mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-17 13:22:36 +00:00
d362d2d740
This PR adds the ability to generate embeddings in all supported inference providers. ``` pytest -v -s llama_stack/providers/tests/inference/test_embeddings.py -k "bedrock" --inference-model="amazon.titan-embed-text-v2:0" --env EMBEDDING_DIMENSION=1024 pytest -v -s -k "vllm" --inferrence-model="intfloat/e5-mistral-7b-instruct" llama_stack/providers/tests/inference/test_embeddings.py --env EMBEDDING_DIMENSION=4096 --env VLLM_URL="http://localhost:9798/v1" pytest -v -s --inference-model="nomic-ai/nomic-embed-text-v1.5" llama_stack/providers/tests/inference/test_embeddings.py -k "fireworks" --env FIREWORKS_API_KEY=<API_KEY>--env EMBEDDING_DIMENSION=128 pytest -v -s --inference-model="togethercomputer/m2-bert-80M-2k-retrieval" llama_stack/providers/tests/inference/test_embeddings.py -k "together" --env TOGETHER_API_KEY=<API_KEY>--env EMBEDDING_DIMENSION=768 pytest -v -s -k "ollama" --inference-model="all-minilm:v8" llama_stack/providers/tests/inference/test_embeddings.py --env EMBEDDING_DIMENSION=384 torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="sentence-transformers/all-MiniLM-L6-v2" llama_stack/providers/tests/inference/test_embeddings.py --env EMBEDDING_DIMENSION=384 ```
74 lines
2.2 KiB
Python
74 lines
2.2 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from enum import Enum
|
|
from typing import Any, Dict, List, Literal, Optional, Protocol, runtime_checkable
|
|
|
|
from llama_models.schema_utils import json_schema_type, webmethod
|
|
from pydantic import BaseModel, ConfigDict, Field
|
|
|
|
from llama_stack.apis.resource import Resource, ResourceType
|
|
from llama_stack.providers.utils.telemetry.trace_protocol import trace_protocol
|
|
|
|
|
|
class CommonModelFields(BaseModel):
|
|
metadata: Dict[str, Any] = Field(
|
|
default_factory=dict,
|
|
description="Any additional metadata for this model",
|
|
)
|
|
|
|
|
|
class ModelType(Enum):
|
|
llm = "llm"
|
|
embedding_model = "embedding"
|
|
|
|
|
|
@json_schema_type
|
|
class Model(CommonModelFields, Resource):
|
|
type: Literal[ResourceType.model.value] = ResourceType.model.value
|
|
|
|
@property
|
|
def model_id(self) -> str:
|
|
return self.identifier
|
|
|
|
@property
|
|
def provider_model_id(self) -> str:
|
|
return self.provider_resource_id
|
|
|
|
model_config = ConfigDict(protected_namespaces=())
|
|
|
|
model_type: ModelType = Field(default=ModelType.llm)
|
|
|
|
|
|
class ModelInput(CommonModelFields):
|
|
model_id: str
|
|
provider_id: Optional[str] = None
|
|
provider_model_id: Optional[str] = None
|
|
model_type: Optional[ModelType] = ModelType.llm
|
|
model_config = ConfigDict(protected_namespaces=())
|
|
|
|
|
|
@runtime_checkable
|
|
@trace_protocol
|
|
class Models(Protocol):
|
|
@webmethod(route="/models/list", method="GET")
|
|
async def list_models(self) -> List[Model]: ...
|
|
|
|
@webmethod(route="/models/get", method="GET")
|
|
async def get_model(self, identifier: str) -> Optional[Model]: ...
|
|
|
|
@webmethod(route="/models/register", method="POST")
|
|
async def register_model(
|
|
self,
|
|
model_id: str,
|
|
provider_model_id: Optional[str] = None,
|
|
provider_id: Optional[str] = None,
|
|
metadata: Optional[Dict[str, Any]] = None,
|
|
model_type: Optional[ModelType] = None,
|
|
) -> Model: ...
|
|
|
|
@webmethod(route="/models/unregister", method="POST")
|
|
async def unregister_model(self, model_id: str) -> None: ...
|