phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-05 20:27:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore(api): remove deprecated embeddings impls

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-02 02:02:02 -04:00
parent 478b4ff1e6
commit 30998fd1ff
20 changed files with 3 additions and 927 deletions
Download patch file Download diff file Expand all files Collapse all files

22
llama_stack/apis/inference/inference.py
View file

@ -17,7 +17,7 @@ from typing import (
from pydantic import BaseModel, Field, field_validator
from typing_extensions import TypedDict
from llama_stack.apis.common.content_types import ContentDelta, InterleavedContent, InterleavedContentItem
from llama_stack.apis.common.content_types import ContentDelta, InterleavedContent
from llama_stack.apis.common.responses import Order
from llama_stack.apis.models import Model
from llama_stack.apis.telemetry import MetricResponseMixin
@ -1135,26 +1135,6 @@ class InferenceProvider(Protocol):
raise NotImplementedError("Batch chat completion is not implemented")
return # this is so mypy's safe-super rule will consider the method concrete
@webmethod(route="/inference/embeddings", method="POST")
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> 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. 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.
:param output_dimension: (Optional) Output dimensionality for the embeddings. Only supported by Matryoshka models.
:param text_truncation: (Optional) Config for how to truncate text for embedding when text is longer than the model's max sequence length.
:param task_type: (Optional) How is the embedding being used? This is only supported by asymmetric embedding models.
: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}.
"""
...
@webmethod(route="/inference/rerank", method="POST", experimental=True)
async def rerank(
self,

23
llama_stack/core/routers/inference.py
View file

@ -16,7 +16,6 @@ from pydantic import Field, TypeAdapter
from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
)
from llama_stack.apis.common.errors import ModelNotFoundError, ModelTypeError
from llama_stack.apis.inference import (
@ -28,8 +27,6 @@ from llama_stack.apis.inference import (
CompletionMessage,
CompletionResponse,
CompletionResponseStreamChunk,
EmbeddingsResponse,
EmbeddingTaskType,
Inference,
ListOpenAIChatCompletionResponse,
LogProbConfig,
@ -50,7 +47,6 @@ from llama_stack.apis.inference import (
ResponseFormat,
SamplingParams,
StopReason,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -347,25 +343,6 @@ class InferenceRouter(Inference):
provider = await self.routing_table.get_provider_impl(model_id)
return await provider.batch_completion(model_id, content_batch, sampling_params, response_format, logprobs)
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
logger.debug(f"InferenceRouter.embeddings: {model_id}")
await self._get_model(model_id, ModelType.embedding)
provider = await self.routing_table.get_provider_impl(model_id)
return await provider.embeddings(
model_id=model_id,
contents=contents,
text_truncation=text_truncation,
output_dimension=output_dimension,
task_type=task_type,
)
async def openai_completion(
self,
model: str,

31
llama_stack/providers/remote/inference/bedrock/bedrock.py
View file

@ -11,21 +11,17 @@ from botocore.client import BaseClient
from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
)
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
ChatCompletionResponseStreamChunk,
EmbeddingsResponse,
EmbeddingTaskType,
Inference,
LogProbConfig,
Message,
OpenAIEmbeddingsResponse,
ResponseFormat,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -47,8 +43,6 @@ from llama_stack.providers.utils.inference.openai_compat import (
)
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
content_has_media,
interleaved_content_as_str,
)
from .models import MODEL_ENTRIES
@ -176,31 +170,6 @@ class BedrockInferenceAdapter(
),
}
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
model = await self.model_store.get_model(model_id)
embeddings = []
for content in contents:
assert not content_has_media(content), "Bedrock does not support media for embeddings"
input_text = interleaved_content_as_str(content)
input_body = {"inputText": input_text}
body = json.dumps(input_body)
response = self.client.invoke_model(
body=body,
modelId=model.provider_resource_id,
accept="application/json",
contentType="application/json",
)
response_body = json.loads(response.get("body").read())
embeddings.append(response_body.get("embedding"))
return EmbeddingsResponse(embeddings=embeddings)
async def openai_embeddings(
self,
model: str,

14
llama_stack/providers/remote/inference/cerebras/cerebras.py
View file

@ -10,21 +10,17 @@ from cerebras.cloud.sdk import AsyncCerebras
from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
)
from llama_stack.apis.inference import (
ChatCompletionRequest,
CompletionRequest,
CompletionResponse,
EmbeddingsResponse,
EmbeddingTaskType,
Inference,
LogProbConfig,
Message,
OpenAIEmbeddingsResponse,
ResponseFormat,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -187,16 +183,6 @@ class CerebrasInferenceAdapter(
**get_sampling_options(request.sampling_params),
}
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
raise NotImplementedError()
async def openai_embeddings(
self,
model: str,

