mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-17 13:22:36 +00:00
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> chore: Enable keyword search for Milvus inline (#3073) With https://github.com/milvus-io/milvus-lite/pull/294 - Milvus Lite supports keyword search using BM25. While introducing keyword search we had explicitly disabled it for inline milvus. This PR removes the need for the check, and enables `inline::milvus` for tests. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Run llama stack with `inline::milvus` enabled: ``` pytest tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes --stack-config=http://localhost:8321 --embedding-model=all-MiniLM-L6-v2 -v ``` ``` INFO 2025-08-07 17:06:20,932 tests.integration.conftest:64 tests: Setting DISABLE_CODE_SANDBOX=1 for macOS =========================================================================================== test session starts ============================================================================================ platform darwin -- Python 3.12.11, pytest-7.4.4, pluggy-1.5.0 -- /Users/vnarsing/miniconda3/envs/stack-client/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.11', 'Platform': 'macOS-14.7.6-arm64-arm-64bit', 'Packages': {'pytest': '7.4.4', 'pluggy': '1.5.0'}, 'Plugins': {'asyncio': '0.23.8', 'cov': '6.0.0', 'timeout': '2.2.0', 'socket': '0.7.0', 'html': '3.1.1', 'langsmith': '0.3.39', 'anyio': '4.8.0', 'metadata': '3.0.0'}} rootdir: /Users/vnarsing/go/src/github/meta-llama/llama-stack configfile: pyproject.toml plugins: asyncio-0.23.8, cov-6.0.0, timeout-2.2.0, socket-0.7.0, html-3.1.1, langsmith-0.3.39, anyio-4.8.0, metadata-3.0.0 asyncio: mode=Mode.AUTO collected 3 items tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-vector] PASSED [ 33%] tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-keyword] PASSED [ 66%] tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-hybrid] PASSED [100%] ============================================================================================ 3 passed in 4.75s ============================================================================================= ``` Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com> Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com> chore: Fixup main pre commit (#3204) build: Bump version to 0.2.18 chore: Faster npm pre-commit (#3206) Adds npm to pre-commit.yml installation and caches ui Removes node installation during pre-commit. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> chiecking in for tonight, wip moving to agents api Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> remove log Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> updated Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> fix: disable ui-prettier & ui-eslint (#3207) chore(pre-commit): add pre-commit hook to enforce llama_stack logger usage (#3061) This PR adds a step in pre-commit to enforce using `llama_stack` logger. Currently, various parts of the code base uses different loggers. As a custom `llama_stack` logger exist and used in the codebase, it is better to standardize its utilization. Signed-off-by: Mustafa Elbehery <melbeher@redhat.com> Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu> fix: fix ```openai_embeddings``` for asymmetric embedding NIMs (#3205) NVIDIA asymmetric embedding models (e.g., `nvidia/llama-3.2-nv-embedqa-1b-v2`) require an `input_type` parameter not present in the standard OpenAI embeddings API. This PR adds the `input_type="query"` as default and updates the documentation to suggest using the `embedding` API for passage embeddings. <!-- If resolving an issue, uncomment and update the line below --> Resolves #2892 ``` pytest -s -v tests/integration/inference/test_openai_embeddings.py --stack-config="inference=nvidia" --embedding-model="nvidia/llama-3.2-nv-embedqa-1b-v2" --env NVIDIA_API_KEY={nvidia_api_key} --env NVIDIA_BASE_URL="https://integrate.api.nvidia.com" ``` cleaning up Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> updating session manager to cache messages locally Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> fix linter Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> more cleanup Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
228 lines
8.3 KiB
Python
228 lines
8.3 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 uuid
|
|
from datetime import UTC, datetime
|
|
|
|
from llama_stack.apis.agents import AgentConfig, Session, ToolExecutionStep, Turn
|
|
from llama_stack.apis.common.errors import SessionNotFoundError
|
|
from llama_stack.core.access_control.access_control import AccessDeniedError, is_action_allowed
|
|
from llama_stack.core.access_control.datatypes import AccessRule
|
|
from llama_stack.core.datatypes import User
|
|
from llama_stack.core.request_headers import get_authenticated_user
|
|
from llama_stack.log import get_logger
|
|
from llama_stack.providers.utils.kvstore import KVStore
|
|
|
|
log = get_logger(name=__name__, category="agents")
|
|
|
|
|
|
class AgentSessionInfo(Session):
