mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
3c72c034e6
# What does this PR do? - as title, cleaning up `import *`'s - upgrade tests to make them more robust to bad model outputs - remove import *'s in llama_stack/apis/* (skip __init__ modules) <img width="465" alt="image" src="https://github.com/user-attachments/assets/d8339c13-3b40-4ba5-9c53-0d2329726ee2" /> - run `sh run_openapi_generator.sh`, no types gets affected ## Test Plan ### Providers Tests **agents** ``` pytest -v -s llama_stack/providers/tests/agents/test_agents.py -m "together" --safety-shield meta-llama/Llama-Guard-3-8B --inference-model meta-llama/Llama-3.1-405B-Instruct-FP8 ``` **inference** ```bash # meta-reference torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="meta-llama/Llama-3.2-11B-Vision-Instruct" ./llama_stack/providers/tests/inference/test_vision_inference.py # together pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.2-11B-Vision-Instruct" ./llama_stack/providers/tests/inference/test_vision_inference.py pytest ./llama_stack/providers/tests/inference/test_prompt_adapter.py ``` **safety** ``` pytest -v -s llama_stack/providers/tests/safety/test_safety.py -m together --safety-shield meta-llama/Llama-Guard-3-8B ``` **memory** ``` pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m "sentence_transformers" --env EMBEDDING_DIMENSION=384 ``` **scoring** ``` pytest -v -s -m llm_as_judge_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py --judge-model meta-llama/Llama-3.2-3B-Instruct pytest -v -s -m basic_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py pytest -v -s -m braintrust_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py ``` **datasetio** ``` pytest -v -s -m localfs llama_stack/providers/tests/datasetio/test_datasetio.py pytest -v -s -m huggingface llama_stack/providers/tests/datasetio/test_datasetio.py ``` **eval** ``` pytest -v -s -m meta_reference_eval_together_inference llama_stack/providers/tests/eval/test_eval.py pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio llama_stack/providers/tests/eval/test_eval.py ``` ### Client-SDK Tests ``` LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v ./tests/client-sdk ``` ### llama-stack-apps ``` PORT=5000 LOCALHOST=localhost python -m examples.agents.hello $LOCALHOST $PORT python -m examples.agents.inflation $LOCALHOST $PORT python -m examples.agents.podcast_transcript $LOCALHOST $PORT python -m examples.agents.rag_as_attachments $LOCALHOST $PORT python -m examples.agents.rag_with_memory_bank $LOCALHOST $PORT python -m examples.safety.llama_guard_demo_mm $LOCALHOST $PORT python -m examples.agents.e2e_loop_with_custom_tools $LOCALHOST $PORT # Vision model python -m examples.interior_design_assistant.app python -m examples.agent_store.app $LOCALHOST $PORT ``` ### CLI ``` which llama llama model prompt-format -m Llama3.2-11B-Vision-Instruct llama model list llama stack list-apis llama stack list-providers inference llama stack build --template ollama --image-type conda ``` ### Distributions Tests **ollama** ``` llama stack build --template ollama --image-type conda ollama run llama3.2:1b-instruct-fp16 llama stack run ./llama_stack/templates/ollama/run.yaml --env INFERENCE_MODEL=meta-llama/Llama-3.2-1B-Instruct ``` **fireworks** ``` llama stack build --template fireworks --image-type conda llama stack run ./llama_stack/templates/fireworks/run.yaml ``` **together** ``` llama stack build --template together --image-type conda llama stack run ./llama_stack/templates/together/run.yaml ``` **tgi** ``` llama stack run ./llama_stack/templates/tgi/run.yaml --env TGI_URL=http://0.0.0.0:5009 --env INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct ``` ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.
