Відео

Is there a part II for this project? Would love to see you struggle through and find a solution for a seemingly "real world" problem:) This is really great. Always enjoy watching your videos:)

Greatt!! I enjoy watching your video. I have tried to hands-on the code from your GitHub but i am facing an error ModuleNotFoundError: No module named 'pgvector_service'. Then, I tried to pip install pgvector_service but this occured. ERROR: Could not find a version that satisfies the requirement pgvector_service (from versions: none) ERROR: No matching distribution found for pgvector_service Do you have any ideas how to overcome this?

U can use the shiny extension for creating rapid webapps also

For people experiencing the webhooks error "The callback URL or verify token couldn't be validated. Please verify the provided information or try again later.", the issue is that Meta don't consider some regions of ngrok as "safe". The solution is to try with other tunneling methods like pinggy, serveo, etc.

4 minutes in, and STILL nothing about what A.I. is. Geez...I'm out.

I think ngrok doesnt work any more

would this work with a deno kernel in a jupyter notebook too?

great work. please publish the next tutorial. is there a github for the code?

🔥

Absolutely fantastic! Thanks for sharing @daveebballar! Can we make this work with a local llm - e.g. ollama?

Hi Brother, This is very much clear and do by anyone easyway , it was amazing Thanks Bro... 🙏

Which app you use to record your Videos

Great video, I am not big on UA-cam, but this is the first time I see someone really understanding the current state of the tech.

Here's something you can help me understand, as an intermediate-level coder learning all of the nuances of AI/ML and their applcations. You're extolling the value of the directed acyclic graph approach towards data processing pipelines, to avoid sending data to earlier stages. As a fan of idempotency and functional programming, I _think_ that I somewhat understand where you're coming from in your premise. But in my studies of models, I'm also seeing a lot of buzz around the differentiation between methodologies of KANs vs MLPs. My question is this: wouldn't there be some value in using information uncovered later in the pipeline to refine what you're doing earlier on? For instance, let's say you're entertaining guests, and planning to serve appetizers. A very early step might be purchasing ingredients. Later on, you realize that not all of the guests show up. If we're just going to keep moving forward, we make more appetizers than are needed. The alternative: when less guests show up or RSVP, instead of making as many apps as your ingredients/plans dictate, you make less. Now you have less appetizers and you store or freeze the ingredients you didn't use. You _could_ make them, and freeze the unused portions. But by sending the information collected later back to an earlier step, you instead have the raw ingredients to use in other recipes instead. This is a really lousy and forced metaphor, but it's all I could come up with off the top of my head. It just seems like there's value in the concept. On a different level, isn't this just sort of a form of backpropagation? The ability to reinform earlier calculations with the results of later ones?

I am an experienced coder and my wife is a nurse. Recently she began online part time job. That is “to evaluate OpenAI’s language models.” I was absolutely convinced it was a scam, but she's already made $500 in three days. What kind of era are we living in?

My problem is having hard time to find girl friends.

AutoGen and CrewAI I think are more experiments than anything else. I use Python as a Maestro... then some AI, when I need it's generative abilities, some playwright when I need web automation... but business run on logic not in a democratic way and not in a creative way. They incorporate creativity in some steps but that's just that. A procedure is the only way to go since ever or else we'll have unpredictability that goes against efficiency and bad for processes in business, in factories, and would make it impossible to have any type of Quality Control.

In Jupyter, why can I still not cut and paste text in a cell using the mouse?

Cyclical/recursive algorithms are needed for many problems which in part, is what agentic frameworks attempt solve. Your sequential processing only paradigm is applicable only to certain problems.

Awesome dude,came across this at the right time of my life

Thank you for putting into words exactly what I had been feeling when trying these agent tools.

Langgraph

Thank you, Dave. I am pretty new to Python and couldn't thank you enough for this great series! You have amazing content and a great channel!

@13:33 Please create an in-depth video on these concepts using the example that you are showing in this video !

Will I be able to put this ai assistant into my car

Great tutorial, clear and concise. Thank you!

This is exactly what i needed.

While your critique of agent frameworks is spot on and compelling, it seems there's a misconception about their potential. Your custom system resembles langchain+langgraph, highlighting a need for deeper understanding before dismissing existing frameworks.

I think this is fair, for linear data flows and data transforms simplicity is best but for complex, multiphase transactional goals which contain conditional variables which could change during the flow you need a controller/manager which can identify and respond to these state changes. In addition ideally an orchestration agent wouldn't be bound to a set of pre agreed agents/services/API s but would be constantly optimising its flow - searching out better ways to reach its outcome. A solid Agentic framework should be able to switch between and explicit and discoverable transformation approach hopefully..

Such a weird take

It’s still working with ngrok? I couldn’t configure the webhook when running through this tunnel.

Great work ❤

I mostly agree with everything. But there are two kinds of pipelines. The first one is when you have a finite amount of transformations, and the second one is when you don't know all the transformations in advance and need to delegate decision-making (in this case, you need an agentic approach). However, every pipeline can be represented as a finite transformation when you know it. for example classification. and t that is the key. So, if your pipeline is research-like, then you can't know it in advance; in other cases, you can.

what to do if your system is windows and not linux because by default it selects linux when you choose python

One of the worst videos I've seen this year. You ignored a very capable framework like LangGraph. Also, the fact you did not talk about hierarchical or sequential agent workflows and you ONLY focused in the multi-agent ones to present us "your case" is not serious. In any event, even a simple multi-agent graph can achieve a 100% success rate in resolving tickets. You don't need to hardcode all those steps at all.

framework in the end is just how you organize your code.

state machines, state machines, state machines...

Really helpful video Dave, thank you for sharing this information!

LangGraph might be the solution you/we are looking for, have you tried it yet ? Definitely agree that first principles should be followed, understanding the foundations before abstraction.

Really cool idea!! You need to get rid of your erat8c teaching style tho. Especially with respect to quickly showing pictures jump g to Code etc.... Anyhow.... I would love to See the full fledged videos!!

in the video you are creating the data from text files, but it seems like a main advantage of having it on your postgres db is being able to use / query the data in your tables. i'd love to see how to build a full text search or something from data stored in regular postgres tables!

Another day - another wave of similar videos… I did not get this agents bullshit from the start(felt like data gathering scams to me), cuz i was chaining prompts when chatgpt came out. You gonna chain prompts manually if you are building something more than a useless demo.

Interesting. Working on a CrewAI project atm and I found I was using a DAG approach to tasks because of my experience with Kedro. One task, one transformation, one output and keep working sequentially. In a nutshell, you're describing Kedro's approach and philosophy. Its just not fine-tuned for generative AI use cases yet. What I've found with multi agent apps is that I end up building tools that do all the heavy lifting and the agent Is used to generate a piece of data (like a query string) used in subsequent processing. The challenge is building guardrails to prevent an agent from going off the reservation when something doesn't work. If you give an agent access to a tool as simple as a search tool, if it gets stuck, it could end up calling the tool in a loop and there goes your credits. So we're still having to treat agents like toddlers... would be interesting to see your take on kedro.

Great video - thank you for sharing:)

Great video! Learnt a lot

Thank you for the video, Dave. Your perspective is very insightful. In my experience, frameworks like LangGraph by LangChain offer a great solution to the complexities you've outlined. LangGraph enables the orchestration of agents within a more structured, acyclic workflow, providing the customization and sequential order necessary for reliable business automation. Have you played with it? What do you think?

amazing ! Thank you so muchhh

can i use these langsmith tools for evaluating models from hugging face instead of openAI

AI was the turning point in my life