|
|
# TODO: is this used anywhere?
|
|
vector_db_id: str | None = None
|
|
started_at: datetime
|
|
owner: User | None = None
|
|
identifier: str | None = None
|
|
type: str = "session"
|
|
|
|
|
|
class AgentInfo(AgentConfig):
|
|
created_at: datetime
|
|
|
|
|
|
class AgentPersistence:
|
|
def __init__(self, agent_id: str, kvstore: KVStore, policy: list[AccessRule]):
|
|
self.agent_id = agent_id
|
|
self.kvstore = kvstore
|
|
self.policy = policy
|
|
|
|
async def create_session(self, name: str) -> str:
|
|
session_id = str(uuid.uuid4())
|
|
|
|
# Get current user's auth attributes for new sessions
|
|
user = get_authenticated_user()
|
|
|
|
session_info = AgentSessionInfo(
|
|
session_id=session_id,
|
|
session_name=name,
|
|
started_at=datetime.now(UTC),
|
|
owner=user,
|
|
turns=[],
|
|
identifier=name, # should this be qualified in any way?
|
|
)
|
|
if not is_action_allowed(self.policy, "create", session_info, user):
|
|
raise AccessDeniedError("create", session_info, user)
|
|
|
|
await self.kvstore.set(
|
|
key=f"session:{self.agent_id}:{session_id}",
|
|
value=session_info.model_dump_json(),
|
|
)
|
|
return session_id
|
|
|
|
async def get_session_info(self, session_id: str) -> AgentSessionInfo:
|
|
value = await self.kvstore.get(
|
|
key=f"session:{self.agent_id}:{session_id}",
|
|
)
|
|
if not value:
|
|
raise SessionNotFoundError(session_id)
|
|
|
|
session_info = AgentSessionInfo(**json.loads(value))
|
|
|
|
# Check access to session
|
|
if not self._check_session_access(session_info):
|
|
return None
|
|
|
|
return session_info
|
|
|
|
def _check_session_access(self, session_info: AgentSessionInfo) -> bool:
|
|
"""Check if current user has access to the session."""
|
|
# Handle backward compatibility for old sessions without access control
|
|
if not hasattr(session_info, "access_attributes") and not hasattr(session_info, "owner"):
|
|
return True
|
|
|
|
return is_action_allowed(self.policy, "read", session_info, get_authenticated_user())
|
|
|
|
async def get_session_if_accessible(self, session_id: str) -> AgentSessionInfo | None:
|
|
"""Get session info if the user has access to it. For internal use by sub-session methods."""
|
|
session_info = await self.get_session_info(session_id)
|
|
if not session_info:
|
|
return None
|
|
|
|
return session_info
|
|
|
|
async def add_vector_db_to_session(self, session_id: str, vector_db_id: str):
|
|
session_info = await self.get_session_if_accessible(session_id)
|
|
if session_info is None:
|
|
raise SessionNotFoundError(session_id)
|
|
|
|
session_info.vector_db_id = vector_db_id
|
|
await self.kvstore.set(
|
|
key=f"session:{self.agent_id}:{session_id}",
|
|
value=session_info.model_dump_json(),
|
|
)
|
|
|
|
async def add_turn_to_session(self, session_id: str, turn: Turn):
|
|
if not await self.get_session_if_accessible(session_id):
|
|
raise SessionNotFoundError(session_id)
|
|
|
|
await self.kvstore.set(
|
|
key=f"session:{self.agent_id}:{session_id}:{turn.turn_id}",
|
|
value=turn.model_dump_json(),
|
|
)
|
|
|
|
async def get_session_turns(self, session_id: str) -> list[Turn]:
|
|
if not await self.get_session_if_accessible(session_id):
|
|
raise SessionNotFoundError(session_id)
|
|
|
|
values = await self.kvstore.values_in_range(
|
|
start_key=f"session:{self.agent_id}:{session_id}:",
|
|
end_key=f"session:{self.agent_id}:{session_id}:\xff\xff\xff\xff",
|
|
)
|
|
turns = []
|
|
for value in values:
|
|
try:
|
|
turn = Turn(**json.loads(value))
|
|
turns.append(turn)
|
|
except Exception as e:
|
|
log.error(f"Error parsing turn: {e}")
