replicate-javascript VS supabase

Replicate (YC W20) | San Francisco, CA + Remote | https://replicate.com/

Replicate makes it easy to run AI in the cloud. You can run a big library of open source models with a few lines of code, or deploy your own models at scale.

We're an experienced team from Spotify, Docker, GitHub, Heroku, Apple, and various other places. We're backed by a16z, Sequoia, Andrej Karpathy, Dylan Field, Guillermo Rauch.

We're hiring:

- An infrastructure engineer

- An expert at deploying and optimizing language models

- An engineer who is good at humans to look after our customers

... and more: https://replicate.com/about#join-us

Email us: [email protected]

import { experimental_buildLlama2Prompt } from 'ai/prompts'; // Now use Replicate LLAMA 70B streaming to perform the autocompletion with context const response = await replicate.predictions.create({ // You must enable streaming. stream: true, // The model must support streaming. See https://replicate.com/docs/streaming model: 'meta/llama-2-70b-chat', // Format the message list into the format expected by Llama 2 // @see https://github.com/vercel/ai/blob/99cf16edf0a09405d15d3867f997c96a8da869c6/packages/core/prompts/huggingface.ts#L53C1-L78C2 input: { prompt: experimental_buildLlama2Prompt([ { // create a system content message to be added as // the llama2prompt generator will supply it as the context with the API role: 'system', content: systemContext }, { // create a system instruction // make sure to wrap code blocks with ``` {% endraw %} so that the svelte markdown picks it up correctly role: 'assistant', content: {% raw %}`When creating repsonses sure to wrap any code blocks that you output as code blocks and not text so that they can be rendered beautifully.`{% endraw %} }, // also, pass the whole conversation! ...messages ]) } }); {% raw %}

We used Replicate to run the models and the cost so far is 26 cents for 90 cards — which means it’s less than a third of a cent per card!

Basically https://replicate.com/

Because it happens when running your own models on localhost too. I have ollama and all the ones they support, but there are some on HuggingFace I run through llama.cpp inside apps where I won't have ollama installed, Replicate also has Stable Diffusion models, not just chat ones, and OpenAI which is its own thing. So it could potentially all be unified under a provider like that.

Haven't actually tried Replicate because I'm just running locally for free, but probably would try to find a single cloud provider for all deployments, like a Heroku of LLMs.

It's very easy to get started, right in your Terminal, no fees! No credit card at all.

And there are cloud providers like https://replicate.com/ and https://lightning.ai/ that will let you use your LLM via an API key just like you did with OpenAI if you need that.

You don't need OpenAI - nobody does.

In this section, we’ll show you how to generate MDE depth map predictions with both DPT and Marigold. In both cases, you can optionally run the model locally with the respective Hugging Face library, or run remotely with Replicate.

Built with Supabase, Astro, Unreal Speech, Stable Diffusion, Replicate, Metropolitan Museum of Art

Now that we understand the process, let’s take a look at the actual code. The first step is simply importing our dependencies. Note that we will be using the replicate npm package, which you can install with npm i replicate.

I see it differently. In the 25 years I've been working in this industry I see a welcome trend toward doing more in the database, such that the impedance mismatch dissipates:

https://gist.github.com/cpursley/c8fb81fe8a7e5df038158bdfe0f...

https://supabase.com/

One way to eliminate the Java-SQL impedance (for example) mismatch is to delete Java altogether, along with JOOQ, Hibernate, and Spring (for example).

My initial, now long abandoned, plan was to use Next/Nuxt to create the front-end and have the back-end be in Python, to allow me to use the recipe-scrapers library, and to use Supabase to organise the database of users and their collection of recipes, and allow the users to enter a list of ingredients and be presented with a selection of recipes from their own curated collection that contained those recipes, allowing people to get some inspiration on what to cook based on the ingredients available to them at the time. Using the recipe-scrapers library, I would have allowed them to enter a URL to add a recipe into their collection, as well as a page displaying all the recipes currently stored in the collection and allow them to delete any they no longer wished to be included. Nothing too crazy, a pretty sweet simple idea, which I would make sure was responsive enough to look good when viewing on a phone.

Step 1: Sign up at supabase.com and create a new project.

Subpabase - Like Planetscale this is only for databases. It is an open source Firebase alternative for building secure and performant Postgres backends with minimal configuration.

If you are new to postgres or if you are a frontend heavy developer who is currently relying on supabase to have a magic backend appearing out of nowhere, or maybe you are just someone who likes to read stuff and in that case I have something to share with you!

Supabase is a backend as a service visual platform that allows you to create postgres DB with minimum code. Their documentation is so good that it feels like home and you can get your project online in no matter of time.

It was a great experience using Supabase’s rock-solid PostgreSQL database for this app. The DX around that product is phenomenal: viewing and managing the DB data was a lifesaver when you don’t want to craft your own admin panel from scratch.

I didn't really give much thought as to which backend I would use. I already had 2 projects in Supabase (BOXCUT & MineWork), but also a few projects in Firebase too. I was more concerned at the time at actually building the product.

Sign up for SupaBase: Head over to SupaBase and sign up. Create a new workspace and project with your preferred names.

Setting up Supabase Create a new Supabase project, and get the connection string for the database from settings > database.