Use PyNNDescent and `nessvec` to index high dimensional vectors (word embeddings)
In this video, Hobson shows how to index high dimensional vectors like word embeddings using a new approximate nearest neighbor algorithm by Leland McInnes. Along the way you can see how to explore an unfamiliar Python package like PyNNDescent without ever having to leave the keyboard (tab-completio...
| Format: | eBook |
|---|---|
| Language: | English |
| Published: |
[Place of publication not identified]
Manning Publications
2022
|
| Edition: | [First edition] |
| Subjects: | |
| Online Access: | |
| Collection: | O'Reilly - Collection details see MPG.ReNa |
| Summary: | In this video, Hobson shows how to index high dimensional vectors like word embeddings using a new approximate nearest neighbor algorithm by Leland McInnes. Along the way you can see how to explore an unfamiliar Python package like PyNNDescent without ever having to leave the keyboard (tab-completion, `help()`, `?` operator) And you will see how to use `SpaCy` language models to retrieve all sorts of NLU tags for words, including word vectors |
|---|---|
| Physical Description: | 1 video file (49 min.) sound, color |