mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-27 06:28:50 +00:00
Some checks failed
Coverage Badge / unit-tests (push) Failing after 1s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Integration Tests / discover-tests (push) Successful in 3s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 5s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 5s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 5s
Test Llama Stack Build / generate-matrix (push) Successful in 4s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 5s
Python Package Build Test / build (3.13) (push) Failing after 2s
Test Llama Stack Build / build-single-provider (push) Failing after 3s
Python Package Build Test / build (3.12) (push) Failing after 2s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 5s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 6s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 3s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 5s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 4s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 5s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 9s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Failing after 6s
Test External API and Providers / test-external (venv) (push) Failing after 5s
Update ReadTheDocs / update-readthedocs (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 5s
Test Llama Stack Build / build (push) Failing after 3s
Unit Tests / unit-tests (3.12) (push) Failing after 5s
Integration Tests / test-matrix (push) Failing after 7s
Pre-commit / pre-commit (push) Successful in 1m13s
# What does this PR do? in #2637, I combined the run and build config provider types to both use `Provider` since this includes a provider_id, a user must now specify this when writing a build yaml. This is not very clear because all a user should care about upon build is the code to be installed (the module and the provider_type) introduce `BuildProvider` and fixup the parts of the code impacted by this Signed-off-by: Charlie Doern <cdoern@redhat.com>
114 lines
4 KiB
Python
114 lines
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.
|
|
|
|
from pathlib import Path
|
|
|
|
from llama_stack.apis.models import ModelType
|
|
from llama_stack.distribution.datatypes import BuildProvider, ModelInput, Provider, ToolGroupInput
|
|
from llama_stack.providers.inline.inference.sentence_transformers import (
|
|
SentenceTransformersInferenceConfig,
|
|
)
|
|
from llama_stack.providers.remote.inference.watsonx import WatsonXConfig
|
|
from llama_stack.providers.remote.inference.watsonx.models import MODEL_ENTRIES
|
|
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings, get_model_registry
|
|
|
|
|
|
def get_distribution_template() -> DistributionTemplate:
|
|
providers = {
|
|
"inference": [
|
|
BuildProvider(provider_type="remote::watsonx"),
|
|
BuildProvider(provider_type="inline::sentence-transformers"),
|
|
],
|
|
"vector_io": [BuildProvider(provider_type="inline::faiss")],
|
|
"safety": [BuildProvider(provider_type="inline::llama-guard")],
|
|
"agents": [BuildProvider(provider_type="inline::meta-reference")],
|
|
"telemetry": [BuildProvider(provider_type="inline::meta-reference")],
|
|
"eval": [BuildProvider(provider_type="inline::meta-reference")],
|
|
"datasetio": [
|
|
BuildProvider(provider_type="remote::huggingface"),
|
|
BuildProvider(provider_type="inline::localfs"),
|
|
],
|
|
"scoring": [
|
|
BuildProvider(provider_type="inline::basic"),
|
|
BuildProvider(provider_type="inline::llm-as-judge"),
|
|
BuildProvider(provider_type="inline::braintrust"),
|
|
],
|
|
"tool_runtime": [
|
|
BuildProvider(provider_type="remote::brave-search"),
|
|
BuildProvider(provider_type="remote::tavily-search"),
|
|
BuildProvider(provider_type="inline::rag-runtime"),
|
|
BuildProvider(provider_type="remote::model-context-protocol"),
|
|
],
|
|
}
|
|
|
|
inference_provider = Provider(
|
|
provider_id="watsonx",
|
|
provider_type="remote::watsonx",
|
|
config=WatsonXConfig.sample_run_config(),
|
|
)
|
|
|
|
embedding_provider = Provider(
|
|
provider_id="sentence-transformers",
|
|
provider_type="inline::sentence-transformers",
|
|
config=SentenceTransformersInferenceConfig.sample_run_config(),
|
|
)
|
|
|
|
available_models = {
|
|
"watsonx": MODEL_ENTRIES,
|
|
}
|
|
default_tool_groups = [
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::websearch",
|
|
provider_id="tavily-search",
|
|
),
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::rag",
|
|
provider_id="rag-runtime",
|
|
),
|
|
]
|
|
|
|
embedding_model = ModelInput(
|
|
model_id="all-MiniLM-L6-v2",
|
|
provider_id="sentence-transformers",
|
|
model_type=ModelType.embedding,
|
|
metadata={
|
|
"embedding_dimension": 384,
|
|
},
|
|
)
|
|
|
|
default_models, _ = get_model_registry(available_models)
|
|
return DistributionTemplate(
|
|
name="watsonx",
|
|
distro_type="remote_hosted",
|
|
description="Use watsonx for running LLM inference",
|
|
container_image=None,
|
|
template_path=Path(__file__).parent / "doc_template.md",
|
|
providers=providers,
|
|
available_models_by_provider=available_models,
|
|
run_configs={
|
|
"run.yaml": RunConfigSettings(
|
|
provider_overrides={
|
|
"inference": [inference_provider, embedding_provider],
|
|
},
|
|
default_models=default_models + [embedding_model],
|
|
default_tool_groups=default_tool_groups,
|
|
),
|
|
},
|
|
run_config_env_vars={
|
|
"LLAMASTACK_PORT": (
|
|
"5001",
|
|
"Port for the Llama Stack distribution server",
|
|
),
|
|
"WATSONX_API_KEY": (
|
|
"",
|
|
"watsonx API Key",
|
|
),
|
|
"WATSONX_PROJECT_ID": (
|
|
"",
|
|
"watsonx Project ID",
|
|
),
|
|
},
|
|
)
|