mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-06 18:40:57 +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/starter/__init__.py
Normal file
7
src/llama_stack/distributions/starter/__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 .starter import get_distribution_template # noqa: F401
|
||||
60
src/llama_stack/distributions/starter/build.yaml
Normal file
60
src/llama_stack/distributions/starter/build.yaml
Normal file
|
|
@ -0,0 +1,60 @@
|
|||
version: 2
|
||||
distribution_spec:
|
||||
description: Quick start template for running Llama Stack with several popular providers.
|
||||
This distribution is intended for CPU-only environments.
|
||||
providers:
|
||||
inference:
|
||||
- provider_type: remote::cerebras
|
||||
- provider_type: remote::ollama
|
||||
- provider_type: remote::vllm
|
||||
- provider_type: remote::tgi
|
||||
- provider_type: remote::fireworks
|
||||
- provider_type: remote::together
|
||||
- provider_type: remote::bedrock
|
||||
- provider_type: remote::nvidia
|
||||
- provider_type: remote::openai
|
||||
- provider_type: remote::anthropic
|
||||
- provider_type: remote::gemini
|
||||
- provider_type: remote::vertexai
|
||||
- provider_type: remote::groq
|
||||
- provider_type: remote::sambanova
|
||||
- provider_type: remote::azure
|
||||
- provider_type: inline::sentence-transformers
|
||||
vector_io:
|
||||
- provider_type: inline::faiss
|
||||
- provider_type: inline::sqlite-vec
|
||||
- provider_type: inline::milvus
|
||||
- provider_type: remote::chromadb
|
||||
- provider_type: remote::pgvector
|
||||
- provider_type: remote::qdrant
|
||||
- provider_type: remote::weaviate
|
||||
files:
|
||||
- provider_type: inline::localfs
|
||||
safety:
|
||||
- provider_type: inline::llama-guard
|
||||
- provider_type: inline::code-scanner
|
||||
agents:
|
||||
- provider_type: inline::meta-reference
|
||||
post_training:
|
||||
- provider_type: inline::torchtune-cpu
|
||||
eval:
|
||||
- provider_type: inline::meta-reference
|
||||
datasetio:
|
||||
- provider_type: remote::huggingface
|
||||
- provider_type: inline::localfs
|
||||
scoring:
|
||||
- provider_type: inline::basic
|
||||
- provider_type: inline::llm-as-judge
|
||||
- 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
|
||||
batches:
|
||||
- provider_type: inline::reference
|
||||
image_type: venv
|
||||
additional_pip_packages:
|
||||
- aiosqlite
|
||||
- asyncpg
|
||||
- sqlalchemy[asyncio]
|
||||
281
src/llama_stack/distributions/starter/run.yaml
Normal file
281
src/llama_stack/distributions/starter/run.yaml
Normal file
|
|
@ -0,0 +1,281 @@
|
|||
version: 2
|
||||
image_name: starter
|
||||
apis:
|
||||
- agents
|
||||
- batches
|
||||
- datasetio
|
||||
- eval
|
||||
- files
|
||||
- inference
|
||||
- post_training
|
||||
- safety
|
||||
- scoring
|
||||
- tool_runtime
|
||||
- vector_io
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
|
||||
provider_type: remote::cerebras
|
||||
config:
|
||||
base_url: https://api.cerebras.ai
|
||||
api_key: ${env.CEREBRAS_API_KEY:=}
|
||||
- provider_id: ${env.OLLAMA_URL:+ollama}
|
||||
provider_type: remote::ollama
|
||||
config:
|
||||
url: ${env.OLLAMA_URL:=http://localhost:11434}
|
||||
- provider_id: ${env.VLLM_URL:+vllm}
|
||||
provider_type: remote::vllm
|
||||
config:
|
||||
url: ${env.VLLM_URL:=}
|
||||
max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
|
||||
api_token: ${env.VLLM_API_TOKEN:=fake}
|
||||
tls_verify: ${env.VLLM_TLS_VERIFY:=true}
|
||||
- provider_id: ${env.TGI_URL:+tgi}
|
||||
provider_type: remote::tgi
|
||||
config:
|
||||
url: ${env.TGI_URL:=}
|
||||
- provider_id: fireworks
|
||||
provider_type: remote::fireworks
|
||||
config:
|
||||
url: https://api.fireworks.ai/inference/v1
|
||||
