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>
164 lines
5.9 KiB
Python
164 lines
5.9 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 importlib.resources
|
|
import sys
|
|
|
|
from pydantic import BaseModel
|
|
from termcolor import cprint
|
|
|
|
from llama_stack.core.datatypes import BuildConfig
|
|
from llama_stack.core.distribution import get_provider_registry
|
|
from llama_stack.core.external import load_external_apis
|
|
from llama_stack.core.utils.exec import run_command
|
|
from llama_stack.core.utils.image_types import LlamaStackImageType
|
|
from llama_stack.distributions.template import DistributionTemplate
|
|
from llama_stack.log import get_logger
|
|
from llama_stack.providers.datatypes import Api
|
|
|
|
log = get_logger(name=__name__, category="core")
|
|
|
|
# These are the dependencies needed by the distribution server.
|
|
# `llama-stack` is automatically installed by the installation script.
|
|
SERVER_DEPENDENCIES = [
|
|
"aiosqlite",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"uvicorn",
|
|
"opentelemetry-sdk",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
]
|
|
|
|
|
|
class ApiInput(BaseModel):
|
|
api: Api
|
|
provider: str
|
|
|
|
|
|
def get_provider_dependencies(
|
|
config: BuildConfig | DistributionTemplate,
|
|
) -> tuple[list[str], list[str], list[str]]:
|
|
"""Get normal and special dependencies from provider configuration."""
|
|
if isinstance(config, DistributionTemplate):
|
|
config = config.build_config()
|
|
|
|
providers = config.distribution_spec.providers
|
|
additional_pip_packages = config.additional_pip_packages
|
|
|
|
deps = []
|
|
external_provider_deps = []
|
|
registry = get_provider_registry(config)
|
|
for api_str, provider_or_providers in providers.items():
|
|
providers_for_api = registry[Api(api_str)]
|
|
|
|
providers = provider_or_providers if isinstance(provider_or_providers, list) else [provider_or_providers]
|
|
|
|
for provider in providers:
|
|
# Providers from BuildConfig and RunConfig are subtly different - not great
|
|
provider_type = provider if isinstance(provider, str) else provider.provider_type
|
|
|
|
if provider_type not in providers_for_api:
|
|
raise ValueError(f"Provider `{provider}` is not available for API `{api_str}`")
|
|
|
|
provider_spec = providers_for_api[provider_type]
|
|
if hasattr(provider_spec, "is_external") and provider_spec.is_external:
|
|
# this ensures we install the top level module for our external providers
|
|
if provider_spec.module:
|
|
if isinstance(provider_spec.module, str):
|
|
external_provider_deps.append(provider_spec.module)
|
|
else:
|
|
external_provider_deps.extend(provider_spec.module)
|
|
if hasattr(provider_spec, "pip_packages"):
|
|
deps.extend(provider_spec.pip_packages)
|
|
if hasattr(provider_spec, "container_image") and provider_spec.container_image:
|
|
raise ValueError("A stack's dependencies cannot have a container image")
|
|
|
|
normal_deps = []
|
|
special_deps = []
|
|
for package in deps:
|
|
if "--no-deps" in package or "--index-url" in package:
|
|
special_deps.append(package)
|
|
else:
|
|
normal_deps.append(package)
|
|
|
|
normal_deps.extend(additional_pip_packages or [])
|
|
|
|
return list(set(normal_deps)), list(set(special_deps)), list(set(external_provider_deps))
|
|
|
|
|
|
def print_pip_install_help(config: BuildConfig):
|
|
normal_deps, special_deps, _ = get_provider_dependencies(config)
|
|
|
|
cprint(
|
|
f"Please install needed dependencies using the following commands:\n\nuv pip install {' '.join(normal_deps)}",
|
|
color="yellow",
|
|
file=sys.stderr,
|
|
)
|
|
for special_dep in special_deps:
|
|
cprint(f"uv pip install {special_dep}", color="yellow", file=sys.stderr)
|
|
print()
|
|
|
|
|
|
def build_image(
|
|
build_config: BuildConfig,
|
|
image_name: str,
|
|
distro_or_config: str,
|
|
run_config: str | None = None,
|
|
):
|
|
container_base = build_config.distribution_spec.container_image or "python:3.12-slim"
|
|
|
|
normal_deps, special_deps, external_provider_deps = get_provider_dependencies(build_config)
|
|
normal_deps += SERVER_DEPENDENCIES
|
|
if build_config.external_apis_dir:
|
|
external_apis = load_external_apis(build_config)
|
|
if external_apis:
|
|
for _, api_spec in external_apis.items():
|
|
normal_deps.extend(api_spec.pip_packages)
|
|
|
|
if build_config.image_type == LlamaStackImageType.CONTAINER.value:
|
|
script = str(importlib.resources.files("llama_stack") / "core/build_container.sh")
|
|
args = [
|
|
script,
|
|
"--distro-or-config",
|
|
distro_or_config,
|
|
"--image-name",
|
|
image_name,
|
|
"--container-base",
|
|
container_base,
|
|
"--normal-deps",
|
|
" ".join(normal_deps),
|
|
]
|
|
# When building from a config file (not a template), include the run config path in the
|
|
# build arguments
|
|
if run_config is not None:
|
|
args.extend(["--run-config", run_config])
|
|
else:
|
|
script = str(importlib.resources.files("llama_stack") / "core/build_venv.sh")
|
|
args = [
|
|
script,
|
|
"--env-name",
|
|
str(image_name),
|
|
"--normal-deps",
|
|
" ".join(normal_deps),
|
|
]
|
|
|
|
# Always pass both arguments, even if empty, to maintain consistent positional arguments
|
|
if special_deps:
|
|
args.extend(["--optional-deps", "#".join(special_deps)])
|
|
if external_provider_deps:
|
|
args.extend(
|
|
["--external-provider-deps", "#".join(external_provider_deps)]
|
|
) # the script will install external provider module, get its deps, and install those too.
|
|
|
|
return_code = run_command(args)
|
|
|
|
if return_code != 0:
|
|
log.error(
|
|
f"Failed to build target {image_name} with return code {return_code}",
|
|
)
|
|
|
|
return return_code
|