14
llama_stack/providers/remote/inference/databricks/databricks.py
View file

@ -10,20 +10,16 @@ from openai import OpenAI
from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
)
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
EmbeddingsResponse,
EmbeddingTaskType,
Inference,
LogProbConfig,
Message,
OpenAIEmbeddingsResponse,
ResponseFormat,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -147,16 +143,6 @@ class DatabricksInferenceAdapter(
**get_sampling_options(request.sampling_params),
}
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
raise NotImplementedError()
async def openai_embeddings(
self,
model: str,

31
llama_stack/providers/remote/inference/fireworks/fireworks.py
View file

@ -12,15 +12,12 @@ from openai import AsyncOpenAI
from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
)
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
CompletionRequest,
CompletionResponse,
EmbeddingsResponse,
EmbeddingTaskType,
Inference,
LogProbConfig,
Message,
@ -33,7 +30,6 @@ from llama_stack.apis.inference import (
ResponseFormat,
ResponseFormatType,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -57,8 +53,6 @@ from llama_stack.providers.utils.inference.openai_compat import (
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
completion_request_to_prompt,
content_has_media,
interleaved_content_as_str,
request_has_media,
)
@ -261,31 +255,6 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProv
return params
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
model = await self.model_store.get_model(model_id)
kwargs = {}
if model.metadata.get("embedding_dimension"):
kwargs["dimensions"] = model.metadata.get("embedding_dimension")
assert all(not content_has_media(content) for content in contents), (
"Fireworks does not support media for embeddings"
)
response = self._get_client().embeddings.create(
model=model.provider_resource_id,
input=[interleaved_content_as_str(content) for content in contents],
**kwargs,
)
embeddings = [data.embedding for data in response.data]
return EmbeddingsResponse(embeddings=embeddings)
async def openai_embeddings(
self,
model: str,

59
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -11,8 +11,6 @@ from openai import NOT_GIVEN, APIConnectionError
from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
TextContentItem,
)
from llama_stack.apis.inference import (
ChatCompletionRequest,
@ -21,8 +19,6 @@ from llama_stack.apis.inference import (
CompletionRequest,
CompletionResponse,
CompletionResponseStreamChunk,
EmbeddingsResponse,
EmbeddingTaskType,
Inference,
LogProbConfig,
Message,
@ -31,7 +27,6 @@ from llama_stack.apis.inference import (
OpenAIEmbeddingUsage,
ResponseFormat,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
)
@ -155,60 +150,6 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference, ModelRegistryHelper):
# we pass n=1 to get only one completion
return convert_openai_completion_choice(response.choices[0])
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
if any(content_has_media(content) for content in contents):
raise NotImplementedError("Media is not supported")
#
# Llama Stack: contents = list[str] | list[InterleavedContentItem]
# ->
# OpenAI: input = str | list[str]
#
# we can ignore str and always pass list[str] to OpenAI
#
flat_contents = [content.text if isinstance(content, TextContentItem) else content for content in contents]
input = [content.text if isinstance(content, TextContentItem) else content for content in flat_contents]
provider_model_id = await self._get_provider_model_id(model_id)
extra_body = {}
if text_truncation is not None:
text_truncation_options = {
TextTruncation.none: "NONE",
TextTruncation.end: "END",
TextTruncation.start: "START",
}
extra_body["truncate"] = text_truncation_options[text_truncation]
if output_dimension is not None:
extra_body["dimensions"] = output_dimension
if task_type is not None:
task_type_options = {
EmbeddingTaskType.document: "passage",
EmbeddingTaskType.query: "query",
}
extra_body["input_type"] = task_type_options[task_type]
response = await self.client.embeddings.create(
model=provider_model_id,
input=input,
extra_body=extra_body,
)
#
# OpenAI: CreateEmbeddingResponse(data=[Embedding(embedding=list[float], ...)], ...)
# ->
# Llama Stack: EmbeddingsResponse(embeddings=list[list[float]])
#
return EmbeddingsResponse(embeddings=[embedding.embedding for embedding in response.data])
async def openai_embeddings(
self,
model: str,