|
|
continue
|
|
|
|
# The kvstore does not guarantee order, so we sort by started_at
|
|
# to ensure consistent ordering of turns.
|
|
turns.sort(key=lambda t: t.started_at)
|
|
|
|
return turns
|
|
|
|
async def get_session_turn(self, session_id: str, turn_id: str) -> Turn | None:
|
|
if not await self.get_session_if_accessible(session_id):
|
|
raise SessionNotFoundError(session_id)
|
|
|
|
value = await self.kvstore.get(
|
|
key=f"session:{self.agent_id}:{session_id}:{turn_id}",
|
|
)
|
|
if not value:
|
|
return None
|
|
return Turn(**json.loads(value))
|
|
|
|
async def set_in_progress_tool_call_step(self, session_id: str, turn_id: str, step: ToolExecutionStep):
|
|
if not await self.get_session_if_accessible(session_id):
|
|
raise SessionNotFoundError(session_id)
|
|
|
|
await self.kvstore.set(
|
|
key=f"in_progress_tool_call_step:{self.agent_id}:{session_id}:{turn_id}",
|
|
value=step.model_dump_json(),
|
|
)
|
|
|
|
async def get_in_progress_tool_call_step(self, session_id: str, turn_id: str) -> ToolExecutionStep | None:
|
|
if not await self.get_session_if_accessible(session_id):
|
|
return None
|
|
|
|
value = await self.kvstore.get(
|
|
key=f"in_progress_tool_call_step:{self.agent_id}:{session_id}:{turn_id}",
|
|
)
|
|
return ToolExecutionStep(**json.loads(value)) if value else None
|
|
|
|
async def set_num_infer_iters_in_turn(self, session_id: str, turn_id: str, num_infer_iters: int):
|
|
if not await self.get_session_if_accessible(session_id):
|
|
raise SessionNotFoundError(session_id)
|
|
|
|
await self.kvstore.set(
|
|
key=f"num_infer_iters_in_turn:{self.agent_id}:{session_id}:{turn_id}",
|
|
value=str(num_infer_iters),
|
|
)
|
|
|
|
async def get_num_infer_iters_in_turn(self, session_id: str, turn_id: str) -> int | None:
|
|
if not await self.get_session_if_accessible(session_id):
|
|
return None
|
|
|
|
value = await self.kvstore.get(
|
|
key=f"num_infer_iters_in_turn:{self.agent_id}:{session_id}:{turn_id}",
|
|
)
|
|
return int(value) if value else None
|
|
|
|
async def list_sessions(self) -> list[Session]:
|
|
values = await self.kvstore.values_in_range(
|
|
start_key=f"session:{self.agent_id}:",
|
|
end_key=f"session:{self.agent_id}:\xff\xff\xff\xff",
|
|
)
|
|
sessions = []
|
|
for value in values:
|
|
try:
|
|
data = json.loads(value)
|
|
if "turn_id" in data:
|
|
continue
|
|
|
|
session_info = Session(**data)
|
|
sessions.append(session_info)
|
|
except Exception as e:
|
|
log.error(f"Error parsing session info: {e}")
|
|
continue
|
|
return sessions
|
|
|
|
async def delete_session_turns(self, session_id: str) -> None:
|
|
"""Delete all turns and their associated data for a session.
|
|
|
|
Args:
|
|
session_id: The ID of the session whose turns should be deleted.
|
|
"""
|
|
turns = await self.get_session_turns(session_id)
|
|
for turn in turns:
|
|
await self.kvstore.delete(key=f"session:{self.agent_id}:{session_id}:{turn.turn_id}")
|
|
|
|
async def delete_session(self, session_id: str) -> None:
|
|
"""Delete a session and all its associated turns.
|
|
|
|
Args:
|
|
session_id: The ID of the session to delete.
|
|
|
|
Raises:
|
|
ValueError: If the session does not exist.
|
|
"""
|
|
session_info = await self.get_session_info(session_id)
|
|
if session_info is None:
|
|
raise SessionNotFoundError(session_id)
|
|
|
|
await self.kvstore.delete(key=f"session:{self.agent_id}:{session_id}")
|