phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 16:12:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Support Tooling

Browse source
This commit is contained in:
Edward Ma 2024-12-02 13:38:54 -08:00
parent efd842d605
commit c0d9b81253
4 changed files with 151 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

20
llama_stack/providers/tests/inference/fixtures.py
View file

@ -20,6 +20,7 @@ from llama_stack.providers.remote.inference.bedrock import BedrockConfig
from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig
from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
from llama_stack.providers.remote.inference.ollama import OllamaImplConfig
from llama_stack.providers.remote.inference.sambanova import SambaNovaImplConfig
from llama_stack.providers.remote.inference.tgi import TGIImplConfig
from llama_stack.providers.remote.inference.together import TogetherImplConfig
from llama_stack.providers.remote.inference.vllm import VLLMInferenceAdapterConfig
@ -173,6 +174,24 @@ def inference_tgi() -> ProviderFixture:
)
@pytest.fixture(scope="session")
def inference_sambanova() -> ProviderFixture:
return ProviderFixture(
providers=[
Provider(
provider_id="sambanova",
provider_type="remote::sambanova",
config=SambaNovaImplConfig(
api_key=get_env_or_fail("SAMBANOVA_API_KEY"),
).model_dump(),
)
],
provider_data=dict(
sambanova_api_key=get_env_or_fail("SAMBANOVA_API_KEY"),
),
)
def get_model_short_name(model_name: str) -> str:
"""Convert model name to a short test identifier.
@ -208,6 +227,7 @@ INFERENCE_FIXTURES = [
"bedrock",
"nvidia",
"tgi",
"sambanova",
]

10
llama_stack/providers/tests/inference/test_prompt_adapter.py
View file

@ -24,7 +24,7 @@ class PrepareMessagesTests(unittest.IsolatedAsyncioTestCase):
UserMessage(content=content),
],
)
messages = chat_completion_request_to_messages(request)
messages = chat_completion_request_to_messages(request, MODEL)
self.assertEqual(len(messages), 2)
self.assertEqual(messages[-1].content, content)
self.assertTrue("Cutting Knowledge Date: December 2023" in messages[0].content)
@ -41,7 +41,7 @@ class PrepareMessagesTests(unittest.IsolatedAsyncioTestCase):
ToolDefinition(tool_name=BuiltinTool.brave_search),
],
)
messages = chat_completion_request_to_messages(request)
messages = chat_completion_request_to_messages(request, MODEL)
self.assertEqual(len(messages), 2)
self.assertEqual(messages[-1].content, content)
self.assertTrue("Cutting Knowledge Date: December 2023" in messages[0].content)
@ -69,7 +69,7 @@ class PrepareMessagesTests(unittest.IsolatedAsyncioTestCase):
],
tool_prompt_format=ToolPromptFormat.json,
)
messages = chat_completion_request_to_messages(request)
messages = chat_completion_request_to_messages(request, MODEL)
self.assertEqual(len(messages), 3)
self.assertTrue("Environment: ipython" in messages[0].content)
@ -99,7 +99,7 @@ class PrepareMessagesTests(unittest.IsolatedAsyncioTestCase):
),
],
)
messages = chat_completion_request_to_messages(request)
messages = chat_completion_request_to_messages(request, MODEL)
self.assertEqual(len(messages), 3)
self.assertTrue("Environment: ipython" in messages[0].content)
@ -121,7 +121,7 @@ class PrepareMessagesTests(unittest.IsolatedAsyncioTestCase):
ToolDefinition(tool_name=BuiltinTool.code_interpreter),
],
)
messages = chat_completion_request_to_messages(request)
messages = chat_completion_request_to_messages(request, MODEL)
self.assertEqual(len(messages), 2, messages)
self.assertTrue(messages[0].content.endswith(system_prompt))

2
llama_stack/providers/tests/inference/test_vision_inference.py
View file

@ -49,6 +49,7 @@ class TestVisionModelInference:
"remote::fireworks",
"remote::ollama",
"remote::vllm",
"remote::sambanova",
):
pytest.skip(
"Other inference providers don't support vision chat completion() yet"
@ -83,6 +84,7 @@ class TestVisionModelInference:
"remote::fireworks",
"remote::ollama",
"remote::vllm",
"remote::sambanova",
):
pytest.skip(
"Other inference providers don't support vision chat completion() yet"