phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-15 09:36:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: move more tests, delete some providers tests (#1382)

Browse source 
Move unittests to tests/unittests. Gradually nuking tests from
providers/tests/ and unifying them into tests/api (which are e2e tests
using SDK types)

## Test Plan

`pytest -s -v tests/unittests/`
This commit is contained in:
Ashwin Bharambe 2025-03-03 20:28:34 -08:00 • committed by GitHub
parent e5ec68f66e
commit 86fc514abb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 6 additions and 142 deletions
Download patch file Download diff file Expand all files Collapse all files

29
llama_stack/providers/tests/inference/groq/test_init.py
View file

@ -1,29 +0,0 @@
# 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.
import pytest
from llama_stack.apis.inference import Inference
from llama_stack.providers.remote.inference.groq import get_adapter_impl
from llama_stack.providers.remote.inference.groq.config import GroqConfig
from llama_stack.providers.remote.inference.groq.groq import GroqInferenceAdapter
from llama_stack.providers.remote.inference.ollama import OllamaImplConfig
class TestGroqInit:
@pytest.mark.asyncio
async def test_raises_runtime_error_if_config_is_not_groq_config(self):
config = OllamaImplConfig(model="llama3.1-8b-8192")
with pytest.raises(RuntimeError):
await get_adapter_impl(config, None)
@pytest.mark.asyncio
async def test_returns_groq_adapter(self):
config = GroqConfig()
adapter = await get_adapter_impl(config, None)
assert type(adapter) is GroqInferenceAdapter
assert isinstance(adapter, Inference)

55
llama_stack/providers/tests/inference/test_embeddings.py
View file

@ -1,55 +0,0 @@
# 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.
import pytest
from llama_stack.apis.inference import EmbeddingsResponse
from llama_stack.apis.models import ModelType
# How to run this test:
# pytest -v -s llama_stack/providers/tests/inference/test_embeddings.py
class TestEmbeddings:
@pytest.mark.asyncio
async def test_embeddings(self, inference_model, inference_stack):
inference_impl, models_impl = inference_stack
model = await models_impl.get_model(inference_model)
if model.model_type != ModelType.embedding:
pytest.skip("This test is only applicable for embedding models")
response = await inference_impl.embeddings(
model_id=inference_model,
contents=["Hello, world!"],
)
assert isinstance(response, EmbeddingsResponse)
assert len(response.embeddings) > 0
assert all(isinstance(embedding, list) for embedding in response.embeddings)
assert all(isinstance(value, float) for embedding in response.embeddings for value in embedding)
@pytest.mark.asyncio
async def test_batch_embeddings(self, inference_model, inference_stack):
inference_impl, models_impl = inference_stack
model = await models_impl.get_model(inference_model)
if model.model_type != ModelType.embedding:
pytest.skip("This test is only applicable for embedding models")
texts = ["Hello, world!", "This is a test", "Testing embeddings"]
response = await inference_impl.embeddings(
model_id=inference_model,
contents=texts,
)
assert isinstance(response, EmbeddingsResponse)
assert len(response.embeddings) == len(texts)
assert all(isinstance(embedding, list) for embedding in response.embeddings)
assert all(isinstance(value, float) for embedding in response.embeddings for value in embedding)
embedding_dim = len(response.embeddings[0])
assert all(len(embedding) == embedding_dim for embedding in response.embeddings)

