LangSmith Tutorial - LLM Evaluation for Beginners
Want to get started with freelancing? Let me help: www.datalumina.com/data-freel...
Need help with a project? Work with me: www.datalumina.com/consulting
This is a complete beginner tutorial for LangSmith. It allows you to find and fix errors, test, evaluate, and keep track of chains and smart agents made with any LLM framework. It also works seamlessly with LangChain, the preferred open-source framework for working with LLMs. LangSmith is developed by the company behind the open-source LangChain framework.
🔗 Links in this video
github.com/daveebbelaar/langc...
smith.langchain.com/
docs.smith.langchain.com/
👋🏻 About Me
Hey there, my name is @daveebbelaar and I work as a freelance data scientist and run a company called Datalumina. You've stumbled upon my KZread channel, where I give away all my secrets when it comes to working with data. If you want to learn more about what I do, then head over to www.datalumina.io/
Пікірлер: 29
🔐 Copy my AI tools & workflows: bit.ly/data-alchemy
I saw your video about deploying a Slack assistant on Azure, I loved it, but how can we deploy a vector database to have an assistant and memory?
can i use these langsmith tools for evaluating models from hugging face instead of openAI
A really nice job. It's really hard to be updated about all these development, but with each passing week, the gap between us and those who do not want to take advantage of these opportunities is widening
@daveebbelaar
10 ай бұрын
Thanks! And I know. It's crazy and a little overwhelming ;)
Did you use any vscode extension to generate those code comments in your file or?
It is clear that you have a very organized mind - the video is crisp and neat. Great to have as a creator! I am actually watching this to write a tutorial on LangSmith for DataCamp blog.
@daveebbelaar
5 ай бұрын
That's an awesome compliment :)
only thing i noticed is that the website doesn't update even after running the code multiple times to reflect the new traces. may be langsmith is still under beta.
How can I integrate a pdf file to a chat gpt in python ( I want ai to use information from my pdf )
@DANNYEL20122
9 ай бұрын
Learn langchain
Fantastic guide, thank you
@daveebbelaar
10 ай бұрын
Thank you! 🙏🏻
Hi, can I get an invite code for Langsmith?
How to get access to Langsmith? What about the data privacy of the client? Can we have this on-prem for data privacy and security purposes? Any response to questions will be highly appreciated.
@daveebbelaar
10 ай бұрын
You can sign up for the beta waitlist. For data privacy, please refer to this section in the docs: docs.smith.langchain.com/organizations#my-team-deals-with-sensitive-data-that-cannot-be-logged-how-can-i-ensure-that-only-my-team-can-access-it
amazing tutorial
Thank you! very informative and clear, and just in time. Is there also a way to evaluate using QAEgn and QAEval chains in Langchain?
I was literally searching for LangSmith tutorials and got your notification of this vid. Such a godsend!
Great job. How you ran you code from .py in Jupyter? I can't find hot keys for this.
@ruslansultanov7646
7 ай бұрын
kzread.info/dash/bejne/rKmgqa-Sl5PcZrg.html😀
Thank you, my friend ... this is awesome!
Hey Dave , really nice video! I was wondering if I could help you edit your videos and also make a highly engaging Thumbnail which will help your video to reach to a wider audience .
I m sorry to say..but you don't know how to teach bro...
@daveebbelaar
Ай бұрын
Why do you think so?
@benzhu2438
Ай бұрын
I wholeheartedly agree... skipped over so many basic steps so really isn't a "beginner tutorial." I wish I could get back the time I wasted listening to him
Hey Dave , really nice video! I was wondering if I could help you edit your videos and also make a highly engaging Thumbnail which will help your video to reach to a wider audience .