chore: rename templates to distributions (#3035)

As the title says. Distributions is in, Templates is out.

`llama stack build --template` --> `llama stack build --distro`. For
backward compatibility, the previous option is kept but results in a
warning.

Updated `server.py` to remove the "config_or_template" backward
compatibility since it has been a couple releases since that change.
This commit is contained in:
Ashwin Bharambe 2025-08-04 11:34:17 -07:00 committed by GitHub
parent 12f964437a
commit cc87995e2b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
87 changed files with 263 additions and 330 deletions

View file

@ -0,0 +1,5 @@
# 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.

View file

@ -0,0 +1,46 @@
version: 2
distribution_spec:
description: Use watsonx for running LLM inference
providers:
inference:
- provider_id: watsonx
provider_type: remote::watsonx
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
vector_io:
- provider_id: faiss
provider_type: inline::faiss
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
- provider_id: localfs
provider_type: inline::localfs
scoring:
- provider_id: basic
provider_type: inline::basic
- provider_id: llm-as-judge
provider_type: inline::llm-as-judge
- provider_id: braintrust
provider_type: inline::braintrust
tool_runtime:
- provider_type: remote::brave-search
- provider_type: remote::tavily-search
- provider_type: inline::rag-runtime
- provider_type: remote::model-context-protocol
image_type: venv
additional_pip_packages:
- sqlalchemy[asyncio]
- aiosqlite
- aiosqlite

View file

@ -0,0 +1,210 @@
version: 2
image_name: watsonx
apis:
- agents
- datasetio
- eval
- inference
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: watsonx
provider_type: remote::watsonx
config:
url: ${env.WATSONX_BASE_URL:=https://us-south.ml.cloud.ibm.com}
api_key: ${env.WATSONX_API_KEY:=}
project_id: ${env.WATSONX_PROJECT_ID:=}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
vector_io:
- provider_id: faiss
provider_type: inline::faiss
config:
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/faiss_store.db
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/trace_store.db
otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config:
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config:
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
- provider_id: llm-as-judge
provider_type: inline::llm-as-judge
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:=}
tool_runtime:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:=}
max_results: 3
- provider_id: tavily-search
provider_type: remote::tavily-search
config:
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/inference_store.db
models:
- metadata: {}
model_id: meta-llama/llama-3-3-70b-instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-3-70b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.3-70B-Instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-3-70b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/llama-2-13b-chat
provider_id: watsonx
provider_model_id: meta-llama/llama-2-13b-chat
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-2-13b
provider_id: watsonx
provider_model_id: meta-llama/llama-2-13b-chat
model_type: llm
- metadata: {}
model_id: meta-llama/llama-3-1-70b-instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-1-70b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-70B-Instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-1-70b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/llama-3-1-8b-instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-1-8b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-8B-Instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-1-8b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/llama-3-2-11b-vision-instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-2-11b-vision-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-2-11b-vision-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/llama-3-2-1b-instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-2-1b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-1B-Instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-2-1b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/llama-3-2-3b-instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-2-3b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-3B-Instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-2-3b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/llama-3-2-90b-vision-instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-2-90b-vision-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: watsonx
provider_model_id: meta-llama/llama-3-2-90b-vision-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/llama-guard-3-11b-vision
provider_id: watsonx
provider_model_id: meta-llama/llama-guard-3-11b-vision
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-Guard-3-11B-Vision
provider_id: watsonx
provider_model_id: meta-llama/llama-guard-3-11b-vision
model_type: llm
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_id: sentence-transformers
model_type: embedding
shields: []
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
server:
port: 8321

View file

@ -0,0 +1,114 @@
# 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.core.datatypes import BuildProvider, ModelInput, Provider, ToolGroupInput
from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings, get_model_registry
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
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",
),
},
)