Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Additional options native embeddings #23

Merged
merged 4 commits into from
Nov 7, 2023
Merged

Additional options native embeddings #23

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e4862ec
Update NativeEmbeddings.swift
Oct 30, 2023
6cf8342
update
Oct 30, 2023
a6a4dc2
Update Sources/SimilaritySearchKit/Core/Embeddings/Models/NativeEmbed…
BernhardEisvogel Nov 7, 2023
0a8e827
Update Sources/SimilaritySearchKit/Core/Embeddings/Models/NativeEmbed…
BernhardEisvogel Nov 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 20 additions & 6 deletions Sources/SimilaritySearchKit/Core/Embeddings/Models/NativeEmbeddings.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,26 +8,40 @@
import Foundation
import NaturalLanguage

public enum NativeEmbeddingType {
case wordEmbedding
case sentenceEmbedding
}

@available(macOS 11.0, iOS 15.0, *)
public class NativeEmbeddings: EmbeddingsProtocol {
public let model: ModelActor
public let tokenizer: any TokenizerProtocol

public init(language: NLLanguage = .english) {
public init(language: NLLanguage = .english, type: NativeEmbeddingType = .sentenceEmbedding) {
self.tokenizer = NativeTokenizer()
self.model = ModelActor(language: language)
self.model = ModelActor(language: language, type: type)
}

// MARK: - Dense Embeddings

public actor ModelActor {
private let model: NLEmbedding

init(language: NLLanguage) {
guard let nativeModel = NLEmbedding.sentenceEmbedding(for: language) else {
fatalError("Failed to load the Core ML model.")
init(language: NLLanguage, type:NativeEmbeddingType = .sentenceEmbedding) {
BernhardEisvogel marked this conversation as resolved.
Show resolved Hide resolved
switch type {
case .sentenceEmbedding:
guard let nativeModel = NLEmbedding.sentenceEmbedding(for: language) else {
fatalError("Failed to load the Core ML model.")
}
model = nativeModel
case .wordEmbedding:
guard let nativeModel = NLEmbedding.wordEmbedding(for: language) else {
fatalError("Failed to load the Core ML model.")
}
model = nativeModel
}
model = nativeModel

}

func vector(for sentence: String) -> [Float]? {
Expand Down