Tuesday, December 26, 2023

"Chroma": Vector Database for ML/AI

podcast: The Cloudcast: Intro to Vector Databases

chroma-core/chroma: the AI-native open-source embedding database @GitHub
Apache license; Go + Python + Jupyter + TypeScript

pip install chromadb # python client
# for javascript, npm install chromadb!
# for client-server mode, chroma run --path /chroma_db_path


What are embeddings?

  • Read the guide from OpenAI
  • Literal: Embedding something turns it from image/text/audio into a list of numbers. 🖼️ or 📄 => [1.2, 2.1, ....]. This process makes documents "understandable" to a machine learning model.
  • By analogy: An embedding represents the essence of a document. This enables documents and queries with the same essence to be "near" each other and therefore easy to find.
  • Technical: An embedding is the latent-space position of a document at a layer of a deep neural network. For models trained specifically to embed data, this is the last layer.
  • A small example: If you search your photos for "famous bridge in San Francisco". By embedding this query and comparing it to the embeddings of your photos and their metadata - it should return photos of the Golden Gate Bridge.

Embeddings databases (also known as vector databases) store embeddings and allow you to search by nearest neighbors rather than by substrings like a traditional database. By default, Chroma uses Sentence Transformers to embed for you but you can also use OpenAI embeddings, Cohere (multilingual) embeddings, or your own.

tryChroma.com (+$18M investment)

"the AI-native open-source embedding database"

No comments: