PydanticAI - The NEW Agent Builder on the Block

Поділитися
Вставка
  • Опубліковано 6 гру 2024

КОМЕНТАРІ • 64

  • @pleabargain
    @pleabargain 2 дні тому +6

    Thanks for the detailed walk through. re: RAG system: Yes, please make a video about PydanticAI RAG.

  • @comfixit
    @comfixit День тому +2

    Great choice of video topic and excellent job demonstrating the potential for the framework, great examples. 5 Stars!

  • @ratral
    @ratral 2 дні тому +1

    Thank you, @Sam. Great job, as always! It's excellent that Pydantic has incorporated AI. I would love to learn more about what can be achieved with PydanticAI.

  • @yotubecreators47
    @yotubecreators47 2 дні тому +34

    it's time to replace Langchain

  • @zakariaabderrahmanesadelao3048
    @zakariaabderrahmanesadelao3048 2 дні тому +5

    The power of LLMs + the control of Vanilla Python. This is going to be awesome.

  • @yschermer3124
    @yschermer3124 17 годин тому

    Finally, a simple AI layer that just abstracts what is actually useful to abstract. Can't wait to try it out on my next project!

  • @60pluscrazy
    @60pluscrazy День тому +2

    How does it decide on the tool call order? Based on the order of tool injection?

  • @SaahilKhan8
    @SaahilKhan8 2 дні тому +6

    Your content is amazing! *Subbed*

  • @dudepowpow
    @dudepowpow 2 дні тому +2

    Straight to the point and great insight, thank you!

  • @gmongalo
    @gmongalo День тому

    Great overview! Thanks for the easy to follow walkthrough, excited to use it. Cheers !

  • @viveksuryavanshi6165
    @viveksuryavanshi6165 2 дні тому

    Thanks Sam, this was great OG style !!

  • @ShlomiSchwartz
    @ShlomiSchwartz 2 дні тому +1

    Great video, Sam! Thanks for breaking down Pydantic Al so well. Quick question: Could you create a video on how you think two agents should communicate and hand off tasks between each other? I’d love to see your perspective on that!

    • @samwitteveenai
      @samwitteveenai  2 дні тому +1

      Sounds interesting do you have a specific use case. I am looking for a few ideas to make so more examples

    • @ShlomiSchwartz
      @ShlomiSchwartz День тому

      What about a booking assistant? One agent gathers user preferences, and the other uses tools to finalize and confirm the booking.

    • @ShlomiSchwartz
      @ShlomiSchwartz День тому

      Adding a RAG system could be great! For example, when asked, 'Can you show me the cancellation policy for this hotel booking?' the first agent could retrieve specific details from indexed data, making the conversation seamless and informative.

  • @RobertFitz-r8r
    @RobertFitz-r8r 2 дні тому +2

    Thanks for the insightful video on this new framework by Pydantic AI. For a single agent, the developer experience looks certainly lightweight and easygoing.
    Does this also apply, if one wants to scale this up to multiple agents that require some sort of intelligent agent orchestration?

  • @MeinDeutschkurs
    @MeinDeutschkurs День тому

    Yeah, all these frameworks and examples being presented look great - but as always, the real problem lies elsewhere: Specifically in the orchestration, meaning the decision about which of all these possibilities (tools, workflows, output formats etc.) are even relevant and should be used for the current user prompt. And all of that while considering the complete conversation history! As far as I can tell, nobody on UA-cam has really dared to tackle this core issue yet.​​​​​​​​​​​​​​​​ 🎉

  • @jafors7
    @jafors7 2 дні тому

    Great vid fella. Keep em coming

  • @horseheadhunchback
    @horseheadhunchback 2 дні тому

    Every time I watch one of your videos it’s a hit.

  • @robcz3926
    @robcz3926 2 дні тому +4

    there has been a serious shortage of frameworks in the AI space so thank god they came out with this.

    • @faustoalbers6314
      @faustoalbers6314 2 дні тому +2

      This is an iteration on Instructor. There have not been many frameworks better than that IMHO, so pretty stoked to see this one come out.

    • @sprobertson
      @sprobertson 2 дні тому

      😂

  • @evgenyminkevich6587
    @evgenyminkevich6587 2 дні тому

    Great overview. Thank you!

  • @ko5syrup
    @ko5syrup 2 дні тому +1

    great walk through! I think the only critique I took from you was it being for “simple” setups. Is that your take?

  • @60pluscrazy
    @60pluscrazy 2 дні тому

    Thanks 🎉🎉🎉

  • @KevinKreger
    @KevinKreger 2 дні тому

    Fabulous! Extremely useful 🙂

  • @lakergreat1
    @lakergreat1 День тому

    So what's the difference from pydantic AI structured outputs vs using open AI structured outputs of both us gpt-4o?

