mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
ac5fd57387
# What does this PR do? * Given that our API packages use "import *" in `__init.py__` we don't need to do `from llama_stack.apis.models.models` but simply from llama_stack.apis.models. The decision to use `import *` is debatable and should probably be revisited at one point. * Remove unneeded Ruff F401 rule * Consolidate Ruff F403 rule in the pyprojectfrom llama_stack.apis.models.models Signed-off-by: Sébastien Han <seb@redhat.com>
104 lines
3.5 KiB
Python
104 lines
3.5 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.
|
|
|
|
from pathlib import Path
|
|
|
|
from llama_stack.apis.models import ModelType
|
|
from llama_stack.distribution.datatypes import 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": ["remote::watsonx", "inline::sentence-transformers"],
|
|
"vector_io": ["inline::faiss"],
|
|
"safety": ["inline::llama-guard"],
|
|
"agents": ["inline::meta-reference"],
|
|
"telemetry": ["inline::meta-reference"],
|
|
"eval": ["inline::meta-reference"],
|
|
"datasetio": ["remote::huggingface", "inline::localfs"],
|
|
"scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
|
|
"tool_runtime": [
|
|
"remote::brave-search",
|
|
"remote::tavily-search",
|
|
"inline::rag-runtime",
|
|
"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",
|
|
),
|
|
},
|
|
)
|