api_key: ${env.FIREWORKS_API_KEY:=}
|
||||
- provider_id: together
|
||||
provider_type: remote::together
|
||||
config:
|
||||
url: https://api.together.xyz/v1
|
||||
api_key: ${env.TOGETHER_API_KEY:=}
|
||||
- provider_id: bedrock
|
||||
provider_type: remote::bedrock
|
||||
- provider_id: ${env.NVIDIA_API_KEY:+nvidia}
|
||||
provider_type: remote::nvidia
|
||||
config:
|
||||
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
|
||||
api_key: ${env.NVIDIA_API_KEY:=}
|
||||
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
|
||||
- provider_id: openai
|
||||
provider_type: remote::openai
|
||||
config:
|
||||
api_key: ${env.OPENAI_API_KEY:=}
|
||||
base_url: ${env.OPENAI_BASE_URL:=https://api.openai.com/v1}
|
||||
- provider_id: anthropic
|
||||
provider_type: remote::anthropic
|
||||
config:
|
||||
api_key: ${env.ANTHROPIC_API_KEY:=}
|
||||
- provider_id: gemini
|
||||
provider_type: remote::gemini
|
||||
config:
|
||||
api_key: ${env.GEMINI_API_KEY:=}
|
||||
- provider_id: ${env.VERTEX_AI_PROJECT:+vertexai}
|
||||
provider_type: remote::vertexai
|
||||
config:
|
||||
project: ${env.VERTEX_AI_PROJECT:=}
|
||||
location: ${env.VERTEX_AI_LOCATION:=us-central1}
|
||||
- provider_id: groq
|
||||
provider_type: remote::groq
|
||||
config:
|
||||
url: https://api.groq.com
|
||||
api_key: ${env.GROQ_API_KEY:=}
|
||||
- provider_id: sambanova
|
||||
provider_type: remote::sambanova
|
||||
config:
|
||||
url: https://api.sambanova.ai/v1
|
||||
api_key: ${env.SAMBANOVA_API_KEY:=}
|
||||
- provider_id: ${env.AZURE_API_KEY:+azure}
|
||||
provider_type: remote::azure
|
||||
config:
|
||||
api_key: ${env.AZURE_API_KEY:=}
|
||||
api_base: ${env.AZURE_API_BASE:=}
|
||||
api_version: ${env.AZURE_API_VERSION:=}
|
||||
api_type: ${env.AZURE_API_TYPE:=}
|
||||
- provider_id: sentence-transformers
|
||||
provider_type: inline::sentence-transformers
|
||||
vector_io:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
persistence:
|
||||
namespace: vector_io::faiss
|
||||
backend: kv_default
|
||||
- provider_id: sqlite-vec
|
||||
provider_type: inline::sqlite-vec
|
||||
config:
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sqlite_vec.db
|
||||
persistence:
|
||||
namespace: vector_io::sqlite_vec
|
||||
backend: kv_default
|
||||
- provider_id: ${env.MILVUS_URL:+milvus}
|
||||
provider_type: inline::milvus
|
||||
config:
|
||||
db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/starter}/milvus.db
|
||||
persistence:
|
||||
namespace: vector_io::milvus
|
||||
backend: kv_default
|
||||
- provider_id: ${env.CHROMADB_URL:+chromadb}
|
||||
provider_type: remote::chromadb
|
||||
config:
|
||||
url: ${env.CHROMADB_URL:=}
|
||||
persistence:
|
||||
namespace: vector_io::chroma_remote
|
||||
backend: kv_default
|
||||
- provider_id: ${env.PGVECTOR_DB:+pgvector}
|
||||
provider_type: remote::pgvector
|
||||
config:
|
||||
host: ${env.PGVECTOR_HOST:=localhost}
|
||||
port: ${env.PGVECTOR_PORT:=5432}
|
||||
db: ${env.PGVECTOR_DB:=}
|
||||
user: ${env.PGVECTOR_USER:=}
|
||||
password: ${env.PGVECTOR_PASSWORD:=}
|
||||
persistence:
|
||||
namespace: vector_io::pgvector
|
||||
backend: kv_default
|
||||
- provider_id: ${env.QDRANT_URL:+qdrant}
|
||||
provider_type: remote::qdrant
|
||||
config:
|
||||
api_key: ${env.QDRANT_API_KEY:=}
|
||||
persistence:
|
||||
namespace: vector_io::qdrant_remote
|
||||
backend: kv_default
|
||||
- provider_id: ${env.WEAVIATE_CLUSTER_URL:+weaviate}
|
||||
provider_type: remote::weaviate
|
||||
config:
|
||||
weaviate_api_key: null
|
||||
weaviate_cluster_url: ${env.WEAVIATE_CLUSTER_URL:=localhost:8080}
|
||||
persistence:
|
||||
namespace: vector_io::weaviate
|
||||
backend: kv_default
|
||||
files:
|
||||
- provider_id: meta-reference-files
