mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-17 17:09:51 +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>
260 lines
8.4 KiB
Python
260 lines
8.4 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 logging # allow-direct-logging
|
|
import os
|
|
import re
|
|
from logging.config import dictConfig # allow-direct-logging
|
|
|
|
from rich.console import Console
|
|
from rich.errors import MarkupError
|
|
from rich.logging import RichHandler
|
|
|
|
from llama_stack.core.datatypes import LoggingConfig
|
|
|
|
# Default log level
|
|
DEFAULT_LOG_LEVEL = logging.INFO
|
|
|
|
# Predefined categories
|
|
CATEGORIES = [
|
|
"core",
|
|
"server",
|
|
"router",
|
|
"inference",
|
|
"agents",
|
|
"safety",
|
|
"eval",
|
|
"tools",
|
|
"client",
|
|
"telemetry",
|
|
"openai_responses",
|
|
]
|
|
|
|
# Initialize category levels with default level
|
|
_category_levels: dict[str, int] = dict.fromkeys(CATEGORIES, DEFAULT_LOG_LEVEL)
|
|
|
|
|
|
def config_to_category_levels(category: str, level: str):
|
|
"""
|
|
Helper function to be called either by environment parsing or yaml parsing to go from a list of categories and levels to a dictionary ready to be
|
|
used by the logger dictConfig.
|
|
|
|
Parameters:
|
|
category (str): logging category to apply the level to
|
|
level (str): logging level to be used in the category
|
|
|
|
Returns:
|
|
Dict[str, int]: A dictionary mapping categories to their log levels.
|
|
"""
|
|
|
|
category_levels: dict[str, int] = {}
|
|
level_value = logging._nameToLevel.get(str(level).upper())
|
|
if level_value is None:
|
|
logging.warning(f"Unknown log level '{level}' for category '{category}'. Falling back to default 'INFO'.")
|
|
return category_levels
|
|
|
|
if category == "all":
|
|
# Apply the log level to all categories and the root logger
|
|
for cat in CATEGORIES:
|
|
category_levels[cat] = level_value
|
|
# Set the root logger's level to the specified level
|
|
category_levels["root"] = level_value
|
|
elif category in CATEGORIES:
|
|
category_levels[category] = level_value
|
|
else:
|
|
logging.warning(f"Unknown logging category: {category}. No changes made.")
|
|
return category_levels
|
|
|
|
|
|
def parse_yaml_config(yaml_config: LoggingConfig) -> dict[str, int]:
|
|
"""
|
|
Helper function to parse a yaml logging configuration found in the run.yaml
|
|
|
|
Parameters:
|
|
yaml_config (Logging): the logger config object found in the run.yaml
|
|
|
|
Returns:
|
|
Dict[str, int]: A dictionary mapping categories to their log levels.
|
|
"""
|
|
category_levels = {}
|
|
for category, level in yaml_config.category_levels.items():
|
|
category_levels.update(config_to_category_levels(category=category, level=level))
|
|
|
|
return category_levels
|
|
|
|
|
|
def parse_environment_config(env_config: str) -> dict[str, int]:
|
|
"""
|
|
Parse the LLAMA_STACK_LOGGING environment variable and return a dictionary of category log levels.
|
|
|
|
Parameters:
|
|
env_config (str): The value of the LLAMA_STACK_LOGGING environment variable.
|
|
|
|
Returns:
|
|
Dict[str, int]: A dictionary mapping categories to their log levels.
|
|
"""
|
|
category_levels = {}
|
|
delimiter = ","
|
|
for pair in env_config.split(delimiter):
|
|
if not pair.strip():
|
|
continue
|
|
|
|
try:
|
|
category, level = pair.split("=", 1)
|
|
category = category.strip().lower()
|
|
level = level.strip().upper() # Convert to uppercase for logging._nameToLevel
|
|
category_levels.update(config_to_category_levels(category=category, level=level))
|
|
|
|
except ValueError:
|
|
logging.warning(f"Invalid logging configuration: '{pair}'. Expected format: 'category=level'.")
|
|
|
|
return category_levels
|
|
|
|
|
|
def strip_rich_markup(text):
|
|
"""Remove Rich markup tags like [dim], [bold magenta], etc."""
|
|
return re.sub(r"\[/?[a-zA-Z0-9 _#=,]+\]", "", text)
|
|
|
|
|
|
class CustomRichHandler(RichHandler):
|
|
def __init__(self, *args, **kwargs):
|
|
kwargs["console"] = Console(width=150)
|
|
super().__init__(*args, **kwargs)
|
|
|
|
def emit(self, record):
|
|
"""Override emit to handle markup errors gracefully."""
