Langsmith LLMOPS Platform By Langchain-Debug ,Monitor And Build Production Grade LLM Application
ฝัง
- เผยแพร่เมื่อ 5 ก.พ. 2025
- LangSmith is a platform for building production-grade LLM applications.
It lets you debug, test, evaluate, and monitor chains and intelligent agents built on any LLM framework and seamlessly integrates with LangChain, the go-to open source framework for building with LLMs.
LangSmith is developed by LangChain, the company behind the open source LangChain framework.
github: github.com/kri...
Thank you Krish. A lots of love n respect.
It would be more useful if you could guide us on performing the same for locally saved models too.
Good Video. Learning a lot from you.
Amazing video. Thanks krish waiting for for your future videos
you are so innocent looking while saying " I have updated my OpeniAI API, because the credit balance was less" :) :)
It's like tensorboard for LLM's!
Thank you Krish. A lots of love n respect.
Can you do video on evaluations for pdf query code
Great video
Thanks krish.
Amazing 🕶❤
I have a very generic question about evaluation of the RAG system. How can we evaluate the responses generated by the RAG system?
RAGAS is a test framework, I started using it in recent times to evaluate RAG
@@BalaguruGupta Can you share any link or youtube channel for this please
Hei Krish, I want to learn AI and build AI agents, but I’m unsure where to start. Should I begin with the basics of AI, or should I jump straight into building AI agents and integrating them with social media? or do i need learn AI from basics with maths!!! 😐
Also, as a full-stack developer, should I focus on tools like LangChain or LangSmith, etc.., or should I explore no-code platforms? I’m looking for some guidance to help me choose the best path forward. Thanks!
In Multi Agent/Tools workflow, whether can we able to track the agents and tools which was used to retrieve the response? If yes, can you please make a video on that?
Can we do this with open source model
👍🙂👍
Hi Krish, Is there a way we can capture these details locally into csv or text files.
@krish Naik. Can you please make a video how do we make LLM model from scratch. Not project but LLM model using pytorch or tensorflow. Very less information on that
Dont do it, its too much of a hassle. It costs too much compute to train it anyway. Just use an API or run your own instance of an open source model
Man's dropping W's 🙏🏼🫡🔥
U r pro bro please explain from scratch
Thanks so much for your videos🙏 If you will have a chance, could you please help to figure out eval and testing part of LangSmith
Is it possible to use a different LLM model like a gemini model rather than OpenAI's gpt model while integrating with langsmith?
we are providing retrieved information as a context, Will this data get transmitted to Langsmith webspace
, as we are using their url?
@Krish Naik. How to make my LLM model from scratch.
Hello Sir. I trying to implement the fake news classifier code of your video but i'm getting the error at this line model.add(Embedding(voc_size,embedding_vector_features,input_length=sent_length)) and the error it's showing is Unrecognized keyword arguments passed to Embedding: {'input_length': 20}. If input_length is removed it's giving empty summary table. Can you please help me to resolve this issue.
why is it that even though I run the code but no projects gets updated
like there's no new projects, only default
Are there any alternatives to langsmith?
will this work with local LLM?
Are you teaching in inuron.
Thank you sir, Is it support the Arabic language
Every second day new model new technology 😢
your contents are very generic. Pls do some hard work and demonstrate complex task like "storing log from langsmith into some files or database based on date range"... that kind of videos will be more helpful for experienced techies.