kylefang/chroma
1
0
Fork 0
mirror of https://github.com/placeholder-soft/chroma.git synced 2026-04-30 12:51:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

more

Browse Source
This commit is contained in:
Jeffrey Huber
2023-02-12 07:33:35 -08:00
parent 8c656d4525
commit 437e4c6b6d
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@@ -56,8 +56,9 @@ Chroma is a rapidly developing project. We welcome PR contributors and ideas for
## Embeddings?
What are embeddings?
- [Read the guide from OpenAI](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings)
- __Literal__: Embedding something turns it from image/text/audio into a list of numbers. 🖼️/📄 => `[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.
- __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". Through embedding the photo and it's metadata - it should return photos of the Golden Gate Bridge.