mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-11 13:44:38 +00:00
0066d986c5
# What does this PR do? use SecretStr for OpenAIMixin providers - RemoteInferenceProviderConfig now has auth_credential: SecretStr - the default alias is api_key (most common name) - some providers override to use api_token (RunPod, vLLM, Databricks) - some providers exclude it (Ollama, TGI, Vertex AI) addresses #3517 ## Test Plan ci w/ new tests
36 lines
1.7 KiB
Python
36 lines
1.7 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 collections.abc import Iterable
|
|
|
|
from anthropic import AsyncAnthropic
|
|
|
|
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
|
|
|
from .config import AnthropicConfig
|
|
|
|
|
|
class AnthropicInferenceAdapter(OpenAIMixin):
|
|
config: AnthropicConfig
|
|
|
|
provider_data_api_key_field: str = "anthropic_api_key"
|
|
# source: https://docs.claude.com/en/docs/build-with-claude/embeddings
|
|
# TODO: add support for voyageai, which is where these models are hosted
|
|
# embedding_model_metadata = {
|
|
# "voyage-3-large": {"embedding_dimension": 1024, "context_length": 32000}, # supports dimensions 256, 512, 1024, 2048
|
|
# "voyage-3.5": {"embedding_dimension": 1024, "context_length": 32000}, # supports dimensions 256, 512, 1024, 2048
|
|
# "voyage-3.5-lite": {"embedding_dimension": 1024, "context_length": 32000}, # supports dimensions 256, 512, 1024, 2048
|
|
# "voyage-code-3": {"embedding_dimension": 1024, "context_length": 32000}, # supports dimensions 256, 512, 1024, 2048
|
|
# "voyage-finance-2": {"embedding_dimension": 1024, "context_length": 32000},
|
|
# "voyage-law-2": {"embedding_dimension": 1024, "context_length": 16000},
|
|
# "voyage-multimodal-3": {"embedding_dimension": 1024, "context_length": 32000},
|
|
# }
|
|
|
|
def get_base_url(self):
|
|
return "https://api.anthropic.com/v1"
|
|
|
|
async def list_provider_model_ids(self) -> Iterable[str]:
|
|
return [m.id async for m in AsyncAnthropic(api_key=self.get_api_key()).models.list()]
|