mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-31 09:23:54 +00:00
99 lines
3.3 KiB
Python
99 lines
3.3 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.preprocessing.preprocessors import PreprocessorInput
|
|
from llama_stack.distribution.datatypes import Provider, ToolGroupInput
|
|
from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
|
|
from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES
|
|
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings, get_model_registry
|
|
|
|
|
|
def get_distribution_template() -> DistributionTemplate:
|
|
providers = {
|
|
"inference": ["remote::nvidia"],
|
|
"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::code-interpreter",
|
|
"inline::rag-runtime",
|
|
"remote::model-context-protocol",
|
|
],
|
|
"preprocessing": ["inline::basic", "inline::simple_chunking"],
|
|
}
|
|
|
|
inference_provider = Provider(
|
|
provider_id="nvidia",
|
|
provider_type="remote::nvidia",
|
|
config=NVIDIAConfig.sample_run_config(),
|
|
)
|
|
|
|
available_models = {
|
|
"nvidia": MODEL_ENTRIES,
|
|
}
|
|
default_tool_groups = [
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::websearch",
|
|
provider_id="tavily-search",
|
|
),
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::rag",
|
|
provider_id="rag-runtime",
|
|
),
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::code_interpreter",
|
|
provider_id="code-interpreter",
|
|
),
|
|
]
|
|
default_preprocessors = [
|
|
PreprocessorInput(
|
|
preprocessor_id="builtin::basic",
|
|
provider_id="basic",
|
|
),
|
|
PreprocessorInput(
|
|
preprocessor_id="builtin::chunking",
|
|
provider_id="simple_chunking",
|
|
),
|
|
]
|
|
|
|
default_models = get_model_registry(available_models)
|
|
return DistributionTemplate(
|
|
name="nvidia",
|
|
distro_type="remote_hosted",
|
|
description="Use NVIDIA NIM 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],
|
|
},
|
|
default_models=default_models,
|
|
default_tool_groups=default_tool_groups,
|
|
default_preprocessors=default_preprocessors,
|
|
),
|
|
},
|
|
run_config_env_vars={
|
|
"LLAMASTACK_PORT": (
|
|
"5001",
|
|
"Port for the Llama Stack distribution server",
|
|
),
|
|
"NVIDIA_API_KEY": (
|
|
"",
|
|
"NVIDIA API Key",
|
|
),
|
|
},
|
|
)
|