feat(api): Add options for supporting various embedding models #1192
Conversation
This file contains 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
ashwinb
requested review from
yanxi0830,
hardikjshah,
dltn,
raghotham,
dineshyv,
vladimirivic,
sixianyi0721,
ehhuang and
terrytangyuan
as code owners
facebook-github-bot
added
the
CLA Signed
This was
linked to
issues
Feb 21, 2025
ashwinb
changed the title
ashwinb
commented
Feb 21, 2025
|
|
||
| class EmbeddingOptions(BaseModel): | ||
| dimensions: Optional[int] = None | ||
| text_truncation: Optional[TextTruncation] = None |
There was a problem hiding this comment.
no image truncation is provided here, images are naturally pre-processed (which means resized / cropped) depending on the settings of each model typically. when a specific need arises to control this pre-processing, we may add an option here. cc @mattf
There was a problem hiding this comment.
@ehhuang default behavior should be to throw. is that communicated clearly by the value "None" or should it be an enum throw (or some other value)?
ashwinb
commented
Feb 21, 2025
| end = "end" | ||
|
|
||
|
|
||
| class EmbeddingContext(Enum): |
There was a problem hiding this comment.
is "Context" a good enough name? any better suggestion?
ehhuang
reviewed
Feb 21, 2025
5 tasks
ashwinb
commented
Feb 21, 2025
| @@ -482,11 +506,17 @@ async def embeddings( | |||
| self, | |||
| model_id: str, | |||
| contents: List[InterleavedContent], | |||
| text_truncation: Optional[TextTruncation] = TextTruncation.none, | |||
| dimensions: Optional[int] = None, | |||
There was a problem hiding this comment.
nitpicking: should this be output_dimensions? dimensionality?
ehhuang
approved these changes
Feb 21, 2025
Hoist options into the method args directly. Make TextTrunction.none be explicit. make text_truncation optional rename
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
We need to support:
Test Plan
$ cd llama_stack/providers/tests/inference $ pytest -s -v -k fireworks test_embeddings.py \ --inference-model nomic-ai/nomic-embed-text-v1.5 --env EMBEDDING_DIMENSION=784 $ pytest -s -v -k together test_embeddings.py \ --inference-model togethercomputer/m2-bert-80M-8k-retrieval --env EMBEDDING_DIMENSION=784 $ pytest -s -v -k ollama test_embeddings.py \ --inference-model all-minilm:latest --env EMBEDDING_DIMENSION=784