feat: Add /v1/embeddings endpoint to batches API #3384
+133
−5
Conversation
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
varshaprasad96
requested review from
ashwinb,
yanxi0830,
hardikjshah,
raghotham,
ehhuang,
terrytangyuan,
leseb,
bbrowning,
reluctantfuturist,
mattf and
slekkala1
as code owners
meta-cla
bot
added
the
CLA Signed
|
cc: @mattf can you take a look at this! Thanks! |
varshaprasad96
force-pushed
the
support/embeddings-api
branch
from
4037309 to
0a5f8ab
Compare
mattf
requested changes
Sep 9, 2025
| else: # /v1/embeddings | ||
| required_params = [ | ||
| ("model", str, "a string"), | ||
| ("input", str, "a string or array of strings"), |
| @@ -449,6 +454,18 @@ async def _validate_input(self, batch: BatchObject) -> tuple[list[BatchError], l | |||
| ) | |||
| ) | |||
| valid = False | |||
| elif param == "input" and batch.endpoint == "/v1/embeddings": | |||
There was a problem hiding this comment.
you can remove this and use (str, list) above
There was a problem hiding this comment.
The issue with (str, list) is, it causes a mypy type error:
llama_stack/providers/inline/batches/reference/batches.py:443: error: List item 1 has incompatible type "tuple[str, tuple[type[str], type[list[_T]]], str]"; expected "tuple[str, ABCMeta, str]" [list-item]
mypy expects a single type in the tuple, not a tuple of types. Which is why I've implemented it using str as the base type with a special case for validation.
There was a problem hiding this comment.
mypy infers the type for required_params the first time it appears -
required_params = [
("model", str, "a string"),
("prompt", str, "a string"), # TODO: allow prompt to be a list of strings??
]
effectively making it required_params: list[tuple[str, type, str]]
so the later required_params = [(..., (x, y), ...)] doesn't match the inferred type.
you can fix this by providing the type so mypy doesn't infer it, something like -
required_params: tuple[str, type | tuple, str] = [
("model", str, "a string"),
("prompt", str, "a string"), # TODO: allow prompt to be a list of strings??
]
This PR extends the Llama Stack Batches API to support the /v1/embeddings endpoint, enabling efficient batch processing of embedding requests alongside the existing /v1/chat/completions and /v1/completions support. Signed-off-by: Varsha Prasad Narsing <[email protected]>
varshaprasad96
force-pushed
the
support/embeddings-api
branch
from
0a5f8ab to
d156008
Compare
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.
What does this PR do?
This PR extends the Llama Stack Batches API to support the /v1/embeddings endpoint, enabling efficient batch processing of embedding requests alongside the existing /v1/chat/completions and /v1/completions support.
Closes: #3145
Test Plan