llama-stack-mirror/llama_stack/core/configure.py
Francisco Javier Arceo 6620b625f1 adding logo and favicon
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>
2025-08-21 16:06:30 -04:00

181 lines
6.5 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 textwrap
from typing import Any
from llama_stack.core.datatypes import (
LLAMA_STACK_RUN_CONFIG_VERSION,
DistributionSpec,
Provider,
StackRunConfig,
)
from llama_stack.core.distribution import (
builtin_automatically_routed_apis,
get_provider_registry,
)
from llama_stack.core.stack import cast_image_name_to_string, replace_env_vars
from llama_stack.core.utils.config_dirs import EXTERNAL_PROVIDERS_DIR
from llama_stack.core.utils.dynamic import instantiate_class_type
from llama_stack.core.utils.prompt_for_config import prompt_for_config
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import Api, ProviderSpec
logger = get_logger(name=__name__, category="core")
def configure_single_provider(registry: dict[str, ProviderSpec], provider: Provider) -> Provider:
provider_spec = registry[provider.provider_type]
config_type = instantiate_class_type(provider_spec.config_class)
try:
if provider.config:
existing = config_type(**provider.config)
else:
existing = None
except Exception:
existing = None
cfg = prompt_for_config(config_type, existing)
return Provider(
provider_id=provider.provider_id,
provider_type=provider.provider_type,
config=cfg.model_dump(),
)
def configure_api_providers(config: StackRunConfig, build_spec: DistributionSpec) -> StackRunConfig:
is_nux = len(config.providers) == 0
if is_nux:
logger.info(
textwrap.dedent(
"""
Llama Stack is composed of several APIs working together. For each API served by the Stack,
we need to configure the providers (implementations) you want to use for these APIs.
"""
)
)
provider_registry = get_provider_registry()
builtin_apis = [a.routing_table_api for a in builtin_automatically_routed_apis()]
if config.apis:
apis_to_serve = config.apis
else:
apis_to_serve = [a.value for a in Api if a not in (Api.telemetry, Api.inspect, Api.providers)]
for api_str in apis_to_serve:
api = Api(api_str)
if api in builtin_apis:
continue
if api not in provider_registry:
raise ValueError(f"Unknown API `{api_str}`")
existing_providers = config.providers.get(api_str, [])
if existing_providers:
logger.info(f"Re-configuring existing providers for API `{api_str}`...")
updated_providers = []
for p in existing_providers:
logger.info(f"> Configuring provider `({p.provider_type})`")
updated_providers.append(configure_single_provider(provider_registry[api], p))
logger.info("")
else:
# we are newly configuring this API
plist = build_spec.providers.get(api_str, [])
plist = plist if isinstance(plist, list) else [plist]
if not plist:
raise ValueError(f"No provider configured for API {api_str}?")
logger.info(f"Configuring API `{api_str}`...")
updated_providers = []
for i, provider in enumerate(plist):
if i >= 1:
others = ", ".join(p.provider_type for p in plist[i:])
logger.info(
f"Not configuring other providers ({others}) interactively. Please edit the resulting YAML directly.\n"
)
break
logger.info(f"> Configuring provider `({provider.provider_type})`")
pid = provider.provider_type.split("::")[-1]
updated_providers.append(
configure_single_provider(
provider_registry[api],
Provider(
provider_id=(f"{pid}-{i:02d}" if len(plist) > 1 else pid),
provider_type=provider.provider_type,
config={},
),
)
)
logger.info("")
config.providers[api_str] = updated_providers
return config
def upgrade_from_routing_table(
config_dict: dict[str, Any],
) -> dict[str, Any]:
def get_providers(entries):
return [
Provider(
provider_id=(f"{entry['provider_type']}-{i:02d}" if len(entries) > 1 else entry["provider_type"]),
provider_type=entry["provider_type"],
config=entry["config"],
)
for i, entry in enumerate(entries)
]
providers_by_api = {}
routing_table = config_dict.get("routing_table", {})
for api_str, entries in routing_table.items():
providers = get_providers(entries)
providers_by_api[api_str] = providers
provider_map = config_dict.get("api_providers", config_dict.get("provider_map", {}))
if provider_map:
for api_str, provider in provider_map.items():
if isinstance(provider, dict) and "provider_type" in provider:
providers_by_api[api_str] = [
Provider(
provider_id=f"{provider['provider_type']}",
provider_type=provider["provider_type"],
config=provider["config"],
)
]
config_dict["providers"] = providers_by_api
config_dict.pop("routing_table", None)
config_dict.pop("api_providers", None)
config_dict.pop("provider_map", None)
config_dict["apis"] = config_dict["apis_to_serve"]
config_dict.pop("apis_to_serve", None)
return config_dict
def parse_and_maybe_upgrade_config(config_dict: dict[str, Any]) -> StackRunConfig:
version = config_dict.get("version", None)
if version == LLAMA_STACK_RUN_CONFIG_VERSION:
processed_config_dict = replace_env_vars(config_dict)
return StackRunConfig(**cast_image_name_to_string(processed_config_dict))
if "routing_table" in config_dict:
logger.info("Upgrading config...")
config_dict = upgrade_from_routing_table(config_dict)
config_dict["version"] = LLAMA_STACK_RUN_CONFIG_VERSION
if not config_dict.get("external_providers_dir", None):
config_dict["external_providers_dir"] = EXTERNAL_PROVIDERS_DIR
processed_config_dict = replace_env_vars(config_dict)
return StackRunConfig(**cast_image_name_to_string(processed_config_dict))