mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
# 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.
207 lines
7.1 KiB
Python
207 lines
7.1 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 asyncio
|
|
from contextlib import asynccontextmanager
|
|
from typing import Dict, List, Optional, Protocol, Tuple
|
|
|
|
import pydantic
|
|
|
|
from llama_stack.distribution.datatypes import KVStoreConfig, RoutableObjectWithProvider
|
|
from llama_stack.distribution.utils.config_dirs import DISTRIBS_BASE_DIR
|
|
|
|
from llama_stack.providers.utils.kvstore import KVStore, kvstore_impl
|
|
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
|
|
|
|
|
class DistributionRegistry(Protocol):
|
|
async def get_all(self) -> List[RoutableObjectWithProvider]: ...
|
|
|
|
async def initialize(self) -> None: ...
|
|
|
|
async def get(self, identifier: str) -> Optional[RoutableObjectWithProvider]: ...
|
|
|
|
def get_cached(self, identifier: str) -> Optional[RoutableObjectWithProvider]: ...
|
|
|
|
async def update(
|
|
self, obj: RoutableObjectWithProvider
|
|
) -> RoutableObjectWithProvider: ...
|
|
|
|
async def register(self, obj: RoutableObjectWithProvider) -> bool: ...
|
|
|
|
async def delete(self, type: str, identifier: str) -> None: ...
|
|
|
|
|
|
REGISTER_PREFIX = "distributions:registry"
|
|
KEY_VERSION = "v3"
|
|
KEY_FORMAT = f"{REGISTER_PREFIX}:{KEY_VERSION}::" + "{type}:{identifier}"
|
|
|
|
|
|
def _get_registry_key_range() -> Tuple[str, str]:
|
|
"""Returns the start and end keys for the registry range query."""
|
|
start_key = f"{REGISTER_PREFIX}:{KEY_VERSION}"
|
|
return start_key, f"{start_key}\xff"
|
|
|
|
|
|
def _parse_registry_values(values: List[str]) -> List[RoutableObjectWithProvider]:
|
|
"""Utility function to parse registry values into RoutableObjectWithProvider objects."""
|
|
all_objects = []
|
|
for value in values:
|
|
obj = pydantic.TypeAdapter(RoutableObjectWithProvider).validate_json(value)
|
|
all_objects.append(obj)
|
|
return all_objects
|
|
|
|
|
|
class DiskDistributionRegistry(DistributionRegistry):
|
|
def __init__(self, kvstore: KVStore):
|
|
self.kvstore = kvstore
|
|
|
|
async def initialize(self) -> None:
|
|
pass
|
|
|
|
def get_cached(
|
|
self, type: str, identifier: str
|
|
) -> Optional[RoutableObjectWithProvider]:
|
|
# Disk registry does not have a cache
|
|
raise NotImplementedError("Disk registry does not have a cache")
|
|
|
|
async def get_all(self) -> List[RoutableObjectWithProvider]:
|
|
start_key, end_key = _get_registry_key_range()
|
|
values = await self.kvstore.range(start_key, end_key)
|
|
return _parse_registry_values(values)
|
|
|
|
async def get(
|
|
self, type: str, identifier: str
|
|
) -> Optional[RoutableObjectWithProvider]:
|
|
json_str = await self.kvstore.get(
|
|
KEY_FORMAT.format(type=type, identifier=identifier)
|
|
)
|
|
if not json_str:
|
|
return None
|
|
|
|
return pydantic.TypeAdapter(RoutableObjectWithProvider).validate_json(json_str)
|
|
|
|
async def update(self, obj: RoutableObjectWithProvider) -> None:
|
|
await self.kvstore.set(
|
|
KEY_FORMAT.format(type=obj.type, identifier=obj.identifier),
|
|
obj.model_dump_json(),
|
|
)
|
|
return obj
|
|
|
|
async def register(self, obj: RoutableObjectWithProvider) -> bool:
|
|
existing_obj = await self.get(obj.type, obj.identifier)
|
|
# dont register if the object's providerid already exists
|
|
if existing_obj and existing_obj.provider_id == obj.provider_id:
|
|
return False
|
|
|
|
await self.kvstore.set(
|
|
KEY_FORMAT.format(type=obj.type, identifier=obj.identifier),
|
|
obj.model_dump_json(),
|
|
)
|
|
return True
|
|
|
|
async def delete(self, type: str, identifier: str) -> None:
|
|
await self.kvstore.delete(KEY_FORMAT.format(type=type, identifier=identifier))
|
|
|
|
|
|
class CachedDiskDistributionRegistry(DiskDistributionRegistry):
|
|
def __init__(self, kvstore: KVStore):
|
|
super().__init__(kvstore)
|
|
self.cache: Dict[Tuple[str, str], RoutableObjectWithProvider] = {}
|
|
self._initialized = False
|
|
self._initialize_lock = asyncio.Lock()
|
|
self._cache_lock = asyncio.Lock()
|
|
|
|
@asynccontextmanager
|
|
async def _locked_cache(self):
|
|
"""Context manager for safely accessing the cache with a lock."""
