phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

fix(api): update embeddings signature so inputs and outputs list align (#1161)

Browse source 
See Issue #922 

The change is slightly backwards incompatible but no callsite (in our
client codebases or stack-apps) every passes a depth-2
`List[List[InterleavedContentItem]]` (which is now disallowed.)

## Test Plan

```bash
$ 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
```

Also ran `tests/client-sdk/inference/test_embeddings.py`
This commit is contained in:
Ashwin Bharambe 2025-02-20 21:43:13 -08:00 • committed by GitHub
parent cfa752fc92
commit 6f9d622340
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 85 additions and 41 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/apis/inference/inference.py
View file

@ -20,7 +20,7 @@ from typing import (
from pydantic import BaseModel, Field, field_validator
from typing_extensions import Annotated
from llama_stack.apis.common.content_types import ContentDelta, InterleavedContent
from llama_stack.apis.common.content_types import ContentDelta, InterleavedContent, InterleavedContentItem
from llama_stack.apis.models import Model
from llama_stack.apis.telemetry.telemetry import MetricResponseMixin
from llama_stack.models.llama.datatypes import (
@ -481,12 +481,12 @@ class Inference(Protocol):
async def embeddings(
self,
model_id: str,
contents: List[InterleavedContent],
contents: List[str] | List[InterleavedContentItem],
) -> EmbeddingsResponse:
"""Generate embeddings for content pieces using the specified model.
:param model_id: The identifier of the model to use. The model must be an embedding model registered with Llama Stack and available via the /models endpoint.
:param contents: List of contents to generate embeddings for. Note that content can be multimodal. The behavior depends on the model and provider. Some models may only support text.
:param contents: List of contents to generate embeddings for. Each content can be a string or an InterleavedContentItem (and hence can be multimodal). The behavior depends on the model and provider. Some models may only support text.
:returns: An array of embeddings, one for each content. Each embedding is a list of floats. The dimensionality of the embedding is model-specific; you can check model metadata using /models/{model_id}
"""
...