zackproser

I will say it was very nice getting the type hints for infrastructure while developing as well as hints about something being unused, etc.

It overall worked better than I was probably expecting.

Also agree with your points on the pain of IaC - it's terrific when it works but there's always those special "except this resource doesn't follow any of those rules" cases to make things painful and extra complex.

I've also found that IaC can have a chilling effect for folks who haven't ever tried it before - it's a powerful abstraction tool - but at the end of the day you also need some level of understanding around what is happening under the hood - where to debug an error (which level), etc.

I do use Grammarly for editing assistance when I'm writing something for work.

This was my first time using Pulumi, and it was very much a delight. There's clearly been a lot of thought and effort put into the plugins and overall developer experience.

For example, you can have Pulumi handle the Docker image builds for you - as well as the ECR repository logins and pushes. This means that your end users don't need to manually build images, log into ECR and push them - they just run `pulumi up` instead.

We get a lot of feedback that our many open-source Jupyter notebooks (github.com/pinecone-io/examples) are very helpful for learning new techniques and understanding how patterns work - even for starting new applications.

However, we're also often asked how to go from Notebook to prod. The Reference Architecture is a step in the direction of making this easier and more clear.

I'm a developer advocate who also does open re-source work and other development as part of my job.

https://youtu.be/Y36rUWeVnMM?si=yqwrOAanvSJ0fOEt

It lets you combine speech to text and markdown editing.

Partly for fun and practice and partly because it helps me to quickly commence new posts and either iterate on the go or return to the open PR when I'm back at my laptop.

That said, I've spent hours this week trying many different AI enhanced IDEs including cursor and I cannot for the life of me get anything to correctly set up jest in a TypeScript project - next.js or just vanilla TS... every single one does not correctly handle the Babel / tsconfig issues.

What I'm saying is I still think we'll see improvements over time but it's not quite there yet. I still prefer Codeium for completion and to take some boilerplate from gpt4 and modify it to my purposes.

This will be the case when you're exposing an interface to end users that they can submit arbitrary queries to - such as "how do I turn off reverse breaking".

By converting the user's query to vectors before sending it to your vector store, you're getting at the user's actual intent behind their words - which can help you retrieve more accurate context to feed to your LLM when asking it to perform a chat completion, for example.

This is also important if you're dealing with proprietary or non-public data that a search engine can't see. Context-specific natural language queries are well suited to vector databases.

We wrote up a guide with examples here: https://www.pinecone.io/learn/retrieval-augmented-generation...

And we've got several example notebooks you can run end to end using our free-tier here: https://docs.pinecone.io/page/examples

and a lot of open-source Notebooks at github.com/pinecone-io/examples which demonstrate techniques from semantic search to question and answering to retrieval augmented generation (RAG)

FWIW, our free tier is sufficient to use any of these notebooks or our open source vercel templates - so whether you're a student or just a solo dev looking to learn, you can create a free account and get started and never pay a dime - the one limitation is you can only have one index live at a time - so delete it once you're finished experimenting with a given notebook.

We've got some additional resources for folks looking to better understand Retrieval Augmented Generation (RAG) and even see it in action - in this example we demonstrate a potentially very dangerous hallucination (that has to do with driving) and how to fix it using RAG: https://www.pinecone.io/learn/retrieval-augmented-generation...

If you're curious to actually try out the difference between an LLM without domain-specific context and an LLM that is using RAG, you can try our live demo here: https://pinecone-vercel-starter.vercel.app/

And if you'd like to fork and make your own tweaks to the above demo ^ chatbot, in order to, for example, swap in your own company logo and extend it for your purposes, you can find our Vercel template here: https://github.com/pinecone-io/pinecone-vercel-starter

In our opinion, RAG is indeed an effective technique partly because you don't need to be a machine learning expert in order to implement it in your Generative AI applications.

I also think it's critical to have those progressive wins, and progressively more difficult, ambitious projects in order to keep learning and growing.

If you take a look at some of my previous posts you'll see I've experimented thoroughly with integrating GenAI services into my workflow, but I don't like using generated text. I'd rather write the article myself.

I find myself more likely to take some generated code as a starting point or talk through a thorny technical issue with GPT4 until the path forward is clear in my mind.

I love them, myself and - this part is really going to bother you - I'm working on an open source project to help me generate them with even greater efficiency: github.com/zackproser/panthalia

But yeah: my content is definitely not for everyone!

In all seriousness I deeply enjoy generating pixel art images and tweaking prompts to get exactly or closer to what I want, but across everyone giving me feedback I seem to get a 50/50 split between they're really pretty, which I tend to think is the case personally, or I'm a terrible person/ programmer/ artist for including them.

You may be interested to know I'm building a side project to help me write posts with generated images while I'm on the go:

github.com/zackproser/panthalia

So at least im the short term, be on the look out for more posts with terrible pixel art.

To be fair, I generate a bunch of Neon Punk stuff, too.

In this post, we explain what RAG is and how it can help reduce the likelihood of hallucinations in GenAI applications.

Mostly open source apps that I build to scratch an itch and then write tutorials about after putting it up on GitHub.

Lately, more AI and DevEx type stuff.

Early days, but you can see some of the ways this is already helping me out quite a bit (and increasing my enjoyment of things I already like to do): github.com/zackproser/automations