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}
|
||||
metadata_store:
|
||||
table_name: files_metadata
|
||||
backend: sql_default
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
config:
|
||||
excluded_categories: []
|
||||
- provider_id: code-scanner
|
||||
provider_type: inline::code-scanner
|
||||
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
|
||||
post_training:
|
||||
- provider_id: torchtune-cpu
|
||||
provider_type: inline::torchtune-cpu
|
||||
config:
|
||||
checkpoint_format: meta
|
||||
eval:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
namespace: eval
|
||||
backend: kv_default
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
namespace: datasetio::huggingface
|
||||
backend: kv_default
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
namespace: datasetio::localfs
|
||||
backend: kv_default
|
||||
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
|
||||
batches:
|
||||
- provider_id: reference
|
||||
provider_type: inline::reference
|
||||
config:
|
||||
kvstore:
|
||||
namespace: batches
|
||||
backend: kv_default
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/kvstore.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sql_store.db
|
||||
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: []
|
||||
shields:
|
||||
- shield_id: llama-guard
|
||||
provider_id: ${env.SAFETY_MODEL:+llama-guard}
|
||||
provider_shield_id: ${env.SAFETY_MODEL:=}
|
||||
- shield_id: code-scanner
|
||||
provider_id: ${env.CODE_SCANNER_MODEL:+code-scanner}
|
||||
provider_shield_id: ${env.CODE_SCANNER_MODEL:=}
|
||||
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
|
||||
vector_stores:
|
||||
default_provider_id: faiss
|
||||
default_embedding_model:
|
||||
provider_id: sentence-transformers
|
||||
model_id: nomic-ai/nomic-embed-text-v1.5
|
||||
safety:
|
||||
default_shield_id: llama-guard
|
||||
331
src/llama_stack/distributions/starter/starter.py
Normal file
331
src/llama_stack/distributions/starter/starter.py
Normal file
|
|
@ -0,0 +1,331 @@
|
|||
# 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 typing import Any
|
||||
|
||||
from llama_stack.core.datatypes import (
|
||||
BuildProvider,
|
||||
Provider,
|
||||
ProviderSpec,
|
||||
QualifiedModel,
|
||||
SafetyConfig,
|
||||
ShieldInput,
|
||||
ToolGroupInput,
|
||||
VectorStoresConfig,
|
||||
)
|
||||
from llama_stack.core.utils.dynamic import instantiate_class_type
|
||||
from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings
|
||||
from llama_stack.providers.datatypes import RemoteProviderSpec
|
||||
from llama_stack.providers.inline.files.localfs.config import LocalfsFilesImplConfig
|
||||
from llama_stack.providers.inline.inference.sentence_transformers import (
|
||||
SentenceTransformersInferenceConfig,
|
||||
)
|
||||
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
|
||||
from llama_stack.providers.inline.vector_io.milvus.config import MilvusVectorIOConfig
|
||||
from llama_stack.providers.inline.vector_io.sqlite_vec.config import (
|
||||
SQLiteVectorIOConfig,
|
||||
)
|
||||
from llama_stack.providers.registry.inference import available_providers
|
||||
from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig
|
||||
from llama_stack.providers.remote.vector_io.pgvector.config import (
|
||||
PGVectorVectorIOConfig,
|
||||
)
|
||||
from llama_stack.providers.remote.vector_io.qdrant.config import QdrantVectorIOConfig
|
||||
from llama_stack.providers.remote.vector_io.weaviate.config import WeaviateVectorIOConfig
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import PostgresSqlStoreConfig
|
||||
|
||||
|
||||
def _get_config_for_provider(provider_spec: ProviderSpec) -> dict[str, Any]:
|
||||
"""Get configuration for a provider using its adapter's config class."""
