# LLM embeddings Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/llm-embeddings
> Markdown URL: https://aitinkerers.org/technologies/llm-embeddings.md
> Technology record last updated: 2026-03-20T03:48:21Z
> Generated: 2026-09-22T05:46:09Z

LLM embeddings are dense vector representations: they convert text into high-dimensional float arrays, enabling machines to process semantic meaning for tasks like RAG.

LLM embeddings are the core mechanism for semantic understanding, transforming raw text—words, phrases, or documents—into dense numerical vectors. These vectors, often with 1536 or 3072 dimensions (e.g., OpenAI’s `text-embedding-3-small`), capture the conceptual relatedness of data. By calculating vector distance (cosine similarity), systems identify semantic similarity, not just keyword matches. This capability is critical for modern AI applications: powering highly accurate semantic search, enabling efficient data clustering, and serving as the foundation for Retrieval-Augmented Generation (RAG) workflows.

- Official technology site: https://platform.openai.com/docs/guides/embeddings
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Mapping AI Companies](https://boston.aitinkerers.org/talks/rsvp_oj3AYSHa9Nc)

We know about the impact of GPUs on AI. Visual cortex is our brain's GPU. It's been empirically proven that people who can visualize math, solve problems faster. So, we're all trying to make sense of a vast number of companies and projects popping up in AI. But search gives us 1-dimensional lists. We want spaces, landscapes, galaxies of projects to better understand what's going on. I'll show a 1-day hack we did to map all YC companies into a galaxy, and the code is on GitHub. We used LLM embeddings to both facilitate querying as well as visualization. Let's build galaxy maps!

- Event context: AI Tinkerers September Meetup Sponsored by BasisTech — 2024-09-23 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_oj3AYSHa9Nc

## Related Technologies

- [GitHub](https://aitinkerers.org/technologies/github) ([Markdown](https://aitinkerers.org/technologies/github.md)) — 74 public demos
- [GPUs](https://aitinkerers.org/technologies/gpus) ([Markdown](https://aitinkerers.org/technologies/gpus.md)) — 5 public demos
- [Visualization](https://aitinkerers.org/technologies/visualization) ([Markdown](https://aitinkerers.org/technologies/visualization.md)) — 3 public demos