27
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -17,7 +17,6 @@ from openai import AsyncOpenAI
from llama_stack.apis.common.content_types import (
ImageContentItem,
InterleavedContent,
InterleavedContentItem,
TextContentItem,
)
from llama_stack.apis.common.errors import UnsupportedModelError
@ -28,8 +27,6 @@ from llama_stack.apis.inference import (
CompletionRequest,
CompletionResponse,
CompletionResponseStreamChunk,
EmbeddingsResponse,
EmbeddingTaskType,
GrammarResponseFormat,
InferenceProvider,
JsonSchemaResponseFormat,
@ -44,7 +41,6 @@ from llama_stack.apis.inference import (
OpenAIResponseFormatParam,
ResponseFormat,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -76,9 +72,7 @@ from llama_stack.providers.utils.inference.openai_compat import (
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
completion_request_to_prompt,
content_has_media,
convert_image_content_to_url,
interleaved_content_as_str,
localize_image_content,
request_has_media,
)
@ -394,27 +388,6 @@ class OllamaInferenceAdapter(
async for chunk in process_chat_completion_stream_response(stream, request):
yield chunk
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
model = await self._get_model(model_id)
assert all(not content_has_media(content) for content in contents), (
"Ollama does not support media for embeddings"
)
response = await self.client.embed(
model=model.provider_resource_id,
input=[interleaved_content_as_str(content) for content in contents],
)
embeddings = response["embeddings"]
return EmbeddingsResponse(embeddings=embeddings)
async def register_model(self, model: Model) -> Model:
try:
model = await self.register_helper.register_model(model)

22
llama_stack/providers/remote/inference/passthrough/passthrough.py
View file

@ -14,8 +14,6 @@ from llama_stack.apis.inference import (
ChatCompletionResponse,
ChatCompletionResponseStreamChunk,
CompletionMessage,
EmbeddingsResponse,
EmbeddingTaskType,
Inference,
LogProbConfig,
Message,
@ -27,7 +25,6 @@ from llama_stack.apis.inference import (
OpenAIResponseFormatParam,
ResponseFormat,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -190,25 +187,6 @@ class PassthroughInferenceAdapter(Inference):
chunk = convert_to_pydantic(ChatCompletionResponseStreamChunk, chunk)
yield chunk
async def embeddings(
self,
model_id: str,
contents: list[InterleavedContent],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
client = self._get_client()
model = await self.model_store.get_model(model_id)
return await client.inference.embeddings(
model_id=model.provider_resource_id,
contents=contents,
text_truncation=text_truncation,
output_dimension=output_dimension,
task_type=task_type,
)
async def openai_embeddings(
self,
model: str,

10
llama_stack/providers/remote/inference/runpod/runpod.py
View file

@ -136,16 +136,6 @@ class RunpodInferenceAdapter(
**get_sampling_options(request.sampling_params),
}
async def embeddings(
self,
model: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
raise NotImplementedError()
async def openai_embeddings(
self,
model: str,

14
llama_stack/providers/remote/inference/tgi/tgi.py
View file

@ -11,14 +11,11 @@ from huggingface_hub import AsyncInferenceClient, HfApi
from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
)
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
CompletionRequest,
EmbeddingsResponse,
EmbeddingTaskType,
Inference,
LogProbConfig,
Message,
@ -26,7 +23,6 @@ from llama_stack.apis.inference import (
ResponseFormat,
ResponseFormatType,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -282,16 +278,6 @@ class _HfAdapter(
**self._build_options(request.sampling_params, request.response_format),
)
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
raise NotImplementedError()
async def openai_embeddings(
self,
model: str,

26
llama_stack/providers/remote/inference/together/together.py
View file

@ -12,14 +12,11 @@ from together import AsyncTogether
from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
)
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
CompletionRequest,
EmbeddingsResponse,
EmbeddingTaskType,
Inference,
LogProbConfig,
Message,
@ -32,7 +29,6 @@ from llama_stack.apis.inference import (
ResponseFormat,
ResponseFormatType,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -53,8 +49,6 @@ from llama_stack.providers.utils.inference.openai_compat import (
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
completion_request_to_prompt,
content_has_media,
interleaved_content_as_str,
request_has_media,
)
@ -235,26 +229,6 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
logger.debug(f"params to together: {params}")
return params
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
model = await self.model_store.get_model(model_id)
assert all(not content_has_media(content) for content in contents), (
"Together does not support media for embeddings"
)
client = self._get_client()
r = await client.embeddings.create(
model=model.provider_resource_id,
input=[interleaved_content_as_str(content) for content in contents],
)
embeddings = [item.embedding for item in r.data]
return EmbeddingsResponse(embeddings=embeddings)
async def openai_embeddings(
self,
model: str,