281
llama_stack/providers/tests/inference/test_prompt_adapter.py
View file

@ -1,281 +0,0 @@
# 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.
import unittest
from llama_stack.apis.inference import (
ChatCompletionRequest,
CompletionMessage,
StopReason,
SystemMessage,
ToolCall,
ToolConfig,
UserMessage,
)
from llama_stack.models.llama.datatypes import (
BuiltinTool,
ToolDefinition,
ToolParamDefinition,
ToolPromptFormat,
)
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_messages,
chat_completion_request_to_prompt,
)
MODEL = "Llama3.1-8B-Instruct"
MODEL3_2 = "Llama3.2-3B-Instruct"
class PrepareMessagesTests(unittest.IsolatedAsyncioTestCase):
async def test_system_default(self):
content = "Hello !"
request = ChatCompletionRequest(
model=MODEL,
messages=[
UserMessage(content=content),
],
)
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)
async def test_system_builtin_only(self):
content = "Hello !"
request = ChatCompletionRequest(
model=MODEL,
messages=[
UserMessage(content=content),
],
tools=[
ToolDefinition(tool_name=BuiltinTool.code_interpreter),
ToolDefinition(tool_name=BuiltinTool.brave_search),
],
)
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)
self.assertTrue("Tools: brave_search" in messages[0].content)
async def test_system_custom_only(self):
content = "Hello !"
request = ChatCompletionRequest(
model=MODEL,
messages=[
UserMessage(content=content),
],
tools=[
ToolDefinition(
tool_name="custom1",
description="custom1 tool",
parameters={
"param1": ToolParamDefinition(
param_type="str",
description="param1 description",
required=True,
),
},
)
],
tool_config=ToolConfig(tool_prompt_format=ToolPromptFormat.json),
)
messages = chat_completion_request_to_messages(request, MODEL)
self.assertEqual(len(messages), 3)
self.assertTrue("Environment: ipython" in messages[0].content)
self.assertTrue("Return function calls in JSON format" in messages[1].content)
self.assertEqual(messages[-1].content, content)
async def test_system_custom_and_builtin(self):
content = "Hello !"
request = ChatCompletionRequest(
model=MODEL,
messages=[
UserMessage(content=content),
],
tools=[
ToolDefinition(tool_name=BuiltinTool.code_interpreter),
ToolDefinition(tool_name=BuiltinTool.brave_search),
ToolDefinition(
tool_name="custom1",
description="custom1 tool",
parameters={
"param1": ToolParamDefinition(
param_type="str",
description="param1 description",
required=True,
),
},
),
],
)
messages = chat_completion_request_to_messages(request, MODEL)
self.assertEqual(len(messages), 3)
self.assertTrue("Environment: ipython" in messages[0].content)
self.assertTrue("Tools: brave_search" in messages[0].content)
self.assertTrue("Return function calls in JSON format" in messages[1].content)
self.assertEqual(messages[-1].content, content)
async def test_completion_message_encoding(self):
request = ChatCompletionRequest(
model=MODEL3_2,
messages=[
UserMessage(content="hello"),
CompletionMessage(
content="",
stop_reason=StopReason.end_of_turn,
tool_calls=[
ToolCall(
tool_name="custom1",
arguments={"param1": "value1"},
call_id="123",
)
],
),
],
tools=[
ToolDefinition(
tool_name="custom1",
description="custom1 tool",
parameters={
"param1": ToolParamDefinition(
param_type="str",
description="param1 description",
required=True,
),
},
),
],
tool_config=ToolConfig(tool_prompt_format=ToolPromptFormat.python_list),
)
prompt = await chat_completion_request_to_prompt(request, request.model)
self.assertIn('[custom1(param1="value1")]', prompt)
request.model = MODEL
request.tool_config.tool_prompt_format = ToolPromptFormat.json
prompt = await chat_completion_request_to_prompt(request, request.model)
self.assertIn('{"type": "function", "name": "custom1", "parameters": {"param1": "value1"}}', prompt)
async def test_user_provided_system_message(self):
content = "Hello !"
system_prompt = "You are a pirate"
request = ChatCompletionRequest(
model=MODEL,
messages=[
SystemMessage(content=system_prompt),
UserMessage(content=content),
],
tools=[
ToolDefinition(tool_name=BuiltinTool.code_interpreter),
],
)
messages = chat_completion_request_to_messages(request, MODEL)
self.assertEqual(len(messages), 2, messages)
self.assertTrue(messages[0].content.endswith(system_prompt))
self.assertEqual(messages[-1].content, content)
async def test_repalce_system_message_behavior_builtin_tools(self):
content = "Hello !"
system_prompt = "You are a pirate"
request = ChatCompletionRequest(
model=MODEL,
messages=[
SystemMessage(content=system_prompt),
UserMessage(content=content),
],
tools=[
ToolDefinition(tool_name=BuiltinTool.code_interpreter),
],
tool_config=ToolConfig(
tool_choice="auto",
tool_prompt_format="python_list",
system_message_behavior="replace",
),
)
messages = chat_completion_request_to_messages(request, MODEL3_2)
self.assertEqual(len(messages), 2, messages)
self.assertTrue(messages[0].content.endswith(system_prompt))
self.assertIn("Environment: ipython", messages[0].content)
self.assertEqual(messages[-1].content, content)
async def test_repalce_system_message_behavior_custom_tools(self):
content = "Hello !"
system_prompt = "You are a pirate"
request = ChatCompletionRequest(
model=MODEL,
messages=[
SystemMessage(content=system_prompt),
UserMessage(content=content),
],
tools=[
ToolDefinition(tool_name=BuiltinTool.code_interpreter),
ToolDefinition(
tool_name="custom1",
description="custom1 tool",
parameters={
"param1": ToolParamDefinition(
param_type="str",
description="param1 description",
required=True,
),
},
),
],
tool_config=ToolConfig(
tool_choice="auto",
tool_prompt_format="python_list",
system_message_behavior="replace",
),
)
messages = chat_completion_request_to_messages(request, MODEL3_2)
self.assertEqual(len(messages), 2, messages)
self.assertTrue(messages[0].content.endswith(system_prompt))
self.assertIn("Environment: ipython", messages[0].content)
self.assertEqual(messages[-1].content, content)
async def test_replace_system_message_behavior_custom_tools_with_template(self):
content = "Hello !"
system_prompt = "You are a pirate {{ function_description }}"
request = ChatCompletionRequest(
model=MODEL,
messages=[
SystemMessage(content=system_prompt),
UserMessage(content=content),
],
tools=[
ToolDefinition(tool_name=BuiltinTool.code_interpreter),
ToolDefinition(
tool_name="custom1",
description="custom1 tool",
parameters={
"param1": ToolParamDefinition(
param_type="str",
description="param1 description",
required=True,
),
},
),
],
tool_config=ToolConfig(
tool_choice="auto",
tool_prompt_format="python_list",
system_message_behavior="replace",
),
)
messages = chat_completion_request_to_messages(request, MODEL3_2)
self.assertEqual(len(messages), 2, messages)
self.assertIn("Environment: ipython", messages[0].content)
self.assertIn("You are a pirate", messages[0].content)
# function description is present in the system prompt
self.assertIn('"name": "custom1"', messages[0].content)
self.assertEqual(messages[-1].content, content)