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.
219 lines
6.7 KiB
Python
219 lines
6.7 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.
|
|
|
|
import json
|
|
import logging
|
|
import shutil
|
|
import tempfile
|
|
import uuid
|
|
from typing import AsyncGenerator, List, Optional, Union
|
|
|
|
from termcolor import colored
|
|
|
|
from llama_stack.apis.agents import (
|
|
AgentConfig,
|
|
AgentCreateResponse,
|
|
Agents,
|
|
AgentSessionCreateResponse,
|
|
AgentStepResponse,
|
|
AgentTurnCreateRequest,
|
|
Attachment,
|
|
Session,
|
|
Turn,
|
|
)
|
|
|
|
from llama_stack.apis.inference import Inference, ToolResponseMessage, UserMessage
|
|
from llama_stack.apis.memory import Memory
|
|
from llama_stack.apis.memory_banks import MemoryBanks
|
|
from llama_stack.apis.safety import Safety
|
|
|
|
from llama_stack.providers.utils.kvstore import InmemoryKVStoreImpl, kvstore_impl
|
|
|
|
from .agent_instance import ChatAgent
|
|
from .config import MetaReferenceAgentsImplConfig
|
|
|
|
logger = logging.getLogger()
|
|
logger.setLevel(logging.INFO)
|
|
|
|
|
|
class MetaReferenceAgentsImpl(Agents):
|
|
def __init__(
|
|
self,
|
|
config: MetaReferenceAgentsImplConfig,
|
|
inference_api: Inference,
|
|
memory_api: Memory,
|
|
safety_api: Safety,
|
|
memory_banks_api: MemoryBanks,
|
|
):
|
|
self.config = config
|
|
self.inference_api = inference_api
|
|
self.memory_api = memory_api
|
|
self.safety_api = safety_api
|
|
self.memory_banks_api = memory_banks_api
|
|
|
|
self.in_memory_store = InmemoryKVStoreImpl()
|
|
self.tempdir = tempfile.mkdtemp()
|
|
|
|
async def initialize(self) -> None:
|
|
self.persistence_store = await kvstore_impl(self.config.persistence_store)
|
|
|
|
# check if "bwrap" is available
|
|
if not shutil.which("bwrap"):
|
|
print(
|
|
colored(
|
|
"Warning: `bwrap` is not available. Code interpreter tool will not work correctly.",
|
|
"yellow",
|
|
)
|
|
)
|
|
|
|
async def create_agent(
|
|
self,
|
|
agent_config: AgentConfig,
|
|
) -> AgentCreateResponse:
|
|
agent_id = str(uuid.uuid4())
|
|
|
|
await self.persistence_store.set(
|
|
key=f"agent:{agent_id}",
|
|
value=agent_config.model_dump_json(),
|
|
)
|
|
return AgentCreateResponse(
|
|
agent_id=agent_id,
|
|
)
|
|
|
|
async def get_agent(self, agent_id: str) -> ChatAgent:
|
|
agent_config = await self.persistence_store.get(
|
|
key=f"agent:{agent_id}",
|
|
)
|
|
if not agent_config:
|
|
raise ValueError(f"Could not find agent config for {agent_id}")
|
|
|
|
try:
|
|
agent_config = json.loads(agent_config)
|
|
except json.JSONDecodeError as e:
|
|
raise ValueError(
|
|
f"Could not JSON decode agent config for {agent_id}"
|
|
) from e
|
|
|
|
try:
|
|
agent_config = AgentConfig(**agent_config)
|
|
except Exception as e:
|
|
raise ValueError(
|
|
f"Could not validate(?) agent config for {agent_id}"
|
|
) from e
|
|
|
|
return ChatAgent(
|
|
agent_id=agent_id,
|
|
agent_config=agent_config,
|
|
tempdir=self.tempdir,
|
|
inference_api=self.inference_api,
|
|
safety_api=self.safety_api,
|
|
memory_api=self.memory_api,
|
|
