mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-30 11:50:14 +00:00
8de8eb03c8
## What does this PR do?
This is a long-pending change and particularly important to get done
now.
Specifically:
- we cannot "localize" (aka download) any URLs from media attachments
anywhere near our modeling code. it must be done within llama-stack.
- `PIL.Image` is infesting all our APIs via `ImageMedia ->
InterleavedTextMedia` and that cannot be right at all. Anything in the
API surface must be "naturally serializable". We need a standard `{
type: "image", image_url: "<...>" }` which is more extensible
- `UserMessage`, `SystemMessage`, etc. are moved completely to
llama-stack from the llama-models repository.
See https://github.com/meta-llama/llama-models/pull/244 for the
corresponding PR in llama-models.
## Test Plan
```bash
cd llama_stack/providers/tests
pytest -s -v -k "fireworks or ollama or together" inference/test_vision_inference.py
pytest -s -v -k "(fireworks or ollama or together) and llama_3b" inference/test_text_inference.py
pytest -s -v -k chroma memory/test_memory.py \
--env EMBEDDING_DIMENSION=384 --env CHROMA_DB_PATH=/tmp/foobar
pytest -s -v -k fireworks agents/test_agents.py \
--safety-shield=meta-llama/Llama-Guard-3-8B \
--inference-model=meta-llama/Llama-3.1-8B-Instruct
```
Updated the client sdk (see PR ...), installed the SDK in the same
environment and then ran the SDK tests:
```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=together pytest -s -v agents/test_agents.py
LLAMA_STACK_CONFIG=ollama pytest -s -v memory/test_memory.py
# this one needed a bit of hacking in the run.yaml to ensure I could register the vision model correctly
INFERENCE_MODEL=llama3.2-vision:latest LLAMA_STACK_CONFIG=ollama pytest -s -v inference/test_inference.py
```
108 lines
3.5 KiB
Python
108 lines
3.5 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):
|
|
fixture_dict = request.param
|
|
|
|
providers = {}
|
|
provider_data = {}
|
|
for key in ["inference", "safety", "memory", "agents"]:
|
|
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]
|
|
)
|
|
models = [
|
|
ModelInput(
|
|
model_id=model,
|
|
model_type=ModelType.llm,
|
|
provider_id=providers["inference"][0].provider_id,
|
|
)
|
|
for model in inference_models
|
|
]
|
|
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],
|
|
providers,
|
|
provider_data,
|
|
models=models,
|
|
shields=[safety_shield] if safety_shield else [],
|
|
)
|
|
return test_stack
|