|
||||
config_class = instantiate_class_type(provider_spec.config_class)
|
||||
|
||||
if hasattr(config_class, "sample_run_config"):
|
||||
config: dict[str, Any] = config_class.sample_run_config()
|
||||
return config
|
||||
return {}
|
||||
|
||||
|
||||
ENABLED_INFERENCE_PROVIDERS = [
|
||||
"ollama",
|
||||
"vllm",
|
||||
"tgi",
|
||||
"fireworks",
|
||||
"together",
|
||||
"gemini",
|
||||
"vertexai",
|
||||
"groq",
|
||||
"sambanova",
|
||||
"anthropic",
|
||||
"openai",
|
||||
"cerebras",
|
||||
"nvidia",
|
||||
"bedrock",
|
||||
"azure",
|
||||
]
|
||||
|
||||
INFERENCE_PROVIDER_IDS = {
|
||||
"ollama": "${env.OLLAMA_URL:+ollama}",
|
||||
"vllm": "${env.VLLM_URL:+vllm}",
|
||||
"tgi": "${env.TGI_URL:+tgi}",
|
||||
"cerebras": "${env.CEREBRAS_API_KEY:+cerebras}",
|
||||
"nvidia": "${env.NVIDIA_API_KEY:+nvidia}",
|
||||
"vertexai": "${env.VERTEX_AI_PROJECT:+vertexai}",
|
||||
"azure": "${env.AZURE_API_KEY:+azure}",
|
||||
}
|
||||
|
||||
|
||||
def get_remote_inference_providers() -> list[Provider]:
|
||||
# Filter out inline providers and some others - the starter distro only exposes remote providers
|
||||
remote_providers = [
|
||||
provider
|
||||
for provider in available_providers()
|
||||
if isinstance(provider, RemoteProviderSpec) and provider.adapter_type in ENABLED_INFERENCE_PROVIDERS
|
||||
]
|
||||
|
||||
inference_providers = []
|
||||
for provider_spec in remote_providers:
|
||||
provider_type = provider_spec.adapter_type
|
||||
|
||||
if provider_type in INFERENCE_PROVIDER_IDS:
|
||||
provider_id = INFERENCE_PROVIDER_IDS[provider_type]
|
||||
else:
|
||||
provider_id = provider_type.replace("-", "_").replace("::", "_")
|
||||
config = _get_config_for_provider(provider_spec)
|
||||
|
||||
inference_providers.append(
|
||||
Provider(
|
||||
provider_id=provider_id,
|
||||
provider_type=f"remote::{provider_type}",
|
||||
config=config,
|
||||
)
|
||||
)
|
||||
return inference_providers
|
||||
|
||||
|
||||
def get_distribution_template(name: str = "starter") -> DistributionTemplate:
|
||||
remote_inference_providers = get_remote_inference_providers()
|
||||
|
||||
providers = {
|
||||
"inference": [BuildProvider(provider_type=p.provider_type, module=p.module) for p in remote_inference_providers]
|
||||
+ [BuildProvider(provider_type="inline::sentence-transformers")],
|
||||
"vector_io": [
|
||||
BuildProvider(provider_type="inline::faiss"),
|
||||
BuildProvider(provider_type="inline::sqlite-vec"),
|
||||
BuildProvider(provider_type="inline::milvus"),
|
||||
BuildProvider(provider_type="remote::chromadb"),
|
||||
BuildProvider(provider_type="remote::pgvector"),
|
||||
BuildProvider(provider_type="remote::qdrant"),
|
||||
BuildProvider(provider_type="remote::weaviate"),
|
||||
],
|
||||
"files": [BuildProvider(provider_type="inline::localfs")],
|
||||
"safety": [
|
||||
