mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-07 12:47:37 +00:00
d23ed26238
# What does this PR do? - implement get_api_key instead of relying on LiteLLMOpenAIMixin.get_api_key - remove use of LiteLLMOpenAIMixin - add default initialize/shutdown methods to OpenAIMixin - remove __init__s to allow proper pydantic construction - remove dead code from vllm adapter and associated / duplicate unit tests - update vllm adapter to use openaimixin for model registration - remove ModelRegistryHelper from fireworks & together adapters - remove Inference from nvidia adapter - complete type hints on embedding_model_metadata - allow extra fields on OpenAIMixin, for model_store, __provider_id__, etc - new recordings for ollama - enhance the list models error handling - update cerebras (remove cerebras-cloud-sdk) and anthropic (custom model listing) inference adapters - parametrized test_inference_client_caching - remove cerebras, databricks, fireworks, together from blanket mypy exclude - removed unnecessary litellm deps ## Test Plan ci
39 lines
1.8 KiB
Python
39 lines
1.8 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_api_key(self) -> str:
|
|
return self.config.api_key or ""
|
|
|
|
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()]
|