mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-08 04:54:38 +00:00
chore: disable openai_embeddings on inference=remote::llama-openai-compat (#3704)
# What does this PR do? api.llama.com does not provide embedding models, this makes that clear ## Test Plan ci
This commit is contained in:
parent
ae74b31ae3
commit
de9940c697
1 changed files with 11 additions and 1 deletions
|
@ -5,7 +5,7 @@
|
||||||
# the root directory of this source tree.
|
# the root directory of this source tree.
|
||||||
from typing import Any
|
from typing import Any
|
||||||
|
|
||||||
from llama_stack.apis.inference.inference import OpenAICompletion
|
from llama_stack.apis.inference.inference import OpenAICompletion, OpenAIEmbeddingsResponse
|
||||||
from llama_stack.log import get_logger
|
from llama_stack.log import get_logger
|
||||||
from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
|
from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
|
||||||
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
||||||
|
@ -56,3 +56,13 @@ class LlamaCompatInferenceAdapter(OpenAIMixin):
|
||||||
suffix: str | None = None,
|
suffix: str | None = None,
|
||||||
) -> OpenAICompletion:
|
) -> OpenAICompletion:
|
||||||
raise NotImplementedError()
|
raise NotImplementedError()
|
||||||
|
|
||||||
|
async def openai_embeddings(
|
||||||
|
self,
|
||||||
|
model: str,
|
||||||
|
input: str | list[str],
|
||||||
|
encoding_format: str | None = "float",
|
||||||
|
dimensions: int | None = None,
|
||||||
|
user: str | None = None,
|
||||||
|
) -> OpenAIEmbeddingsResponse:
|
||||||
|
raise NotImplementedError()
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue