mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
chore(package): migrate to src/ layout (#3920)
Migrates package structure to src/ layout following Python packaging best practices. All code moved from `llama_stack/` to `src/llama_stack/`. Public API unchanged - imports remain `import llama_stack.*`. Updated build configs, pre-commit hooks, scripts, and GitHub workflows accordingly. All hooks pass, package builds cleanly. **Developer note**: Reinstall after pulling: `pip install -e .`
This commit is contained in:
Ashwin Bharambe
GitHub
parent
98a5047f9d
commit
471b1b248b
791 changed files with 2983 additions and 456 deletions
7
src/llama_stack/distributions/postgres-demo/__init__.py
Normal file
7
src/llama_stack/distributions/postgres-demo/__init__.py
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
# 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 .postgres_demo import get_distribution_template # noqa: F401
|
||||
23
src/llama_stack/distributions/postgres-demo/build.yaml
Normal file
23
src/llama_stack/distributions/postgres-demo/build.yaml
Normal file
|
|
@ -0,0 +1,23 @@
|
|||
version: 2
|
||||
distribution_spec:
|
||||
description: Quick start template for running Llama Stack with several popular providers
|
||||
providers:
|
||||
inference:
|
||||
- provider_type: remote::vllm
|
||||
- provider_type: inline::sentence-transformers
|
||||
vector_io:
|
||||
- provider_type: remote::chromadb
|
||||
safety:
|
||||
- provider_type: inline::llama-guard
|
||||
agents:
|
||||
- provider_type: inline::meta-reference
|
||||
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:
|
||||
- asyncpg
|
||||
- psycopg2-binary
|
||||
- sqlalchemy[asyncio]
|
||||
125
src/llama_stack/distributions/postgres-demo/postgres_demo.py
Normal file
125
src/llama_stack/distributions/postgres-demo/postgres_demo.py
Normal file
|
|
@ -0,0 +1,125 @@
|
|||
# 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,
|
||||
},
|
||||
)
|
||||
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,
|
||||
},
|
||||
default_models=default_models + [embedding_model],
|
||||
default_tool_groups=default_tool_groups,
|
||||
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
|
||||
storage_backends={
|
||||
"kv_default": PostgresKVStoreConfig.sample_run_config(
|
||||
table_name="llamastack_kvstore",
|
||||
),
|
||||
"sql_default": PostgresSqlStoreConfig.sample_run_config(),
|
||||
},
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"LLAMA_STACK_PORT": (
|
||||
"8321",
|
||||
"Port for the Llama Stack distribution server",
|
||||
),
|
||||
},
|
||||
)
|
||||
118
src/llama_stack/distributions/postgres-demo/run.yaml
Normal file
118
src/llama_stack/distributions/postgres-demo/run.yaml
Normal file
|
|
@ -0,0 +1,118 @@
|
|||
version: 2
|
||||
image_name: postgres-demo
|
||||
apis:
|
||||
- agents
|
||||
- inference
|
||||
- safety
|
||||
- tool_runtime
|
||||
- vector_io
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: vllm-inference
|
||||
provider_type: remote::vllm
|
||||
config:
|
||||
url: ${env.VLLM_URL:=http://localhost:8000/v1}
|
||||
max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
|
||||
api_token: ${env.VLLM_API_TOKEN:=fake}
|
||||
tls_verify: ${env.VLLM_TLS_VERIFY:=true}
|
||||
- provider_id: sentence-transformers
|
||||
provider_type: inline::sentence-transformers
|
||||
vector_io:
|
||||
- provider_id: ${env.ENABLE_CHROMADB:+chromadb}
|
||||
provider_type: remote::chromadb
|
||||
config:
|
||||
url: ${env.CHROMADB_URL:=}
|
||||
persistence:
|
||||
namespace: vector_io::chroma_remote
|
||||
backend: kv_default
|
||||
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:
|
||||
agent_state:
|
||||
namespace: agents
|
||||
backend: kv_default
|
||||
responses:
|
||||
table_name: responses
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
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
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_postgres
|
||||
host: ${env.POSTGRES_HOST:=localhost}
|
||||
port: ${env.POSTGRES_PORT:=5432}
|
||||
db: ${env.POSTGRES_DB:=llamastack}
|
||||
user: ${env.POSTGRES_USER:=llamastack}
|
||||
password: ${env.POSTGRES_PASSWORD:=llamastack}
|
||||
table_name: ${env.POSTGRES_TABLE_NAME:=llamastack_kvstore}
|
||||
sql_default:
|
||||
type: sql_postgres
|
||||
host: ${env.POSTGRES_HOST:=localhost}
|
||||
port: ${env.POSTGRES_PORT:=5432}
|
||||
db: ${env.POSTGRES_DB:=llamastack}
|
||||
user: ${env.POSTGRES_USER:=llamastack}
|
||||
password: ${env.POSTGRES_PASSWORD:=llamastack}
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
prompts:
|
||||
namespace: prompts
|
||||
backend: kv_default
|
||||
registered_resources:
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
provider_id: vllm-inference
|
||||
model_type: llm
|
||||
- metadata:
|
||||
embedding_dimension: 768
|
||||
model_id: nomic-embed-text-v1.5
|
||||
provider_id: sentence-transformers
|
||||
model_type: embedding
|
||||
shields:
|
||||
- shield_id: meta-llama/Llama-Guard-3-8B
|
||||
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
|
||||
telemetry:
|
||||
enabled: true
|
||||
Loading…
Add table
Add a link
Reference in a new issue