StoryGraph DB,AI: Cloud => baremetal, with Cloud 66

2 people startup, 2 millions of users (!), profitable!

to keep it functioning and profitable,
needed to move out of (PaaS) cloud (Heroku) to "baremetal cloud",
with Cloud 66 · Everything you need to run your code to any cloud

Rails + "local" DB, local AI

excellent podcast!

Hanselminutes Technology Podcast - Fresh Air and Fresh Perspectives for Developers - Local AI empowers startups with StoryGraph's Rob Frelow

The StoryGraph | Because life's too short for a book you're not in the mood for

The StoryGraph - Wikipedia

The StoryGraph (sometimes shortened to just "StoryGraph") is a social cataloguing web platform for books, serving as a competitor of Goodreads (an Amazon-owned social cataloguing platform). The StoryGraph received awareness after Book Riot covered the platform's assets, including more personalized recommendations for readers, customized ratings options (including half-star and quarter-star ratings), and its non-affiliation with Amazon. The StoryGraph uses a freemium model, with some features only available in the paid subscription plan.

The StoryGraph | Our Team

A Word of Warning | Nadia Odunayo | TEDxUCSD - YouTube TED talk

Getting to One Million Users as a One-Woman Dev — Nadia Odunayo - YouTube Rails talk

Nadia Odunayo | LinkedIn

example book:

Areté: Activate Your Heroic Potential by Brian Johnson | The StoryGraph
Powered by AI (Beta)
Areté: Activate Your Heroic Potential by Brian Johnson is a good fit for individuals seeking practical tools and ancient wisdom to help them overcome life's challenges and fulfill their destiny, with a focus on personal growth and self-improvement.

Is Cloud 66 a "new Heroku?"

Why "baremetal" / dedicated cloud? to get predictable performance and cost, no "noisy neighbor" and security issues, and for sw licensing. Examples:

//www.vultr.com/ 

//us.ovhcloud.com/

strangely, Oracle cloud is not listed on Cloud66, while this is one of differentiating features Oracle is claiming... 

similar functionality: dedicated hosts

Dedicated Server Hosting - Amazon EC2 Dedicated Hosts - AWS

Azure Dedicated Host - Private Cloud | Microsoft Azure

Dome Homes, NJ

575 Atsion Rd - Google Maps

575 Atsion Rd, Vincentown, NJ 08088 | Zillow

575 Atsion Rd, Vincentown, NJ 08088 | Trulia

141 Powell Place Rd, Tabernacle, NJ 08088 | MLS# 1004808008 | Redfin

Once considered a home of the future, this unique geodesic dome can be yours for $575K - nj.com

Natural Spaces Domes - Geodesic Dome Homes

Vector databases for AI embeddings

Sentence embedding - Wikipedia

In natural language processing, a sentence embedding refers to a numeric representation of a sentence in the form of a vector of real numbers which encodes meaningful semantic information.

Vector database - Wikipedia

A vector database management system (VDBMS) or simply vector database or vector store is a database that can store vectors (fixed-length lists of numbers) along with other data items. Vector databases typically implement one or more Approximate Nearest Neighbor (ANN) algorithms,[1][2] so that one can search the database with a query vector to retrieve the closest matching database records.

Name	License
Apache Cassandra[7][8]	Apache License 2.0
Chroma[9][10]	Apache License 2.0[11]
Azure Cosmos DB Vector Database Extension[12]	Proprietary (Managed Service)
Couchbase[13][14]	BSL 1.1[15]
Elasticsearch[16]	Server Side Public License, Elastic License[17]
FAISS[18]	MIT License[19]
Infinity[20][21][22]	Apache License 2.0
LlamaIndex[23]	MIT License[24]
Milvus[25][26]	Apache License 2.0
MongoDB Atlas[27]	Server Side Public License (Managed service)
OpenSearch[28][29][30]	Apache License 2.0[31]
Pinecone[32]	Proprietary (Managed Service)
Postgres with pgvector[33]	PostgreSQL License[34]
Qdrant[35]	Apache License 2.0[36]
Redis Stack[37][38]	Redis Source Available License[39]
SurrealDB[40]	BSL 1.1[41]
Vespa[42]	Apache License 2.0[43]
Weaviate[44]	BSD 3-Clause[45]

Vector databases can be used for similarity search, multi-modal search, recommendations engines, large language models (LLMs), etc

vector databases

What is a Vector Database & How Does it Work? Use Cases + Examples | Pinecone

A vector database indexes and stores vector embeddings for fast retrieval and similarity search, with capabilities like CRUD operations, metadata filtering, horizontal scaling, and serveless.

AI (LLMs) rely on vector embeddings, a type of vector data representation that carries within it semantic information that’s critical for the AI to gain understanding and maintain a long-term memory they can draw upon when executing complex tasks.

The vector database to build knowledgeable AI | Pinecone

Pinecone serverless lets you deliver remarkable GenAI applications faster, at up to 50x lower cost.

faiss.ai: Faiss Documentation

facebookresearch/faiss: A library for efficient similarity search and clustering of dense vectors.

@Github, MIT license, by Facebook, C++ & Python

milvus-io/milvus: A cloud-native vector database, storage for next generation AI applications

@Github, Apache, GoLang

Milvus is an open-source vector database built to power embedding similarity search and AI applications. 

Milvus Architecture Overview Milvus documentation

courses on Udemy

Course: Master Vector Database with Python for AI & LLM Use Cases | Udemy Business

"Learn Vector Database using Python, Pinecone, LangChain, Open AI, Hugging Face and build out AI, ML , Chat applications" 7.5h
by Dr. KM Mohsin

Introduction to Milvus (Vector Database) Using Python | Udemy Business

1.5h

Learn LangChain, Pinecone & OpenAI: Build Next-Gen LLM Apps | Udemy Business

Course: LangChain- Develop LLM powered applications with LangChain | Udemy Business

FAISS local vectorstore

tutorials

a good brief explanation of LLMs (AI transformers models), embeddings, "attention", with examples

Large language models - Training | Microsoft Learn