feat: add matryoshka embedding truncation #6606
+124
−10
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,37 @@ | ||
| import { EmbeddingsInterface } from '@langchain/core/embeddings' | ||
| import { applyMatryoshkaTruncation } from './matryoshkaEmbeddings' | ||
|
|
||
| const makeEmbeddings = (): EmbeddingsInterface<number[]> => ({ | ||
| embedDocuments: jest.fn(async () => [ | ||
| [1, 2, 3, 4], | ||
| [5, 6, 7, 8] | ||
| ]), | ||
| embedQuery: jest.fn(async () => [9, 10, 11, 12]) | ||
| }) | ||
|
|
||
| describe('applyMatryoshkaTruncation', () => { | ||
| it('returns the original embeddings when no truncate dimension is configured', async () => { | ||
| const embeddings = makeEmbeddings() | ||
| const result = applyMatryoshkaTruncation(embeddings, undefined) | ||
|
|
||
| expect(result).toBe(embeddings) | ||
| await expect(result.embedQuery('hello')).resolves.toEqual([9, 10, 11, 12]) | ||
| }) | ||
|
|
||
| it('truncates document and query embeddings to the configured dimension', async () => { | ||
| const embeddings = makeEmbeddings() | ||
| const result = applyMatryoshkaTruncation(embeddings, '2') | ||
|
|
||
| await expect(result.embedDocuments(['a', 'b'])).resolves.toEqual([ | ||
| [1, 2], | ||
| [5, 6] | ||
| ]) | ||
| await expect(result.embedQuery('hello')).resolves.toEqual([9, 10]) | ||
| }) | ||
|
|
||
| it('rejects invalid truncate dimensions', () => { | ||
| expect(() => applyMatryoshkaTruncation(makeEmbeddings(), '0')).toThrow('Matryoshka truncate dimension must be a positive integer') | ||
| expect(() => applyMatryoshkaTruncation(makeEmbeddings(), '2.5')).toThrow('Matryoshka truncate dimension must be a positive integer') | ||
| expect(() => applyMatryoshkaTruncation(makeEmbeddings(), 'abc')).toThrow('Matryoshka truncate dimension must be a positive integer') | ||
| }) | ||
| }) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,35 @@ | ||
| import { EmbeddingsInterface } from '@langchain/core/embeddings' | ||
|
|
||
| export const MATRYOSHKA_TRUNCATE_DIMENSIONS = 'matryoshkaTruncateDimensions' | ||
|
|
||
| const parseTruncateDimension = (value: unknown): number | undefined => { | ||
| if (value === undefined || value === null || value === '') return undefined | ||
|
|
||
| const dimension = typeof value === 'number' ? value : Number(value) | ||
| if (!Number.isInteger(dimension) || dimension <= 0) { | ||
| throw new Error('Matryoshka truncate dimension must be a positive integer') | ||
| } | ||
|
|
||
| return dimension | ||
| } | ||
|
|
||
| const truncateVector = (vector: number[], dimension: number): number[] => vector.slice(0, dimension) | ||
|
|
||
| export const applyMatryoshkaTruncation = <T extends EmbeddingsInterface<number[]>>(embeddings: T, truncateDimensions: unknown): T => { | ||
| const dimension = parseTruncateDimension(truncateDimensions) | ||
| if (!dimension) return embeddings | ||
|
|
||
| const wrappedEmbeddings = Object.create(embeddings) as T | ||
|
|
||
| wrappedEmbeddings.embedDocuments = async (documents: string[]): Promise<number[][]> => { | ||
| const vectors = await embeddings.embedDocuments(documents) | ||
| return vectors.map((vector) => truncateVector(vector, dimension)) | ||
| } | ||
|
|
||
| wrappedEmbeddings.embedQuery = async (document: string): Promise<number[]> => { | ||
| const vector = await embeddings.embedQuery(document) | ||
| return truncateVector(vector, dimension) | ||
| } | ||
|
|
||
| return wrappedEmbeddings | ||
|
Comment on lines
+22
to
+34
Contributor
There was a problem hiding this comment. Using Since the embedding instance is created fresh for each operation and is not shared globally, directly monkey-patching the methods on the original const originalEmbedDocuments = embeddings.embedDocuments.bind(embeddings)
const originalEmbedQuery = embeddings.embedQuery.bind(embeddings)
embeddings.embedDocuments = async (documents: string[]): Promise<number[][]> => {
const vectors = await originalEmbedDocuments(documents)
return vectors.map((vector) => truncateVector(vector, dimension))
}
embeddings.embedQuery = async (document: string): Promise<number[]> => {
const vector = await originalEmbedQuery(document)
return truncateVector(vector, dimension)
}
return embeddings |
||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
According to the general rules, loose equality (
== null) should be used as a standard idiom for a 'nullish' check that covers bothnullandundefined.References
== null) as a standard idiom for a 'nullish' check that covers both 'null' and 'undefined'.