188 lines
7 KiB
Python
188 lines
7 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 typing import List
|
|
|
|
from llama_stack.providers.datatypes import (
|
|
AdapterSpec,
|
|
Api,
|
|
InlineProviderSpec,
|
|
ProviderSpec,
|
|
remote_provider_spec,
|
|
)
|
|
|
|
META_REFERENCE_DEPS = [
|
|
"accelerate",
|
|
"blobfile",
|
|
"fairscale",
|
|
"torch",
|
|
"torchvision",
|
|
"transformers",
|
|
"zmq",
|
|
"lm-format-enforcer",
|
|
"sentence-transformers",
|
|
]
|
|
|
|
|
|
def available_providers() -> List[ProviderSpec]:
|
|
return [
|
|
InlineProviderSpec(
|
|
api=Api.inference,
|
|
provider_type="inline::meta-reference",
|
|
pip_packages=META_REFERENCE_DEPS,
|
|
module="llama_stack.providers.inline.inference.meta_reference",
|
|
config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceInferenceConfig",
|
|
),
|
|
InlineProviderSpec(
|
|
api=Api.inference,
|
|
provider_type="inline::meta-reference-quantized",
|
|
pip_packages=(
|
|
META_REFERENCE_DEPS
|
|
+ [
|
|
"fbgemm-gpu",
|
|
"torchao==0.5.0",
|
|
]
|
|
),
|
|
module="llama_stack.providers.inline.inference.meta_reference",
|
|
config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceQuantizedInferenceConfig",
|
|
),
|
|
InlineProviderSpec(
|
|
api=Api.inference,
|
|
provider_type="inline::vllm",
|
|
pip_packages=[
|
|
"vllm",
|
|
],
|
|
module="llama_stack.providers.inline.inference.vllm",
|
|
config_class="llama_stack.providers.inline.inference.vllm.VLLMConfig",
|
|
),
|
|
InlineProviderSpec(
|
|
api=Api.inference,
|
|
provider_type="inline::sentence-transformers",
|
|
pip_packages=["sentence-transformers"],
|
|
module="llama_stack.providers.inline.inference.sentence_transformers",
|
|
config_class="llama_stack.providers.inline.inference.sentence_transformers.config.SentenceTransformersInferenceConfig",
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="sample",
|
|
pip_packages=[],
|
|
module="llama_stack.providers.remote.inference.sample",
|
|
config_class="llama_stack.providers.remote.inference.sample.SampleConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="cerebras",
|
|
pip_packages=[
|
|
"cerebras_cloud_sdk",
|
|
],
|
|
module="llama_stack.providers.remote.inference.cerebras",
|
|
config_class="llama_stack.providers.remote.inference.cerebras.CerebrasImplConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="ollama",
|
|
pip_packages=["ollama", "aiohttp"],
|
|
config_class="llama_stack.providers.remote.inference.ollama.OllamaImplConfig",
|
|
module="llama_stack.providers.remote.inference.ollama",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="vllm",
|
|
pip_packages=["openai"],
|
|
module="llama_stack.providers.remote.inference.vllm",
|
|
config_class="llama_stack.providers.remote.inference.vllm.VLLMInferenceAdapterConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="tgi",
|
|
pip_packages=["huggingface_hub", "aiohttp"],
|
|
module="llama_stack.providers.remote.inference.tgi",
|
|
config_class="llama_stack.providers.remote.inference.tgi.TGIImplConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="hf::serverless",
|
|
pip_packages=["huggingface_hub", "aiohttp"],
|
|
module="llama_stack.providers.remote.inference.tgi",
|
|
config_class="llama_stack.providers.remote.inference.tgi.InferenceAPIImplConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="hf::endpoint",
|
|
pip_packages=["huggingface_hub", "aiohttp"],
|
|
module="llama_stack.providers.remote.inference.tgi",
|
|
config_class="llama_stack.providers.remote.inference.tgi.InferenceEndpointImplConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="fireworks",
|
|
pip_packages=[
|
|
"fireworks-ai",
|
|
],
|
|
module="llama_stack.providers.remote.inference.fireworks",
|
|
config_class="llama_stack.providers.remote.inference.fireworks.FireworksImplConfig",
|
|
provider_data_validator="llama_stack.providers.remote.inference.fireworks.FireworksProviderDataValidator",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="together",
|
|
pip_packages=[
|
|
"together",
|
|
],
|
|
module="llama_stack.providers.remote.inference.together",
|
|
config_class="llama_stack.providers.remote.inference.together.TogetherImplConfig",
|
|
provider_data_validator="llama_stack.providers.remote.inference.together.TogetherProviderDataValidator",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="bedrock",
|
|
pip_packages=["boto3"],
|
|
module="llama_stack.providers.remote.inference.bedrock",
|
|
config_class="llama_stack.providers.remote.inference.bedrock.BedrockConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="databricks",
|
|
pip_packages=[
|
|
"openai",
|
|
],
|
|
module="llama_stack.providers.remote.inference.databricks",
|
|
config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="nvidia",
|
|
pip_packages=[
|
|
"openai",
|
|
],
|
|
module="llama_stack.providers.remote.inference.nvidia",
|
|
config_class="llama_stack.providers.remote.inference.nvidia.NVIDIAConfig",
|
|
),
|
|
),
|
|
]
|