mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-19 15:38:52 +00:00
f22aaef42f
# What does this PR do? remove telemetry as a providable API from the codebase. This includes removing it from generated distributions but also the provider registry, the router, etc since `setup_logger` is tied pretty strictly to `Api.telemetry` being in impls we still need an "instantiated provider" in our implementations. However it should not be auto-routed or provided. So in validate_and_prepare_providers (called from resolve_impls) I made it so that if run_config.telemetry.enabled, we set up the meta-reference "provider" internally to be used so that log_event will work when called. This is the neatest way I think we can remove telemetry from the provider configs but also not need to rip apart the whole "telemetry is a provider" logic just yet, but we can do it internally later without disrupting users. so telemetry is removed from the registry such that if a user puts `telemetry:` as an API in their build/run config it will err out, but can still be used by us internally as we go through this transition. relates to #3806 Signed-off-by: Charlie Doern <cdoern@redhat.com>
132 lines
4.7 KiB
Python
132 lines
4.7 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 llama_stack.apis.models import ModelType
|
|
from llama_stack.core.datatypes import (
|
|
BuildProvider,
|
|
ModelInput,
|
|
Provider,
|
|
ShieldInput,
|
|
ToolGroupInput,
|
|
)
|
|
from llama_stack.distributions.template import (
|
|
DistributionTemplate,
|
|
RunConfigSettings,
|
|
)
|
|
from llama_stack.providers.inline.inference.sentence_transformers import SentenceTransformersInferenceConfig
|
|
from llama_stack.providers.remote.inference.vllm import VLLMInferenceAdapterConfig
|
|
from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig
|
|
from llama_stack.providers.utils.kvstore.config import PostgresKVStoreConfig
|
|
from llama_stack.providers.utils.sqlstore.sqlstore import PostgresSqlStoreConfig
|
|
|
|
|
|
def get_distribution_template() -> DistributionTemplate:
|
|
inference_providers = [
|
|
Provider(
|
|
provider_id="vllm-inference",
|
|
provider_type="remote::vllm",
|
|
config=VLLMInferenceAdapterConfig.sample_run_config(
|
|
url="${env.VLLM_URL:=http://localhost:8000/v1}",
|
|
),
|
|
),
|
|
]
|
|
providers = {
|
|
"inference": [
|
|
BuildProvider(provider_type="remote::vllm"),
|
|
BuildProvider(provider_type="inline::sentence-transformers"),
|
|
],
|
|
"vector_io": [BuildProvider(provider_type="remote::chromadb")],
|
|
"safety": [BuildProvider(provider_type="inline::llama-guard")],
|
|
"agents": [BuildProvider(provider_type="inline::meta-reference")],
|
|
"tool_runtime": [
|
|
BuildProvider(provider_type="remote::brave-search"),
|
|
BuildProvider(provider_type="remote::tavily-search"),
|
|
BuildProvider(provider_type="inline::rag-runtime"),
|
|
BuildProvider(provider_type="remote::model-context-protocol"),
|
|
],
|
|
}
|
|
name = "postgres-demo"
|
|
|
|
vector_io_providers = [
|
|
Provider(
|
|
provider_id="${env.ENABLE_CHROMADB:+chromadb}",
|
|
provider_type="remote::chromadb",
|
|
config=ChromaVectorIOConfig.sample_run_config(
|
|
f"~/.llama/distributions/{name}",
|
|
url="${env.CHROMADB_URL:=}",
|
|
),
|
|
),
|
|
]
|
|
default_tool_groups = [
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::websearch",
|
|
provider_id="tavily-search",
|
|
),
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::rag",
|
|
provider_id="rag-runtime",
|
|
),
|
|
]
|
|
|
|
default_models = [
|
|
ModelInput(
|
|
model_id="${env.INFERENCE_MODEL}",
|
|
provider_id="vllm-inference",
|
|
)
|
|
]
|
|
embedding_provider = Provider(
|
|
provider_id="sentence-transformers",
|
|
provider_type="inline::sentence-transformers",
|
|
config=SentenceTransformersInferenceConfig.sample_run_config(),
|
|
)
|
|
embedding_model = ModelInput(
|
|
model_id="nomic-embed-text-v1.5",
|
|
provider_id=embedding_provider.provider_id,
|
|
model_type=ModelType.embedding,
|
|
metadata={
|
|
"embedding_dimension": 768,
|
|
},
|
|
)
|
|
postgres_config = PostgresSqlStoreConfig.sample_run_config()
|
|
return DistributionTemplate(
|
|
name=name,
|
|
distro_type="self_hosted",
|
|
description="Quick start template for running Llama Stack with several popular providers",
|
|
container_image=None,
|
|
template_path=None,
|
|
providers=providers,
|
|
available_models_by_provider={},
|
|
run_configs={
|
|
"run.yaml": RunConfigSettings(
|
|
provider_overrides={
|
|
"inference": inference_providers + [embedding_provider],
|
|
"vector_io": vector_io_providers,
|
|
"agents": [
|
|
Provider(
|
|
provider_id="meta-reference",
|
|
provider_type="inline::meta-reference",
|
|
config=dict(
|
|
persistence_store=postgres_config,
|
|
responses_store=postgres_config,
|
|
),
|
|
)
|
|
],
|
|
},
|
|
default_models=default_models + [embedding_model],
|
|
default_tool_groups=default_tool_groups,
|
|
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
|
|
metadata_store=PostgresKVStoreConfig.sample_run_config(),
|
|
inference_store=postgres_config,
|
|
),
|
|
},
|
|
run_config_env_vars={
|
|
"LLAMA_STACK_PORT": (
|
|
"8321",
|
|
"Port for the Llama Stack distribution server",
|
|
),
|
|
},
|
|
)
|