub!
Great intro. More videos on pydantic ai agents please.
Definitely! A good framework deserves more videos 😁
Thanks for the video. One quick question, what are the pros and cons for Pydantic and CrewAI agent framework?
@@AngusLou Great question. While not an expert, I can share from experience that CrewAI is more established and it uses domain-specific structures to build and configure agents. PydanticAI is newer and it relies on idiomatic Python code, aiming to simplify the agent management process. Perhaps others, with more experience, can also chime in.
Extremely simple demo
Thanks for the support. More complicated demos are on the way. As an introduction, I wanted to keep it simple and show how easy it is to create an agent. 🕵️♂️
Two videos in playlist is showing unavailable. Aprreciate if you make it publicly available.
Thanks, they are coming online as soon as the coding exercise are complete and fully tested. Thanks for the nudge. Happy new 2025 - may this year be the year of learning 😁🎁🎄
DO We need to purchase OpenAI subscription?
@@AIwithsameer-y6l no, PydanticAI can be used with any model that supports agents, including the open source Llama 🦙 models. If you want to use OpenAI model, only then you’ll need a paid plan.
Very good 🎉🎉🎉
Thank you for the feedback. I am glad you enjoyed the video 😀
Excellent well done thanks
Thanks for the comment. Stay tuned for more updates on this.
Thank you.
@@dreamphoenix thanks for the support
Hi This is great but i hope this is your first but not the last video.
I hope to see how to use tools which is the crux of any AgenticAI framework.
I went through the code but i am stuck at how to register tool(python function) with the Agent.
It use a class called RunContext. I am not really getting the code.
There will be more videos, including tools. I have all the code examples ready, it’s just a matter of recording, editing and posting. Please stay tuned and thank you for the support!
Nice ty :D
You are welcome. I am glad you found the content helpful.
Can we please move on from python to a faster language
What’s the rationale? LLM calls are the slowest link in the chain. Can you elaborate?
@AISoftwareDevelopers and why throttle the pipeline more with a slow to respond language
@@greendsnow Roger that 👍 Curious to learn - what’s your choice of language, framework and model?
thanks:)
You're welcome! Cheers 😁
Thank you so much for this amazing video! Just a quick off-topic question: I have a SafePal wallet with USDT, and I have the seed phrase. (alarm fetch churn bridge exercise tape speak race clerk couch crater letter). What's the best way to send them to Binance?
Can't help with that, sorry. Tahnk you for the comment.
why AzureOpenAI?
Many corporate users use Azure-based OpenAI APIs as a way to control access, costs and privacy. I used it as an example of an OpenAI-compatible model passed as a client to PydanticAI. Any other model will do just as fine. Thank you for your comment! 👍
This has nothing to do with agents lol, this is completely normal, sequential, and explicit calling of wrappers of random LLMs. This is what langchain was doing 3 years ago
Ha! Exactly as you said- PydanticAI uses plain Python, making it look like just a wrapper. Stay tuned for future videos where I’ll show how to customise the system prompts, add tools and agent memory. Then, the power of this simple, yet powerful framework will become more visible. Thanks for the comment. Ciao! 😁🎁🎄