mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
feat: add api.llama provider, llama-guard-4 model (#2058)
This PR adds a llama-stack inference provider for `api.llama.com`, as well as adds entries for Llama-Guard-4 and updated Prompt-Guard models.
This commit is contained in:
Ashwin Bharambe
GitHub
parent
934446ddb4
commit
4d0bfbf984
21 changed files with 1526 additions and 47 deletions
|
|
@ -344,6 +344,45 @@
|
|||
"sentence-transformers --no-deps",
|
||||
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
|
||||
],
|
||||
"llama_api": [
|
||||
"aiosqlite",
|
||||
"autoevals",
|
||||
"blobfile",
|
||||
"chardet",
|
||||
"chromadb-client",
|
||||
"datasets",
|
||||
"emoji",
|
||||
"fastapi",
|
||||
"fire",
|
||||
"httpx",
|
||||
"langdetect",
|
||||
"litellm",
|
||||
"matplotlib",
|
||||
"mcp",
|
||||
"nltk",
|
||||
"numpy",
|
||||
"openai",
|
||||
"opentelemetry-exporter-otlp-proto-http",
|
||||
"opentelemetry-sdk",
|
||||
"pandas",
|
||||
"pillow",
|
||||
"psycopg2-binary",
|
||||
"pymongo",
|
||||
"pypdf",
|
||||
"pythainlp",
|
||||
"redis",
|
||||
"requests",
|
||||
"scikit-learn",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"sqlite-vec",
|
||||
"tqdm",
|
||||
"transformers",
|
||||
"tree_sitter",
|
||||
"uvicorn",
|
||||
"sentence-transformers --no-deps",
|
||||
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
|
||||
],
|
||||
"meta-reference-gpu": [
|
||||
"accelerate",
|
||||
"aiosqlite",
|
||||
|
|
|
|||
7
llama_stack/templates/llama_api/__init__.py
Normal file
7
llama_stack/templates/llama_api/__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 .llama_api import get_distribution_template # noqa: F401
|
||||
33
llama_stack/templates/llama_api/build.yaml
Normal file
33
llama_stack/templates/llama_api/build.yaml
Normal file
|
|
@ -0,0 +1,33 @@
|
|||
version: '2'
|
||||
distribution_spec:
|
||||
description: Distribution for running e2e tests in CI
|
||||
providers:
|
||||
inference:
|
||||
- remote::llama-openai-compat
|
||||
- inline::sentence-transformers
|
||||
vector_io:
|
||||
- inline::sqlite-vec
|
||||
- remote::chromadb
|
||||
- remote::pgvector
|
||||
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
|
||||
image_type: conda
|
||||
159
llama_stack/templates/llama_api/llama_api.py
Normal file
159
llama_stack/templates/llama_api/llama_api.py
Normal file
|
|
@ -0,0 +1,159 @@
|
|||
# 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 List, Tuple
|
||||
|
||||
from llama_stack.apis.models.models import ModelType
|
||||
from llama_stack.distribution.datatypes import (
|
||||
ModelInput,
|
||||
Provider,
|
||||
ShieldInput,
|
||||
ToolGroupInput,
|
||||
)
|
||||
from llama_stack.providers.inline.inference.sentence_transformers import (
|
||||
SentenceTransformersInferenceConfig,
|
||||
)
|
||||
from llama_stack.providers.inline.vector_io.sqlite_vec.config import (
|
||||
SQLiteVectorIOConfig,
|
||||
)
|
||||
from llama_stack.providers.remote.inference.llama_openai_compat.config import (
|
||||
LlamaCompatConfig,
|
||||
)
|
||||
from llama_stack.providers.remote.inference.llama_openai_compat.models import (
|
||||
MODEL_ENTRIES as LLLAMA_MODEL_ENTRIES,
|
||||
)
|
||||
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.templates.template import (
|
||||
DistributionTemplate,
|
||||
RunConfigSettings,
|
||||
get_model_registry,
|
||||
)
|
||||
|
||||
|
||||
def get_inference_providers() -> Tuple[List[Provider], List[ModelInput]]:
|
||||
# in this template, we allow each API key to be optional
|
||||
providers = [
|
||||
(
|
||||
"llama-openai-compat",
|
||||
LLLAMA_MODEL_ENTRIES,
|
||||
LlamaCompatConfig.sample_run_config(api_key="${env.LLAMA_API_KEY:}"),
|
||||
),
|
||||
]
|
||||
inference_providers = []
|
||||
available_models = {}
|
||||
for provider_id, model_entries, config in providers:
|
||||
inference_providers.append(
|
||||
Provider(
|
||||
provider_id=provider_id,
|
||||
provider_type=f"remote::{provider_id}",
|
||||
config=config,
|
||||
)
|
||||
)
|
||||
available_models[provider_id] = model_entries
|
||||
return inference_providers, available_models
|
||||
|
||||
|
||||
def get_distribution_template() -> DistributionTemplate:
|
||||
inference_providers, available_models = get_inference_providers()
|
||||
providers = {
|
||||
"inference": ([p.provider_type for p in inference_providers] + ["inline::sentence-transformers"]),
|
||||
"vector_io": ["inline::sqlite-vec", "remote::chromadb", "remote::pgvector"],
|
||||
"safety": ["inline::llama-guard"],
|
||||
"agents": ["inline::meta-reference"],
|
||||
"telemetry": ["inline::meta-reference"],
|
||||
"eval": ["inline::meta-reference"],
|
||||
"datasetio": ["remote::huggingface", "inline::localfs"],
|
||||
"scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
|
||||
"tool_runtime": [
|
||||
"remote::brave-search",
|
||||
"remote::tavily-search",
|
||||
"inline::code-interpreter",
|
||||
"inline::rag-runtime",
|
||||
"remote::model-context-protocol",
|
||||
],
|
||||
}
|
||||
name = "llama_api"
|
||||
|
||||
vector_io_providers = [
|
||||
Provider(
|
||||
provider_id="sqlite-vec",
|
||||
provider_type="inline::sqlite-vec",
|
||||
config=SQLiteVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