memory_banks_api=self.memory_banks_api,
|
|
persistence_store=(
|
|
self.persistence_store
|
|
if agent_config.enable_session_persistence
|
|
else self.in_memory_store
|
|
),
|
|
)
|
|
|
|
async def create_agent_session(
|
|
self,
|
|
agent_id: str,
|
|
session_name: str,
|
|
) -> AgentSessionCreateResponse:
|
|
agent = await self.get_agent(agent_id)
|
|
|
|
session_id = await agent.create_session(session_name)
|
|
return AgentSessionCreateResponse(
|
|
session_id=session_id,
|
|
)
|
|
|
|
async def create_agent_turn(
|
|
self,
|
|
agent_id: str,
|
|
session_id: str,
|
|
messages: List[
|
|
Union[
|
|
UserMessage,
|
|
ToolResponseMessage,
|
|
]
|
|
],
|
|
attachments: Optional[List[Attachment]] = None,
|
|
stream: Optional[bool] = False,
|
|
) -> AsyncGenerator:
|
|
request = AgentTurnCreateRequest(
|
|
agent_id=agent_id,
|
|
session_id=session_id,
|
|
messages=messages,
|
|
attachments=attachments,
|
|
stream=True,
|
|
)
|
|
if stream:
|
|
return self._create_agent_turn_streaming(request)
|
|
else:
|
|
raise NotImplementedError("Non-streaming agent turns not yet implemented")
|
|
|
|
async def _create_agent_turn_streaming(
|
|
self,
|
|
request: AgentTurnCreateRequest,
|
|
) -> AsyncGenerator:
|
|
agent = await self.get_agent(request.agent_id)
|
|
async for event in agent.create_and_execute_turn(request):
|
|
yield event
|
|
|
|
async def get_agents_turn(
|
|
self, agent_id: str, session_id: str, turn_id: str
|
|
) -> Turn:
|
|
turn = await self.persistence_store.get(
|
|
f"session:{agent_id}:{session_id}:{turn_id}"
|
|
)
|
|
turn = json.loads(turn)
|
|
turn = Turn(**turn)
|
|
return turn
|
|
|
|
async def get_agents_step(
|
|
self, agent_id: str, session_id: str, turn_id: str, step_id: str
|
|
) -> AgentStepResponse:
|
|
turn = await self.persistence_store.get(
|
|
f"session:{agent_id}:{session_id}:{turn_id}"
|
|
)
|
|
turn = json.loads(turn)
|
|
turn = Turn(**turn)
|
|
steps = turn.steps
|
|
for step in steps:
|
|
if step.step_id == step_id:
|
|
return AgentStepResponse(step=step)
|
|
raise ValueError(f"Provided step_id {step_id} could not be found")
|
|
|
|
async def get_agents_session(
|
|
self,
|
|
agent_id: str,
|
|
session_id: str,
|
|
turn_ids: Optional[List[str]] = None,
|
|
) -> Session:
|
|
session = await self.persistence_store.get(f"session:{agent_id}:{session_id}")
|
|
session = Session(**json.loads(session), turns=[])
|
|
turns = []
|
|
if turn_ids:
|
|
for turn_id in turn_ids:
|
|
turn = await self.persistence_store.get(
|
|
f"session:{agent_id}:{session_id}:{turn_id}"
|
|
)
|
|
turn = json.loads(turn)
|
|
turn = Turn(**turn)
|
|
turns.append(turn)
|
|
return Session(
|
|
session_name=session.session_name,
|
|
session_id=session_id,
|
|
turns=turns if turns else [],
|
|
started_at=session.started_at,
|
|
)
|
|
|
|
async def delete_agents_session(self, agent_id: str, session_id: str) -> None:
|
|
await self.persistence_store.delete(f"session:{agent_id}:{session_id}")
|
|
|
|
async def delete_agents(self, agent_id: str) -> None:
|
|
await self.persistence_store.delete(f"agent:{agent_id}")
|