  •  2 дні тому

    very nice. thanks Sam

  • @nathannowack6459
    @nathannowack6459 2 дні тому +1

    fwiw instructor fast followed prefecthq/marvin, but has broader llm support. anyways, glad to see pydantic make this!
    PS: i wouldn’t use use nest_asyncio, it causes problems in practice. just don’t use notebooks :)

    • @samwitteveenai
      @samwitteveenai  2 дні тому +1

      Colab is a great way to show something so people can see how it works. without having to install all the dependencies etc. Not telling people to use this for prod

    • @nathannowack6459
      @nathannowack6459 2 дні тому

      i appreciate that! good video by the way. i’ve just been bitten by nest_asyncio conflicts with normal asyncio before haha

  • @theh1ve
    @theh1ve 23 години тому

    I'm using bedrock through AWS to call Claude how easy would it be to hook it up? Would love to see agent RAG with this.

  • @josephfouad3561
    @josephfouad3561 2 дні тому

    Great content as usual, Please make a follow-up for RAG

  • @ShubharthakSangharsha
    @ShubharthakSangharsha 2 дні тому

    Now I can build amazing tools without thinking of any bugs. Thanks to pydantic AI. I will defintely gonna use it on my apsara2.0. Time to say Bye to Langchain (so complex man)

  • @avi7278
    @avi7278 2 дні тому

    Sam how well would this integrate with the outlines project?

  • @adamgkruger
    @adamgkruger День тому

    Love it

  • @martg0
    @martg0 2 дні тому

    What AI workflow orchestrator would you use in AWS combined with Bedrock?

  • @Jurfyste
    @Jurfyste 2 дні тому

    Would this work with a private model?

  • @WillJohnston-wg9ew
    @WillJohnston-wg9ew 2 дні тому

    Sam, with all of these agent models, which would you say is generically the best (breadth of functionality, ease of implementation, future ready...)?

    • @samwitteveenai
      @samwitteveenai  2 дні тому

      it really depends on your use case. LLMs I generally use Sonnet 3.5, Gemini Flash for proprietary models these days. Open Source I generally am using fine tunes of small models, like Phi, Gemma2 and Qwen

  • @Profusion_AI
    @Profusion_AI 2 дні тому

    Thanks for dropping this info. So is this essentially competing with Anthropic’s MCP to standardize function calling?

    • @samwitteveenai
      @samwitteveenai  2 дні тому

      no more competing with LangChain and CrewAI etc

    • @preyenperumallable
      @preyenperumallable 2 дні тому +1

      I immediately thought about MCP too. So thanks for posing the question. Can we use the pydantic framework to do all the orchestrating in host app and tool call using the MCP etc? I liked the idea of separating the tools logic from the interface logic. Or I have completely lost the plot, boy do these things move fast! Im a biomedical engineer dabbling in the computer sciences, what a ride.

    • @samwitteveenai
      @samwitteveenai  2 дні тому

      interesting idea. yeah you could use it with MCP. I have a 2nd MCP vid done but I had some issues with timeouts I might look at putting something with this in.

    • @preyenperumallable
      @preyenperumallable 2 дні тому

      I look forward to seeing it! . And thank you again for your work. Always helpful to watch and challenging my own thoughts about all these things.
      I’ve just discovered Bret Victor’s DynamicLand and my mind is blowing out of control with all these ideas .
      All the best to you.

  • @IdPreferNot1
    @IdPreferNot1 2 дні тому

    Given that LLMs are stateless, agents serve as large state models to carry context from action to action and agent to agent. No better model system than Pydantic. This is a better version of Swarm, also using dynamic prompts and context variable injection, automatic function interpretation to drive tool calls, and with a better state model for better context management. I built a backup context manager for my attempt at a personal agent Swarm with pydantic models, and here thye come out and have it built in. I wouldn't bet against these guys. There is no need for complicated agent frameworks and graphs etc beyond this, as llms can now drive their own path.

  • @dankprole7884
    @dankprole7884 2 дні тому

    I will use this just to spite open ai and anthropic

  • @thanhquachable
    @thanhquachable 2 дні тому

    Pydantic should have done this a long time ago

  • @sitrakaforler8696
    @sitrakaforler8696 2 дні тому

    Dammmm nice !

  • @kenchang3456
    @kenchang3456 2 дні тому +1

    Thanks Sam for another valuable video.

  • @donFrankAlvarez
    @donFrankAlvarez 2 дні тому

    This or CrewAI, you think?

    • @samwitteveenai
      @samwitteveenai  2 дні тому +1

      this gives you far more control than CrewAI. CrewAI is probably easier to use for non coders though.

    • @donFrankAlvarez
      @donFrankAlvarez 2 дні тому

      @@samwitteveenai It might actually be the opposite. Getting started wasn't hard but now that the project has grown, I spend more time dealing with input validation and parsing errors than actually developing, that's why I'm looking at PydanticAI as an alternative. It just seems more production-ready. Plus, I have a feeling that my AI IDE (Widsurf) will have an easier time with conventional python usage instead of having to re-learn CrewAI usage patterns every single dev session.

  • @will2ride
    @will2ride 2 дні тому

    Top uitgelegd.

  • @auslei
    @auslei 2 дні тому +1

    Unless there is limitless context window and AI can directly manage and interact with an environment. Agentic AI is overrated. You still have to write functions and AI is basically deciding a process flow and fails on simple ones even, due to hallucinations. Also it is extremely hard to debug and expensive to run. It’s a lot easier to write code right now to perform tasks they can do.

  • @Quaquaquaqua
    @Quaquaquaqua День тому

    Glad i can stop building this myself