mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 18:00:36 +00:00
a078f089d9
Some checks failed
Integration Tests (Replay) / generate-matrix (push) Successful in 3s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Test Llama Stack Build / generate-matrix (push) Successful in 5s
Python Package Build Test / build (3.12) (push) Failing after 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 12s
Test llama stack list-deps / generate-matrix (push) Successful in 29s
Test Llama Stack Build / build-single-provider (push) Successful in 33s
Test llama stack list-deps / list-deps-from-config (push) Successful in 32s
UI Tests / ui-tests (22) (push) Successful in 39s
Test Llama Stack Build / build (push) Successful in 39s
Test llama stack list-deps / show-single-provider (push) Successful in 46s
Python Package Build Test / build (3.13) (push) Failing after 44s
Test External API and Providers / test-external (venv) (push) Failing after 44s
Vector IO Integration Tests / test-matrix (push) Failing after 56s
Test llama stack list-deps / list-deps (push) Failing after 47s
Unit Tests / unit-tests (3.12) (push) Failing after 1m42s
Unit Tests / unit-tests (3.13) (push) Failing after 1m55s
Test Llama Stack Build / build-ubi9-container-distribution (push) Successful in 2m0s
Test Llama Stack Build / build-custom-container-distribution (push) Successful in 2m2s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 2m42s
Pre-commit / pre-commit (push) Successful in 5m17s
# What does this PR do? the directory structure was src/llama-stack-api/llama_stack_api instead it should just be src/llama_stack_api to match the other packages. update the structure and pyproject/linting config --------- Signed-off-by: Charlie Doern <cdoern@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
69 lines
2.6 KiB
Python
69 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.providers.remote.inference.bedrock.bedrock import BedrockInferenceAdapter
|
|
from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig
|
|
from llama_stack_api import OpenAIChatCompletionRequestWithExtraBody
|
|
|
|
|
|
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
|