mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-17 17:02:49 +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>
114 lines
3.8 KiB
Python
114 lines
3.8 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 datetime import datetime
|
|
|
|
import psycopg2
|
|
from psycopg2.extras import DictCursor
|
|
|
|
from llama_stack.log import get_logger
|
|
|
|
from ..api import KVStore
|
|
from ..config import PostgresKVStoreConfig
|
|
|
|
log = get_logger(name=__name__, category="kvstore")
|
|
|
|
|
|
class PostgresKVStoreImpl(KVStore):
|
|
def __init__(self, config: PostgresKVStoreConfig):
|
|
self.config = config
|
|
self.conn = None
|
|
self.cursor = None
|
|
|
|
async def initialize(self) -> None:
|
|
try:
|
|
self.conn = psycopg2.connect(
|
|
host=self.config.host,
|
|
port=self.config.port,
|
|
database=self.config.db,
|
|
user=self.config.user,
|
|
password=self.config.password,
|
|
sslmode=self.config.ssl_mode,
|
|
sslrootcert=self.config.ca_cert_path,
|
|
)
|
|
self.conn.autocommit = True
|
|
self.cursor = self.conn.cursor(cursor_factory=DictCursor)
|
|
|
|
# Create table if it doesn't exist
|
|
self.cursor.execute(
|
|
f"""
|
|
CREATE TABLE IF NOT EXISTS {self.config.table_name} (
|
|
key TEXT PRIMARY KEY,
|
|
value TEXT,
|
|
expiration TIMESTAMP
|
|
)
|
|
"""
|
|
)
|
|
except Exception as e:
|
|
log.exception("Could not connect to PostgreSQL database server")
|
|
raise RuntimeError("Could not connect to PostgreSQL database server") from e
|
|
|
|
def _namespaced_key(self, key: str) -> str:
|
|
if not self.config.namespace:
|
|
return key
|
|
return f"{self.config.namespace}:{key}"
|
|
|
|
async def set(self, key: str, value: str, expiration: datetime | None = None) -> None:
|
|
key = self._namespaced_key(key)
|
|
self.cursor.execute(
|
|
f"""
|
|
INSERT INTO {self.config.table_name} (key, value, expiration)
|
|
VALUES (%s, %s, %s)
|
|
ON CONFLICT (key) DO UPDATE
|
|
SET value = EXCLUDED.value, expiration = EXCLUDED.expiration
|
|
""",
|
|
(key, value, expiration),
|
|
)
|
|
|
|
async def get(self, key: str) -> str | None:
|
|
key = self._namespaced_key(key)
|
|
self.cursor.execute(
|
|
f"""
|
|
SELECT value FROM {self.config.table_name}
|
|
WHERE key = %s
|
|
AND (expiration IS NULL OR expiration > NOW())
|
|
""",
|
|
(key,),
|
|
)
|
|
result = self.cursor.fetchone()
|
|
return result[0] if result else None
|
|
|
|
async def delete(self, key: str) -> None:
|
|
key = self._namespaced_key(key)
|
|
self.cursor.execute(
|
|
f"DELETE FROM {self.config.table_name} WHERE key = %s",
|
|
(key,),
|
|
)
|
|
|
|
async def values_in_range(self, start_key: str, end_key: str) -> list[str]:
|
|
start_key = self._namespaced_key(start_key)
|
|
end_key = self._namespaced_key(end_key)
|
|
|
|
self.cursor.execute(
|
|
f"""
|
|
SELECT value FROM {self.config.table_name}
|
|
WHERE key >= %s AND key < %s
|
|
AND (expiration IS NULL OR expiration > NOW())
|
|
ORDER BY key
|
|
""",
|
|
(start_key, end_key),
|
|
)
|
|
return [row[0] for row in self.cursor.fetchall()]
|
|
|
|
async def keys_in_range(self, start_key: str, end_key: str) -> list[str]:
|
|
start_key = self._namespaced_key(start_key)
|
|
end_key = self._namespaced_key(end_key)
|
|
|
|
self.cursor.execute(
|
|
f"SELECT key FROM {self.config.table_name} WHERE key >= %s AND key < %s",
|
|
(start_key, end_key),
|
|
)
|
|
return [row[0] for row in self.cursor.fetchall()]
|