Відео

Is there any free gpu online that can we use to code with llm?

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.

You should choose an even smaller font size that way no one can read anything you're showing isn't that what you're going for here ... $tupid!!

Obrigado pelo conteúdo ❤

NGL I've been struggling to wrap my head around coding using LangGraph; Looking forward to testing this and adapting it for bigquery.

This is great. Can you do a video on putting these agents in a backend/fastapi/REST API framework so we can learn how to productionalize agents? Especially with human in the loop, and streaming in REST API. Thank you

Great video as always! Such cool tool! Appreciate you guys posting these helpful video, this is game changer!

This is a mind blowing video...... how much can we can get done these days with just a page of code

I am at the end of my career in IT ( having started it before the advent of the Internet) and when I watch videos like this one and what you could do with such frameworks I feel like I wish I was born at this time of history because knowledge is shared so freely and the field has advanced so much and the possibilities are so many

Can you share the link to the iPython book

Keep going ❤❤

When I run the app in chat mode it shows a pop up saying: "Expected content-type to be text/event-stream, Actual: application/json Check your backend logs for errors." Do you have an idea why that is ?

Nice. This is great content. I am gonna run it with phi-3. One Question: Can I use a ReactAgent and provide multiple control flows as tools?

Python? 😩

How important is the chunk size and what is the best way t set it up?

Keep up the good work man!

I'm getting "KeyError: 'tools'" on "for event in events:". Has anyone else gotten this and solved it? Maybe bug?

This may be a stupid question, but how do I start from scratch, i.e. srape the wikipedia page, create embeding, create an index, upload the embeddings, ... I am missing all this stuff in the explanation ...

Thank you for the discussion.

Odd that the original question isn't used. Why not use the original question and generate just four additional questions?

Keep up the great work

a great challenge would be to accurately ascertain whether the model is capable of answering the question/topic itself or whether external tooling such as web browsing is required. I haven't been able to do this yet with llama3. I guess I haven't managed to find the correct routing prompt (a stage after the initial routing)

working fast cool

absolutely fantastic tutorial. I've been working on some langgraph projects and this helped massively with some of the llama3 prompts. Need to check out the langchain Chroma library to see how to persist the vector store with an instance of chromadb running

Thank you. I instinctively started googling, because for me answer accuracy / answer quality is more significant to me

Googles team does AlphaFold and changes the world and Sam gives us NSFW tools….

You guys are awesome!

I forgot how much computer people like watch blocks and blocks of text.

Quick and to the point! Love the eval!

Did you make this graphic at 1.48 programmatically or did you import it as image from a different tool?

Amazing!

Nice. Thanks for sharing!

ahhaa, very fast reaction! great job

So fast. 🎉thank you.

Thank you for the discussion.

Hi, I requested access to your notion page.... 🙏

🎯 Key Takeaways for quick navigation: 00:44 *🚧 Improving the User Experience of Customer Support Chatbots* 00:46 *💼 Enhanced Control over the User Experience* Made with HARPA AI

Awesome video and easy to understand, really appreciate!

How will this work in a rest API application ?

Thanks Lance for more one great tutorial! Really useful and easy to follow.

when I am using llama3 or mistral it doesn't recognize the tools, does anyone try it?

When I used ollama for predict in evaluator function. It send request for all elements in dataset at same time to ollama. It gave 500 server error. Iwant to use one element atatime in dataset. How

This is so awesome! when you inspect the off the shelf evaluator prompts, is it possible to edit the evaluator prompts and save as a new custom evaluator directly from LangSmith?

Hello. First of all thank you for this video. I am trying to follow you but when I run part_1 I am getting an error in checkpoints and I stuck there. Can you help me to understand what is happening File C:\Python311\Lib\site-packages\langgraph\channels\base.py:117, in create_checkpoint(checkpoint, channels) 115 """Create a checkpoint for the given channels.""" 116 ts = datetime.now(timezone.utc).isoformat() --> 117 assert ts > checkpoint["ts"], "Timestamps must be monotonically increasing" 118 values: dict[str, Any] = {} 119 for k, v in channels.items(): AssertionError: Timestamps must be monotonically increasing

do you have any advice on using other llm models?

Did anyone try this with a local model? (Llava for example)

Great video. In a project I've just completed I did see some of the benefits of a multi-agent design (simpler than this one). I also saw some of the limitations of LLMs if you attempt to put everything in a single prompt. This video presents a much more structured way of looking at the problem. Thank-you :)

Could you add reflection on LangGraph nodes ?

Great tutorial! I would like to see soon some example in a task oriented dialogue

Great piece of knowledge! I am not a professional python developer (yet) and the syntax with building a chain with " | " broke my brain. You could either explain it a little bit or use more explicit syntax if possible in the future.