32
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -15,7 +15,6 @@ from openai.types.chat.chat_completion_chunk import (
from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
TextDelta,
ToolCallDelta,
ToolCallParseStatus,
@ -30,8 +29,6 @@ from llama_stack.apis.inference import (
CompletionRequest,
CompletionResponse,
CompletionResponseStreamChunk,
EmbeddingsResponse,
EmbeddingTaskType,
GrammarResponseFormat,
Inference,
JsonSchemaResponseFormat,
@ -47,7 +44,6 @@ from llama_stack.apis.inference import (
OpenAIResponseFormatParam,
ResponseFormat,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -78,8 +74,6 @@ from llama_stack.providers.utils.inference.openai_compat import (
)
from llama_stack.providers.utils.inference.prompt_adapter import (
completion_request_to_prompt,
content_has_media,
interleaved_content_as_str,
request_has_media,
)
@ -535,32 +529,6 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
**options,
}
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
self._lazy_initialize_client()
assert self.client is not None
model = await self._get_model(model_id)
kwargs = {}
assert model.model_type == ModelType.embedding
assert model.metadata.get("embedding_dimension")
kwargs["dimensions"] = model.metadata.get("embedding_dimension")
assert all(not content_has_media(content) for content in contents), "VLLM does not support media for embeddings"
response = await self.client.embeddings.create(
model=model.provider_resource_id,
input=[interleaved_content_as_str(content) for content in contents],
**kwargs,
)
embeddings = [data.embedding for data in response.data]
return EmbeddingsResponse(embeddings=embeddings)
async def openai_embeddings(
self,
model: str,

15
llama_stack/providers/remote/inference/watsonx/watsonx.py
View file

@ -11,13 +11,11 @@ from ibm_watson_machine_learning.foundation_models import Model
from ibm_watson_machine_learning.metanames import GenTextParamsMetaNames as GenParams
from openai import AsyncOpenAI
from llama_stack.apis.common.content_types import InterleavedContent, InterleavedContentItem
from llama_stack.apis.common.content_types import InterleavedContent
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
CompletionRequest,
EmbeddingsResponse,
EmbeddingTaskType,
GreedySamplingStrategy,
Inference,
LogProbConfig,
@ -30,7 +28,6 @@ from llama_stack.apis.inference import (
OpenAIResponseFormatParam,
ResponseFormat,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -249,16 +246,6 @@ class WatsonXInferenceAdapter(Inference, ModelRegistryHelper):
}
return params
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
raise NotImplementedError("embedding is not supported for watsonx")
async def openai_embeddings(
self,
model: str,

20
llama_stack/providers/utils/inference/embedding_mixin.py
View file

@ -14,16 +14,11 @@ if TYPE_CHECKING:
from sentence_transformers import SentenceTransformer
from llama_stack.apis.inference import (
EmbeddingsResponse,
EmbeddingTaskType,
InterleavedContentItem,
ModelStore,
OpenAIEmbeddingData,
OpenAIEmbeddingsResponse,
OpenAIEmbeddingUsage,
TextTruncation,
)
from llama_stack.providers.utils.inference.prompt_adapter import interleaved_content_as_str
EMBEDDING_MODELS = {}
@ -34,21 +29,6 @@ log = get_logger(name=__name__, category="providers::utils")
class SentenceTransformerEmbeddingMixin:
model_store: ModelStore
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
model = await self.model_store.get_model(model_id)
embedding_model = self._load_sentence_transformer_model(model.provider_resource_id)
embeddings = embedding_model.encode(
[interleaved_content_as_str(content) for content in contents], show_progress_bar=False
)
return EmbeddingsResponse(embeddings=embeddings)
async def openai_embeddings(
self,
model: str,

25
llama_stack/providers/utils/inference/litellm_openai_mixin.py
View file

@ -11,14 +11,11 @@ import litellm
from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
)
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
ChatCompletionResponseStreamChunk,
EmbeddingsResponse,
EmbeddingTaskType,
InferenceProvider,
JsonSchemaResponseFormat,
LogProbConfig,
@ -32,7 +29,6 @@ from llama_stack.apis.inference import (
OpenAIResponseFormatParam,
ResponseFormat,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -50,9 +46,6 @@ from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options,
prepare_openai_completion_params,
)
from llama_stack.providers.utils.inference.prompt_adapter import (
interleaved_content_as_str,
)
logger = get_logger(name=__name__, category="providers::utils")
@ -269,24 +262,6 @@ class LiteLLMOpenAIMixin(
)
return api_key
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
model = await self.model_store.get_model(model_id)
response = litellm.embedding(
model=self.get_litellm_model_name(model.provider_resource_id),
input=[interleaved_content_as_str(content) for content in contents],
)
embeddings = [data["embedding"] for data in response["data"]]
return EmbeddingsResponse(embeddings=embeddings)
async def openai_embeddings(
self,
model: str,