feat: add nvidia embedding implementation for new signature, task_type, output_dimention, text_truncation #1213
+161
−14
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
…put_dimention, text_truncation
mattf
requested review from
ashwinb,
yanxi0830,
hardikjshah,
dltn,
raghotham,
dineshyv,
vladimirivic,
sixianyi0721,
ehhuang and
terrytangyuan
as code owners
facebook-github-bot
added
the
CLA Signed
|
this is blocked by meta-llama/llama-stack-client-python#162 |
mattf
changed the title
ehhuang
reviewed
Feb 25, 2025
Comment on lines
151
to
158
| if text_truncation is not None: | ||
| text_truncation_options = { | ||
| TextTruncation.none: "NONE", | ||
| TextTruncation.end: "END", | ||
| TextTruncation.start: "START", | ||
| } | ||
| if text_truncation not in text_truncation_options: | ||
| raise ValueError(f"Invalid text_truncation: {text_truncation}") |
There was a problem hiding this comment.
We can move this validation here [1], so it applies to all providers.
[1]
There was a problem hiding this comment.
turns out fastapi will type validate before invoking the routers. i can remove this defensive code.
Comment on lines
164
to
170
| if task_type is not None: | ||
| task_type_options = { | ||
| EmbeddingTaskType.document: "passage", | ||
| EmbeddingTaskType.query: "query", | ||
| } | ||
| if task_type not in task_type_options: | ||
| raise ValueError(f"Invalid task_type: {task_type}") |
There was a problem hiding this comment.
also removing, will rely on fastapi request validation
| ) | ||
|
|
||
|
|
||
| @pytest.mark.xfail(reason="Only valid for model supporting dimension reduction") |
There was a problem hiding this comment.
is there a model we can use for testing this?
There was a problem hiding this comment.
edit: you can use baai/bge-m3. i've also updated the test instructions.
oops. yes, nvidia/llama-3.2-nv-embedqa-1b-v2, see https://docs.nvidia.com/nim/nemo-retriever/text-embedding/latest/support-matrix.html
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?
updates nvidia inference provider's embedding implementation to use new signature
add support for task_type, output_dimensions, text_truncation parameters
Test Plan
LLAMA_STACK_BASE_URL=http://localhost:8321 pytest -v tests/client-sdk/inference/test_embedding.py --embedding-model baai/bge-m3