mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
a5c57cd381
# What does this PR do? PR #639 introduced the notion of Tools API and ability to invoke tools through API just as any resource. This PR changes the Agents to start using the Tools API to invoke tools. Major changes include: 1) Ability to specify tool groups with AgentConfig 2) Agent gets the corresponding tool definitions for the specified tools and pass along to the model 3) Attachements are now named as Documents and their behavior is mostly unchanged from user perspective 4) You can specify args that can be injected to a tool call through Agent config. This is especially useful in case of memory tool, where you want the tool to operate on a specific memory bank. 5) You can also register tool groups with args, which lets the agent inject these as well into the tool call. 6) All tests have been migrated to use new tools API and fixtures including client SDK tests 7) Telemetry just works with tools API because of our trace protocol decorator ## Test Plan ``` pytest -s -v -k fireworks llama_stack/providers/tests/agents/test_agents.py \ --safety-shield=meta-llama/Llama-Guard-3-8B \ --inference-model=meta-llama/Llama-3.1-8B-Instruct pytest -s -v -k together llama_stack/providers/tests/tools/test_tools.py \ --safety-shield=meta-llama/Llama-Guard-3-8B \ --inference-model=meta-llama/Llama-3.1-8B-Instruct LLAMA_STACK_CONFIG="/Users/dineshyv/.llama/distributions/llamastack-together/together-run.yaml" pytest -v tests/client-sdk/agents/test_agents.py ``` run.yaml: https://gist.github.com/dineshyv/0365845ad325e1c2cab755788ccc5994 Notebook: https://colab.research.google.com/drive/1ck7hXQxRl6UvT-ijNRZ-gMZxH1G3cN2d?usp=sharing
128 lines
4.1 KiB
Python
128 lines
4.1 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.
|
|
|
|
import tempfile
|
|
|
|
import pytest
|
|
import pytest_asyncio
|
|
|
|
from llama_stack.apis.models import ModelInput, ModelType
|
|
from llama_stack.distribution.datatypes import Api, Provider
|
|
from llama_stack.providers.inline.agents.meta_reference import (
|
|
MetaReferenceAgentsImplConfig,
|
|
)
|
|
from llama_stack.providers.tests.resolver import construct_stack_for_test
|
|
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
|
|
|
from ..conftest import ProviderFixture, remote_stack_fixture
|
|
|
|
|
|
def pick_inference_model(inference_model):
|
|
# This is not entirely satisfactory. The fixture `inference_model` can correspond to
|
|
# multiple models when you need to run a safety model in addition to normal agent
|
|
# inference model. We filter off the safety model by looking for "Llama-Guard"
|
|
if isinstance(inference_model, list):
|
|
inference_model = next(m for m in inference_model if "Llama-Guard" not in m)
|
|
assert inference_model is not None
|
|
return inference_model
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def agents_remote() -> ProviderFixture:
|
|
return remote_stack_fixture()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def agents_meta_reference() -> ProviderFixture:
|
|
sqlite_file = tempfile.NamedTemporaryFile(delete=False, suffix=".db")
|
|
return ProviderFixture(
|
|
providers=[
|
|
Provider(
|
|
provider_id="meta-reference",
|
|
provider_type="inline::meta-reference",
|
|
config=MetaReferenceAgentsImplConfig(
|
|
# TODO: make this an in-memory store
|
|
persistence_store=SqliteKVStoreConfig(
|
|
db_path=sqlite_file.name,
|
|
),
|
|
).model_dump(),
|
|
)
|
|
],
|
|
)
|
|
|
|
|
|
AGENTS_FIXTURES = ["meta_reference", "remote"]
|
|
|
|
|
|
@pytest_asyncio.fixture(scope="session")
|
|
async def agents_stack(
|
|
request,
|
|
inference_model,
|
|
safety_shield,
|
|
tool_group_input_memory,
|
|
tool_group_input_tavily_search,
|
|
):
|
|
fixture_dict = request.param
|
|
|
|
providers = {}
|
|
provider_data = {}
|
|
for key in ["inference", "safety", "memory", "agents", "tool_runtime"]:
|
|
fixture = request.getfixturevalue(f"{key}_{fixture_dict[key]}")
|
|
providers[key] = fixture.providers
|
|
if key == "inference":
|
|
providers[key].append(
|
|
Provider(
|
|
provider_id="agents_memory_provider",
|
|
provider_type="inline::sentence-transformers",
|
|
config={},
|
|
)
|
|
)
|
|
if fixture.provider_data:
|
|
provider_data.update(fixture.provider_data)
|
|
|
|
inference_models = (
|
|
inference_model if isinstance(inference_model, list) else [inference_model]
|
|
)
|
|
|
|
# NOTE: meta-reference provider needs 1 provider per model, lookup provider_id from provider config
|
|
model_to_provider_id = {}
|
|
for provider in providers["inference"]:
|
|
if "model" in provider.config:
|
|
model_to_provider_id[provider.config["model"]] = provider.provider_id
|
|
|
|
models = []
|
|
for model in inference_models:
|
|
if model in model_to_provider_id:
|
|
provider_id = model_to_provider_id[model]
|
|
else:
|
|
provider_id = providers["inference"][0].provider_id
|
|
|
|
models.append(
|
|
ModelInput(
|
|
model_id=model,
|
|
model_type=ModelType.llm,
|
|
provider_id=provider_id,
|
|
)
|
|
)
|
|
|
|
models.append(
|
|
ModelInput(
|
|
model_id="all-MiniLM-L6-v2",
|
|
model_type=ModelType.embedding,
|
|
provider_id="agents_memory_provider",
|
|
metadata={"embedding_dimension": 384},
|
|
)
|
|
)
|
|
|
|
test_stack = await construct_stack_for_test(
|
|
[Api.agents, Api.inference, Api.safety, Api.memory, Api.tool_runtime],
|
|
providers,
|
|
provider_data,
|
|
models=models,
|
|
shields=[safety_shield] if safety_shield else [],
|
|
tool_groups=[tool_group_input_memory, tool_group_input_tavily_search],
|
|
)
|
|
return test_stack
|