langchain
create-t3-app
langchain | create-t3-app | |
---|---|---|
33 | 183 | |
83,874 | 23,398 | |
3.9% | 2.4% | |
10.0 | 9.2 | |
3 days ago | 7 days ago | |
Python | TypeScript | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
langchain
- Construyendo un asistente genAI de WhatsApp con Amazon Bedrock
- Show HN: SpRAG – Open-source RAG implementation for challenging real-world tasks
-
Aider: AI pair programming in your terminal
Big fan of Aider.
We are interesting in integrating Aider as a tool for Dosu https://dosu.dev/ to help it navigate and modify a codebase on issues like this https://github.com/langchain-ai/langchain/issues/8263#issuec...
-
🦙 Llama-2-GGML-CSV-Chatbot 🤖
Developed using Langchain and Streamlit technologies for enhanced performance.
-
Building a WhatsApp generative AI assistant with Amazon Bedrock and Python
Tip: Kenton Blacutt, an AWS Associate Cloud App Developer, collaborated with Langchain, creating the Amazon Dynamodb based memory class that allows us to store the history of a langchain agent in an Amazon DynamoDB.
-
👑 Top Open Source Projects of 2023 🚀
LangChain was first released in October 2022 as an open-source side project, a framework that makes developing AI applications more flexible. It got so popular that it was promptly turned into a startup.
-
Fuck You, Show Me the Prompt
> Furthermore, the prompt has a spelling error (Let'w) and also overly focuses on the negative about identifying errors - which makes me skeptical that this prompt has been optimized or tested.
Fixed in https://github.com/langchain-ai/langchain/commit/7c6009b76f0...
- LangChain Repository Disappeared
-
🆓 Local & Open Source AI: a kind ollama & LlamaIndex intro
Being able to plug third party frameworks (Langchain, LlamaIndex) so you can build complex projects
-
Easy Guide to Creating Smart Chatbots with Langchain & GPT-4
Access Langchain's repository at Langchain's Repository.
create-t3-app
-
Deploy Full-Stack Next.js T3App with Cognito and Prisma using AWS Lambda
import { unstable_noStore as noStore } from "next/cache"; import Link from "next/link"; import { CreatePost } from "~/app/_components/create-post"; import { getServerAuthSession } from "~/server/auth"; import { api } from "~/trpc/server"; export default async function Home() { noStore(); const hello = await api.post.hello.query({ text: "from tRPC" }); const session = await getServerAuthSession(); return (
Create T3span> App h1>
First Steps →h3>
Just the basics - Everything you need to know to set up your database and authentication. div> Link>Documentation →h3>
Learn more about Create T3 App, the libraries it uses, and how to deploy it.div> Link> div>{hello ? hello.greeting : "Loading tRPC query..."}p>
{session && Logged in as {session.user?.email}span>} p> {session ? "Sign out" : "Sign in"} Link> div> div> div> main> ); } async function CrudShowcase() { const session = await getServerAuthSession(); if (!session?.user) return null; const latestPost = await api.post.getLatest.query(); return (
{latestPost ? (Your most recent post: {latestPost.name}p> ) : (
You have no posts yet.p> )} div> ); }
-
Interview with Senior JavaScript Developer 2024 [video]
I thought he was making stuff up - "t3 stack vs t4 stack". But about 2 minutes in, I realized that I'd heard of a few things that he's talking about so I looked it up and they're real!
I think it's possible everything he's saying is true, more or less. LOL
t3: https://create.t3.gg
t4: https://t4stack.com
-
Localized tRPC errors
We start with a project that was bootstrapped with create-t3-app. For internationalization we use next-intl and set it up as described in the getting started guide. With this initial project setup we can jump into implementing localized error messages.
-
Building an Admin Console With Minimum Code Using React-Admin, Prisma, and Zenstack
I used create-t3-app to scaffold the Next.js app, with TypeScript, Prisma, and "app router" enabled in the options. You can also use create-next-app for the job and install Prisma manually.
-
Leaving Everything Behind For Elixir [Theo – t3․gg] [video]
I agree that the quantity of publicly available code isn't the most reliable indicator of someone's seniority.
My issue with this individual arises from the discrepancy between his public claims of significant expertise in the content he produces. He positions himself as a highly experienced developer, attracting a large following of junior developers who take his advice at face value.
I am trying to collect data points supporting his claims of seniority. For instance, his website prominently features a statement that he is the creator of the T3 Stack. However, a review of the contributor statistics for the T3 Stack (https://github.com/t3-oss/create-t3-app/graphs/contributors)... minimal contributions from him, which raises questions about the validity of his claims.
-
Ask HN: Which full stack framework (NextJS, Remix, SvelteKit) would you use?
I would recommend - https://create.t3.gg/
It uses the following, which as of late are pretty well know and common, so you can punch in your problems to stackoverflow, google, or chatgpt and get some pretty good answers.
It uses:
Nextjs (React), typescript, trpc (typescript rpc), auth, tailwind, and Prisma (ORM)
Though of course these could go out of fashion tomorrow, but I don't think the essential idea behind these libs and frameworks are that wacky, unique or unordinary.
Prisma ORM, is a little opinionated, and you could swap it out for Drizzle, which is basically typescript side sugared SQL.
TRPC might be also be a little sticky because it is tied to typescript, this is the tradeoff for the buttery smooth coupling for the fullstack experience. I think there exists a typed-rest solution out there, but haven't used it.
Personal anecdata, I used this stack for a little hobby project and it was FUN.
-
You don't need to pay for SaaS boilerplates - Open SaaS
Open SaaS was built with Typescript, and because it’s a full-stack app, type safety from the back-end to the front-end can be a real lifesaver. I mean, some opinionated stacks have gotten hugely popular on this basis.
-
Building a Local Development Environment: Running a Next.js Full-Stack App with PostgreSQL and Minio S3 Using Docker
Let's start by creating a Next.js application. We will use the T3 stack (TypeScript, TailwindCSS, and Prisma ORM) for this tutorial to skip installing and configuring all the dependencies which is out of the scope of this article. You can find more information about the T3 stack.
- Ask HN: Who wants to be hired? (January 2024)
-
Show HN: Build your startup or side project faster with these SaaS templates
https://github.com/t3-oss/create-t3-app
You still would need to add Stripe but there are so many examples publicly available that it should be straight forward
What are some alternatives?
llama_index - LlamaIndex is a data framework for your LLM applications
vite - Next generation frontend tooling. It's fast!
semantic-kernel - Integrate cutting-edge LLM technology quickly and easily into your apps
next-pwa-contentlayer - Next.js PWA App with `next-i18next` and `Contentlayer`.
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
Refine - A React Framework for building internal tools, admin panels, dashboards & B2B apps with unmatched flexibility.
griptape - Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.
supabase - The open source Firebase alternative.
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
turbo - Incremental bundler and build system optimized for JavaScript and TypeScript, written in Rust – including Turbopack and Turborepo.
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
next-auth - Authentication for the Web.