|
|
async with self._cache_lock:
|
|
yield self.cache
|
|
|
|
async def _ensure_initialized(self):
|
|
"""Ensures the registry is initialized before operations."""
|
|
if self._initialized:
|
|
return
|
|
|
|
async with self._initialize_lock:
|
|
if self._initialized:
|
|
return
|
|
|
|
start_key, end_key = _get_registry_key_range()
|
|
values = await self.kvstore.range(start_key, end_key)
|
|
objects = _parse_registry_values(values)
|
|
|
|
async with self._locked_cache() as cache:
|
|
for obj in objects:
|
|
cache_key = (obj.type, obj.identifier)
|
|
cache[cache_key] = obj
|
|
|
|
self._initialized = True
|
|
|
|
async def initialize(self) -> None:
|
|
await self._ensure_initialized()
|
|
|
|
def get_cached(
|
|
self, type: str, identifier: str
|
|
) -> Optional[RoutableObjectWithProvider]:
|
|
return self.cache.get((type, identifier), None)
|
|
|
|
async def get_all(self) -> List[RoutableObjectWithProvider]:
|
|
await self._ensure_initialized()
|
|
async with self._locked_cache() as cache:
|
|
return list(cache.values())
|
|
|
|
async def get(
|
|
self, type: str, identifier: str
|
|
) -> Optional[RoutableObjectWithProvider]:
|
|
await self._ensure_initialized()
|
|
cache_key = (type, identifier)
|
|
|
|
async with self._locked_cache() as cache:
|
|
return cache.get(cache_key, None)
|
|
|
|
async def register(self, obj: RoutableObjectWithProvider) -> bool:
|
|
await self._ensure_initialized()
|
|
success = await super().register(obj)
|
|
|
|
if success:
|
|
cache_key = (obj.type, obj.identifier)
|
|
async with self._locked_cache() as cache:
|
|
cache[cache_key] = obj
|
|
|
|
return success
|
|
|
|
async def update(self, obj: RoutableObjectWithProvider) -> None:
|
|
await super().update(obj)
|
|
cache_key = (obj.type, obj.identifier)
|
|
async with self._locked_cache() as cache:
|
|
cache[cache_key] = obj
|
|
return obj
|
|
|
|
async def delete(self, type: str, identifier: str) -> None:
|
|
await super().delete(type, identifier)
|
|
cache_key = (type, identifier)
|
|
async with self._locked_cache() as cache:
|
|
if cache_key in cache:
|
|
del cache[cache_key]
|
|
|
|
|
|
async def create_dist_registry(
|
|
metadata_store: Optional[KVStoreConfig],
|
|
image_name: str,
|
|
) -> tuple[CachedDiskDistributionRegistry, KVStore]:
|
|
# instantiate kvstore for storing and retrieving distribution metadata
|
|
if metadata_store:
|
|
dist_kvstore = await kvstore_impl(metadata_store)
|
|
else:
|
|
dist_kvstore = await kvstore_impl(
|
|
SqliteKVStoreConfig(
|
|
db_path=(DISTRIBS_BASE_DIR / image_name / "kvstore.db").as_posix()
|
|
)
|
|
)
|
|
dist_registry = CachedDiskDistributionRegistry(dist_kvstore)
|
|
await dist_registry.initialize()
|
|
return dist_registry, dist_kvstore
|