BuildProvider(provider_type="inline::llama-guard"),
|
||||
BuildProvider(provider_type="inline::code-scanner"),
|
||||
],
|
||||
"agents": [BuildProvider(provider_type="inline::meta-reference")],
|
||||
"post_training": [BuildProvider(provider_type="inline::torchtune-cpu")],
|
||||
"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"),
|
||||
],
|
||||
"batches": [
|
||||
BuildProvider(provider_type="inline::reference"),
|
||||
],
|
||||
}
|
||||
files_provider = Provider(
|
||||
provider_id="meta-reference-files",
|
||||
provider_type="inline::localfs",
|
||||
config=LocalfsFilesImplConfig.sample_run_config(f"~/.llama/distributions/{name}"),
|
||||
)
|
||||
embedding_provider = Provider(
|
||||
provider_id="sentence-transformers",
|
||||
provider_type="inline::sentence-transformers",
|
||||
config=SentenceTransformersInferenceConfig.sample_run_config(),
|
||||
)
|
||||
default_tool_groups = [
|
||||
ToolGroupInput(
|
||||
toolgroup_id="builtin::websearch",
|
||||
provider_id="tavily-search",
|
||||
),
|
||||
ToolGroupInput(
|
||||
toolgroup_id="builtin::rag",
|
||||
provider_id="rag-runtime",
|
||||
),
|
||||
]
|
||||
default_shields = [
|
||||
# if the
|
||||
ShieldInput(
|
||||
shield_id="llama-guard",
|
||||
provider_id="${env.SAFETY_MODEL:+llama-guard}",
|
||||
provider_shield_id="${env.SAFETY_MODEL:=}",
|
||||
),
|
||||
ShieldInput(
|
||||
shield_id="code-scanner",
|
||||
provider_id="${env.CODE_SCANNER_MODEL:+code-scanner}",
|
||||
provider_shield_id="${env.CODE_SCANNER_MODEL:=}",
|
||||
),
|
||||
]
|
||||
|
||||
return DistributionTemplate(
|
||||
name=name,
|
||||
distro_type="self_hosted",
|
||||
description="Quick start template for running Llama Stack with several popular providers. This distribution is intended for CPU-only environments.",
|
||||
container_image=None,
|
||||
template_path=None,
|
||||
providers=providers,
|
||||
additional_pip_packages=PostgresSqlStoreConfig.pip_packages(),
|
||||
run_configs={
|
||||
"run.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": remote_inference_providers + [embedding_provider],
|
||||
"vector_io": [
|
||||
Provider(
|
||||
provider_id="faiss",
|
||||
provider_type="inline::faiss",
|
||||
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
|
||||
),
|
||||
Provider(
|
||||
provider_id="sqlite-vec",
|
||||
provider_type="inline::sqlite-vec",
|
||||
config=SQLiteVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
|
||||
),
|
||||
Provider(
|
||||
provider_id="${env.MILVUS_URL:+milvus}",
|
||||
provider_type="inline::milvus",
|
||||
config=MilvusVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
|
||||
),
|
||||
Provider(
|
||||
provider_id="${env.CHROMADB_URL:+chromadb}",
|
||||
provider_type="remote::chromadb",
|
||||
config=ChromaVectorIOConfig.sample_run_config(
|
||||
f"~/.llama/distributions/{name}/",
|
||||
url="${env.CHROMADB_URL:=}",
|
||||
),
|
||||
),
|
