mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +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
```
145 lines
5 KiB
Python
145 lines
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.
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
|
|
from llama_models.llama3.api.datatypes import * # noqa: F403
|
|
from llama_stack.apis.inference import * # noqa: F403
|
|
from llama_stack.apis.common.content_types import ImageContentItem, TextContentItem, URL
|
|
|
|
from .utils import group_chunks
|
|
|
|
THIS_DIR = Path(__file__).parent
|
|
|
|
with open(THIS_DIR / "pasta.jpeg", "rb") as f:
|
|
PASTA_IMAGE = f.read()
|
|
|
|
|
|
class TestVisionModelInference:
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize(
|
|
"image, expected_strings",
|
|
[
|
|
(
|
|
ImageContentItem(data=PASTA_IMAGE),
|
|
["spaghetti"],
|
|
),
|
|
(
|
|
ImageContentItem(
|
|
url=URL(
|
|
uri="https://www.healthypawspetinsurance.com/Images/V3/DogAndPuppyInsurance/Dog_CTA_Desktop_HeroImage.jpg"
|
|
)
|
|
),
|
|
["puppy"],
|
|
),
|
|
],
|
|
)
|
|
async def test_vision_chat_completion_non_streaming(
|
|
self, inference_model, inference_stack, image, expected_strings
|
|
):
|
|
inference_impl, _ = inference_stack
|
|
|
|
provider = inference_impl.routing_table.get_provider_impl(inference_model)
|
|
if provider.__provider_spec__.provider_type not in (
|
|
"inline::meta-reference",
|
|
"remote::together",
|
|
"remote::fireworks",
|
|
"remote::ollama",
|
|
"remote::vllm",
|
|
):
|
|
pytest.skip(
|
|
"Other inference providers don't support vision chat completion() yet"
|
|
)
|
|
|
|
response = await inference_impl.chat_completion(
|
|
model_id=inference_model,
|
|
messages=[
|
|
UserMessage(content="You are a helpful assistant."),
|
|
UserMessage(
|
|
content=[
|
|
image,
|
|
TextContentItem(text="Describe this image in two sentences."),
|
|
]
|
|
),
|
|
],
|
|
stream=False,
|
|
sampling_params=SamplingParams(max_tokens=100),
|
|
)
|
|
|
|
assert isinstance(response, ChatCompletionResponse)
|
|
assert response.completion_message.role == "assistant"
|
|
assert isinstance(response.completion_message.content, str)
|
|
for expected_string in expected_strings:
|
|
assert expected_string in response.completion_message.content
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_vision_chat_completion_streaming(
|
|
self, inference_model, inference_stack
|
|
):
|
|
inference_impl, _ = inference_stack
|
|
|
|
provider = inference_impl.routing_table.get_provider_impl(inference_model)
|
|
if provider.__provider_spec__.provider_type not in (
|
|
"inline::meta-reference",
|
|
"remote::together",
|
|
"remote::fireworks",
|
|
"remote::ollama",
|
|
"remote::vllm",
|
|
):
|
|
pytest.skip(
|
|
"Other inference providers don't support vision chat completion() yet"
|
|
)
|
|
|
|
images = [
|
|
ImageContentItem(
|
|
url=URL(
|
|
uri="https://www.healthypawspetinsurance.com/Images/V3/DogAndPuppyInsurance/Dog_CTA_Desktop_HeroImage.jpg"
|
|
)
|
|
),
|
|
]
|
|
expected_strings_to_check = [
|
|
["puppy"],
|
|
]
|
|
for image, expected_strings in zip(images, expected_strings_to_check):
|
|
response = [
|
|
r
|
|
async for r in await inference_impl.chat_completion(
|
|
model_id=inference_model,
|
|
messages=[
|
|
UserMessage(content="You are a helpful assistant."),
|
|
UserMessage(
|
|
content=[
|
|
image,
|
|
TextContentItem(
|
|
text="Describe this image in two sentences."
|
|
),
|
|
]
|
|
),
|
|
],
|
|
stream=True,
|
|
sampling_params=SamplingParams(max_tokens=100),
|
|
)
|
|
]
|
|
|
|
assert len(response) > 0
|
|
assert all(
|
|
isinstance(chunk, ChatCompletionResponseStreamChunk)
|
|
for chunk in response
|
|
)
|
|
grouped = group_chunks(response)
|
|
assert len(grouped[ChatCompletionResponseEventType.start]) == 1
|
|
assert len(grouped[ChatCompletionResponseEventType.progress]) > 0
|
|
assert len(grouped[ChatCompletionResponseEventType.complete]) == 1
|
|
|
|
content = "".join(
|
|
chunk.event.delta
|
|
for chunk in grouped[ChatCompletionResponseEventType.progress]
|
|
)
|
|
for expected_string in expected_strings:
|
|
assert expected_string in content
|