forked from phoenix-oss/llama-stack-mirror
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
```
74 lines
2.2 KiB
Python
74 lines
2.2 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 pytest
|
|
import pytest_asyncio
|
|
|
|
from llama_stack.apis.common.type_system import * # noqa: F403
|
|
from llama_stack.apis.common.content_types import URL
|
|
from llama_stack.apis.datasets import DatasetInput
|
|
from llama_stack.apis.models import ModelInput
|
|
|
|
from llama_stack.distribution.datatypes import Api, Provider
|
|
|
|
from llama_stack.providers.tests.resolver import construct_stack_for_test
|
|
|
|
from ..conftest import ProviderFixture
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def post_training_torchtune() -> ProviderFixture:
|
|
return ProviderFixture(
|
|
providers=[
|
|
Provider(
|
|
provider_id="torchtune",
|
|
provider_type="inline::torchtune",
|
|
config={},
|
|
)
|
|
],
|
|
)
|
|
|
|
|
|
POST_TRAINING_FIXTURES = ["torchtune"]
|
|
|
|
|
|
@pytest_asyncio.fixture(scope="session")
|
|
async def post_training_stack(request):
|
|
fixture_dict = request.param
|
|
|
|
providers = {}
|
|
provider_data = {}
|
|
for key in ["post_training", "datasetio"]:
|
|
fixture = request.getfixturevalue(f"{key}_{fixture_dict[key]}")
|
|
providers[key] = fixture.providers
|
|
if fixture.provider_data:
|
|
provider_data.update(fixture.provider_data)
|
|
|
|
test_stack = await construct_stack_for_test(
|
|
[Api.post_training, Api.datasetio],
|
|
providers,
|
|
provider_data,
|
|
models=[ModelInput(model_id="meta-llama/Llama-3.2-3B-Instruct")],
|
|
datasets=[
|
|
DatasetInput(
|
|
dataset_id="alpaca",
|
|
provider_id="huggingface",
|
|
url=URL(uri="https://huggingface.co/datasets/tatsu-lab/alpaca"),
|
|
metadata={
|
|
"path": "tatsu-lab/alpaca",
|
|
"split": "train",
|
|
},
|
|
dataset_schema={
|
|
"instruction": StringType(),
|
|
"input": StringType(),
|
|
"output": StringType(),
|
|
"text": StringType(),
|
|
},
|
|
),
|
|
],
|
|
)
|
|
|
|
return test_stack.impls[Api.post_training]
|