||||
Provider(
|
||||
provider_id="${env.PGVECTOR_DB:+pgvector}",
|
||||
provider_type="remote::pgvector",
|
||||
config=PGVectorVectorIOConfig.sample_run_config(
|
||||
f"~/.llama/distributions/{name}",
|
||||
db="${env.PGVECTOR_DB:=}",
|
||||
user="${env.PGVECTOR_USER:=}",
|
||||
password="${env.PGVECTOR_PASSWORD:=}",
|
||||
),
|
||||
),
|
||||
Provider(
|
||||
provider_id="${env.QDRANT_URL:+qdrant}",
|
||||
provider_type="remote::qdrant",
|
||||
config=QdrantVectorIOConfig.sample_run_config(
|
||||
f"~/.llama/distributions/{name}",
|
||||
url="${env.QDRANT_URL:=}",
|
||||
),
|
||||
),
|
||||
Provider(
|
||||
provider_id="${env.WEAVIATE_CLUSTER_URL:+weaviate}",
|
||||
provider_type="remote::weaviate",
|
||||
config=WeaviateVectorIOConfig.sample_run_config(
|
||||
f"~/.llama/distributions/{name}",
|
||||
cluster_url="${env.WEAVIATE_CLUSTER_URL:=}",
|
||||
),
|
||||
),
|
||||
],
|
||||
"files": [files_provider],
|
||||
},
|
||||
default_models=[],
|
||||
default_tool_groups=default_tool_groups,
|
||||
default_shields=default_shields,
|
||||
vector_stores_config=VectorStoresConfig(
|
||||
default_provider_id="faiss",
|
||||
default_embedding_model=QualifiedModel(
|
||||
provider_id="sentence-transformers",
|
||||
model_id="nomic-ai/nomic-embed-text-v1.5",
|
||||
),
|
||||
),
|
||||
safety_config=SafetyConfig(
|
||||
default_shield_id="llama-guard",
|
||||
),
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"LLAMA_STACK_PORT": (
|
||||
"8321",
|
||||
"Port for the Llama Stack distribution server",
|
||||
),
|
||||
"FIREWORKS_API_KEY": (
|
||||
"",
|
||||
"Fireworks API Key",
|
||||
),
|
||||
"OPENAI_API_KEY": (
|
||||
"",
|
||||
"OpenAI API Key",
|
||||
),
|
||||
"GROQ_API_KEY": (
|
||||
"",
|
||||
"Groq API Key",
|
||||
),
|
||||
"ANTHROPIC_API_KEY": (
|
||||
"",
|
||||
"Anthropic API Key",
|
||||
),
|
||||
"GEMINI_API_KEY": (
|
||||
"",
|
||||
"Gemini API Key",
|
||||
),
|
||||
"VERTEX_AI_PROJECT": (
|
||||
"",
|
||||
"Google Cloud Project ID for Vertex AI",
|
||||
),
|
||||
"VERTEX_AI_LOCATION": (
|
||||
"us-central1",
|
||||
"Google Cloud Location for Vertex AI",
|
||||
),
|
||||
"SAMBANOVA_API_KEY": (
|
||||
"",
|
||||
"SambaNova API Key",
|
||||
),
|
||||
"VLLM_URL": (
|
||||
"http://localhost:8000/v1",
|
||||
"vLLM URL",
|
||||
),
|
||||
"VLLM_INFERENCE_MODEL": (
|
||||
"",
|
||||
"Optional vLLM Inference Model to register on startup",
|
||||
),
|
||||
"OLLAMA_URL": (
|
||||
"http://localhost:11434",
|
||||
"Ollama URL",
|
||||
),
|
||||
"AZURE_API_KEY": (
|
||||
"",
|
||||
"Azure API Key",
|
||||
),
|
||||
"AZURE_API_BASE": (
|
||||
"",
|
||||
"Azure API Base",
|
||||
),
|
||||
"AZURE_API_VERSION": (
|
||||
"",
|
||||
"Azure API Version",
|
||||
),
|
||||
"AZURE_API_TYPE": (
|
||||
"azure",
|
||||
"Azure API Type",
|
||||
),
|
||||
},
|
||||
)
|
||||
Loading…
Add table
Add a link
Reference in a new issue