mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
840ad75fe9
# What does this PR do? Extract API definitions and provider specifications into a standalone llama-stack-api package that can be published to PyPI independently of the main llama-stack server. see: https://github.com/llamastack/llama-stack/pull/2978 and https://github.com/llamastack/llama-stack/pull/2978#issuecomment-3145115942 Motivation External providers currently import from llama-stack, which overrides the installed version and causes dependency conflicts. This separation allows external providers to: - Install only the type definitions they need without server dependencies - Avoid version conflicts with the installed llama-stack package - Be versioned and released independently This enables us to re-enable external provider module tests that were previously blocked by these import conflicts. Changes - Created llama-stack-api package with minimal dependencies (pydantic, jsonschema) - Moved APIs, providers datatypes, strong_typing, and schema_utils - Updated all imports from llama_stack.* to llama_stack_api.* - Configured local editable install for development workflow - Updated linting and type-checking configuration for both packages Next Steps - Publish llama-stack-api to PyPI - Update external provider dependencies - Re-enable external provider module tests Pre-cursor PRs to this one: - #4093 - #3954 - #4064 These PRs moved key pieces _out_ of the Api pkg, limiting the scope of change here. relates to #3237 ## Test Plan Package builds successfully and can be imported independently. All pre-commit hooks pass with expected exclusions maintained. --------- Signed-off-by: Charlie Doern <cdoern@redhat.com>
70 lines
2.6 KiB
Python
70 lines
2.6 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 types import SimpleNamespace
|
|
from unittest.mock import AsyncMock, PropertyMock, patch
|
|
|
|
from llama_stack_api import OpenAIChatCompletionRequestWithExtraBody
|
|
|
|
from llama_stack.providers.remote.inference.bedrock.bedrock import BedrockInferenceAdapter
|
|
from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig
|
|
|
|
|
|
def test_can_create_adapter():
|
|
config = BedrockConfig(api_key="test-key", region_name="us-east-1")
|
|
adapter = BedrockInferenceAdapter(config=config)
|
|
|
|
assert adapter is not None
|
|
assert adapter.config.region_name == "us-east-1"
|
|
assert adapter.get_api_key() == "test-key"
|
|
|
|
|
|
def test_different_aws_regions():
|
|
# just check a couple regions to verify URL construction works
|
|
config = BedrockConfig(api_key="key", region_name="us-east-1")
|
|
adapter = BedrockInferenceAdapter(config=config)
|
|
assert adapter.get_base_url() == "https://bedrock-runtime.us-east-1.amazonaws.com/openai/v1"
|
|
|
|
config = BedrockConfig(api_key="key", region_name="eu-west-1")
|
|
adapter = BedrockInferenceAdapter(config=config)
|
|
assert adapter.get_base_url() == "https://bedrock-runtime.eu-west-1.amazonaws.com/openai/v1"
|
|
|
|
|
|
async def test_basic_chat_completion():
|
|
"""Test basic chat completion works with OpenAIMixin"""
|
|
config = BedrockConfig(api_key="k", region_name="us-east-1")
|
|
adapter = BedrockInferenceAdapter(config=config)
|
|
|
|
class FakeModelStore:
|
|
async def has_model(self, model_id):
|
|
return True
|
|
|
|
async def get_model(self, model_id):
|
|
return SimpleNamespace(provider_resource_id="meta.llama3-1-8b-instruct-v1:0")
|
|
|
|
adapter.model_store = FakeModelStore()
|
|
|
|
fake_response = SimpleNamespace(
|
|
id="chatcmpl-123",
|
|
choices=[SimpleNamespace(message=SimpleNamespace(content="Hello!", role="assistant"), finish_reason="stop")],
|
|
)
|
|
|
|
mock_create = AsyncMock(return_value=fake_response)
|
|
|
|
class FakeClient:
|
|
def __init__(self):
|
|
self.chat = SimpleNamespace(completions=SimpleNamespace(create=mock_create))
|
|
|
|
with patch.object(type(adapter), "client", new_callable=PropertyMock, return_value=FakeClient()):
|
|
params = OpenAIChatCompletionRequestWithExtraBody(
|
|
model="llama3-1-8b",
|
|
messages=[{"role": "user", "content": "hello"}],
|
|
stream=False,
|
|
)
|
|
response = await adapter.openai_chat_completion(params=params)
|
|
|
|
assert response.id == "chatcmpl-123"
|
|
assert mock_create.await_count == 1
|