|
||||
),
|
||||
Provider(
|
||||
provider_id="${env.ENABLE_CHROMADB+chromadb}",
|
||||
provider_type="remote::chromadb",
|
||||
config=ChromaVectorIOConfig.sample_run_config(url="${env.CHROMADB_URL:}"),
|
||||
),
|
||||
Provider(
|
||||
provider_id="${env.ENABLE_PGVECTOR+pgvector}",
|
||||
provider_type="remote::pgvector",
|
||||
config=PGVectorVectorIOConfig.sample_run_config(
|
||||
db="${env.PGVECTOR_DB:}",
|
||||
user="${env.PGVECTOR_USER:}",
|
||||
password="${env.PGVECTOR_PASSWORD:}",
|
||||
),
|
||||
),
|
||||
]
|
||||
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",
|
||||
),
|
||||
ToolGroupInput(
|
||||
toolgroup_id="builtin::code_interpreter",
|
||||
provider_id="code-interpreter",
|
||||
),
|
||||
]
|
||||
embedding_model = ModelInput(
|
||||
model_id="all-MiniLM-L6-v2",
|
||||
provider_id=embedding_provider.provider_id,
|
||||
model_type=ModelType.embedding,
|
||||
metadata={
|
||||
"embedding_dimension": 384,
|
||||
},
|
||||
)
|
||||
|
||||
default_models = get_model_registry(available_models)
|
||||
return DistributionTemplate(
|
||||
name=name,
|
||||
distro_type="self_hosted",
|
||||
description="Distribution for running e2e tests in CI",
|
||||
container_image=None,
|
||||
template_path=None,
|
||||
providers=providers,
|
||||
available_models_by_provider=available_models,
|
||||
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")],
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"LLAMA_STACK_PORT": (
|
||||
"8321",
|
||||
"Port for the Llama Stack distribution server",
|
||||
),
|
||||
},
|
||||
)
|
||||
167
llama_stack/templates/llama_api/run.yaml
Normal file
167
llama_stack/templates/llama_api/run.yaml
Normal file
|
|
@ -0,0 +1,167 @@
|
|||
version: '2'
|
||||
image_name: llama_api
|
||||
apis:
|
||||
- agents
|
||||
- datasetio
|
||||
- eval
|
||||
- inference
|
||||
- safety
|
||||
- scoring
|
||||
- telemetry
|
||||
- tool_runtime
|
||||
- vector_io
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: llama-openai-compat
|
||||
provider_type: remote::llama-openai-compat
|
||||
config:
|
||||
openai_compat_api_base: https://api.llama.com/compat/v1/
|
||||
api_key: ${env.LLAMA_API_KEY:}
|
||||
- provider_id: sentence-transformers
|
||||
provider_type: inline::sentence-transformers
|
||||
config: {}
|
||||
vector_io:
|
||||
- provider_id: sqlite-vec
|
||||
provider_type: inline::sqlite-vec
|
||||
config:
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/llama_api}/sqlite_vec.db
|
||||
- provider_id: ${env.ENABLE_CHROMADB+chromadb}
|
||||
provider_type: remote::chromadb
|
||||
config:
|
||||
url: ${env.CHROMADB_URL:}
|
||||
- provider_id: ${env.ENABLE_PGVECTOR+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:}
|
||||
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
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/llama_api}/agents_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/llama_api/trace_store.db}
|
||||
eval:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/llama_api}/meta_reference_eval.db
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/llama_api}/huggingface_datasetio.db
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/llama_api}/localfs_datasetio.db
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
config: {}
|
||||
- provider_id: llm-as-judge
|
||||
provider_type: inline::llm-as-judge
|
||||
config: {}
|
||||
- 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: code-interpreter
|
||||
provider_type: inline::code-interpreter
|
||||
config: {}
|
||||
- provider_id: rag-runtime
|
||||
provider_type: inline::rag-runtime
|
||||
config: {}
|
||||
- provider_id: model-context-protocol
|
||||
provider_type: remote::model-context-protocol
|
||||
config: {}
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/llama_api}/registry.db
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: Llama-3.3-70B-Instruct
|
||||
provider_id: llama-openai-compat
|
||||
provider_model_id: Llama-3.3-70B-Instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.3-70B-Instruct
|
||||
provider_id: llama-openai-compat
|
||||
provider_model_id: Llama-3.3-70B-Instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: Llama-4-Scout-17B-16E-Instruct-FP8
|
||||
provider_id: llama-openai-compat
|
||||
provider_model_id: Llama-4-Scout-17B-16E-Instruct-FP8
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
|
||||
provider_id: llama-openai-compat
|
||||
provider_model_id: Llama-4-Scout-17B-16E-Instruct-FP8
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: Llama-4-Maverick-17B-128E-Instruct-FP8
|
||||
provider_id: llama-openai-compat
|
||||
provider_model_id: Llama-4-Maverick-17B-128E-Instruct-FP8
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
|
||||
provider_id: llama-openai-compat
|
||||
provider_model_id: Llama-4-Maverick-17B-128E-Instruct-FP8
|
||||
model_type: llm
|
||||
- metadata:
|
||||
embedding_dimension: 384
|
||||
model_id: all-MiniLM-L6-v2
|
||||
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
|
||||
- toolgroup_id: builtin::code_interpreter
|
||||
provider_id: code-interpreter
|
||||
server:
|
||||
port: 8321
|
||||
Loading…
Add table
Add a link
Reference in a new issue