|
|
try:
|
|
super().emit(record)
|
|
except MarkupError:
|
|
original_markup = self.markup
|
|
self.markup = False
|
|
try:
|
|
super().emit(record)
|
|
finally:
|
|
self.markup = original_markup
|
|
|
|
|
|
class CustomFileHandler(logging.FileHandler):
|
|
def __init__(self, filename, mode="a", encoding=None, delay=False):
|
|
super().__init__(filename, mode, encoding, delay)
|
|
# Default formatter to match console output
|
|
self.default_formatter = logging.Formatter("%(asctime)s %(name)s:%(lineno)d %(category)s: %(message)s")
|
|
self.setFormatter(self.default_formatter)
|
|
|
|
def emit(self, record):
|
|
if hasattr(record, "msg"):
|
|
record.msg = strip_rich_markup(str(record.msg))
|
|
super().emit(record)
|
|
|
|
|
|
def setup_logging(category_levels: dict[str, int], log_file: str | None) -> None:
|
|
"""
|
|
Configure logging based on the provided category log levels and an optional log file.
|
|
|
|
Parameters:
|
|
category_levels (Dict[str, int]): A dictionary mapping categories to their log levels.
|
|
log_file (str): Path to a log file to additionally pipe the logs into
|
|
"""
|
|
log_format = "%(asctime)s %(name)s:%(lineno)d %(category)s: %(message)s"
|
|
|
|
class CategoryFilter(logging.Filter):
|
|
"""Ensure category is always present in log records."""
|
|
|
|
def filter(self, record):
|
|
if not hasattr(record, "category"):
|
|
record.category = "uncategorized" # Default to 'uncategorized' if no category found
|
|
return True
|
|
|
|
# Determine the root logger's level (default to WARNING if not specified)
|
|
root_level = category_levels.get("root", logging.WARNING)
|
|
|
|
handlers = {
|
|
"console": {
|
|
"()": CustomRichHandler, # Use custom console handler
|
|
"formatter": "rich",
|
|
"rich_tracebacks": True,
|
|
"show_time": False,
|
|
"show_path": False,
|
|
"markup": True,
|
|
"filters": ["category_filter"],
|
|
}
|
|
}
|
|
|
|
# Add a file handler if log_file is set
|
|
if log_file:
|
|
handlers["file"] = {
|
|
"()": CustomFileHandler,
|
|
"filename": log_file,
|
|
"mode": "a",
|
|
"encoding": "utf-8",
|
|
}
|
|
|
|
logging_config = {
|
|
"version": 1,
|
|
"disable_existing_loggers": False,
|
|
"formatters": {
|
|
"rich": {
|
|
"()": logging.Formatter,
|
|
"format": log_format,
|
|
}
|
|
},
|
|
"handlers": handlers,
|
|
"filters": {
|
|
"category_filter": {
|
|
"()": CategoryFilter,
|
|
}
|
|
},
|
|
"loggers": {
|
|
category: {
|
|
"handlers": list(handlers.keys()), # Apply all handlers
|
|
"level": category_levels.get(category, DEFAULT_LOG_LEVEL),
|
|
"propagate": False, # Disable propagation to root logger
|
|
}
|
|
for category in CATEGORIES
|
|
},
|
|
"root": {
|
|
"handlers": list(handlers.keys()),
|
|
"level": root_level, # Set root logger's level dynamically
|
|
},
|
|
}
|
|
dictConfig(logging_config)
|
|
|
|
# Ensure third-party libraries follow the root log level
|
|
for _, logger in logging.root.manager.loggerDict.items():
|
|
if isinstance(logger, logging.Logger):
|
|
logger.setLevel(root_level)
|
|
|
|
|
|
def get_logger(
|
|
name: str, category: str = "uncategorized", config: LoggingConfig | None | None = None
|
|
) -> logging.LoggerAdapter:
|
|
"""
|
|
Returns a logger with the specified name and category.
|
|
If no category is provided, defaults to 'uncategorized'.
|
|
|
|
Parameters:
|
|
name (str): The name of the logger (e.g., module or filename).
|
|
category (str): The category of the logger (default 'uncategorized').
|
|
config (Logging): optional yaml config to override the existing logger configuration
|
|
|
|
Returns:
|
|
logging.LoggerAdapter: Configured logger with category support.
|
|
"""
|
|
if config:
|
|
_category_levels.update(parse_yaml_config(config))
|
|
|
|
logger = logging.getLogger(name)
|
|
logger.setLevel(_category_levels.get(category, DEFAULT_LOG_LEVEL))
|
|
return logging.LoggerAdapter(logger, {"category": category})
|
|
|
|
|
|
env_config = os.environ.get("LLAMA_STACK_LOGGING", "")
|
|
if env_config:
|
|
_category_levels.update(parse_environment_config(env_config))
|
|
|
|
log_file = os.environ.get("LLAMA_STACK_LOG_FILE")
|
|
|
|
setup_logging(_category_levels, log_file)
|