phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 06:12:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into add-mcp-streamable-http-support

Browse source
This commit is contained in:
Calum Murray 2025-07-02 10:51:42 -04:00 • committed by GitHub
commit e027a526c9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
81 changed files with 811 additions and 689 deletions
Download patch file Download diff file Expand all files Collapse all files

25
llama_stack/distribution/stack.py
View file

@ -166,20 +166,31 @@ def replace_env_vars(config: Any, path: str = "") -> Any:
env_value = os.environ.get(env_var)
if operator == "=": # Default value syntax: ${env.FOO:=default}
if not env_value:
# If the env is set like ${env.FOO:=default} then use the env value when set
if env_value:
value = env_value
else:
# If the env is not set, look for a default value
# value_expr returns empty string (not None) when not matched
# This means ${env.FOO:=} is an error
# This means ${env.FOO:=} and it's accepted and returns empty string - just like bash
if value_expr == "":
raise EnvVarError(env_var, path)
return ""
else:
value = value_expr
else:
value = env_value
elif operator == "+": # Conditional value syntax: ${env.FOO:+value_if_set}
# If the env is set like ${env.FOO:+value_if_set} then use the value_if_set
if env_value:
value = value_expr
if value_expr:
value = value_expr
# This means ${env.FOO:+}
else:
# Just like bash, this doesn't care whether the env is set or not and applies
# the value, in this case the empty string
return ""
else:
# If env var is not set, return empty string for the conditional case
# Just like bash, this doesn't care whether the env is set or not, since it's not set
# we return an empty string
value = ""
else: # No operator case: ${env.FOO}
if not env_value:

2
llama_stack/providers/inline/scoring/braintrust/config.py
View file

@ -17,5 +17,5 @@ class BraintrustScoringConfig(BaseModel):
@classmethod
def sample_run_config(cls, **kwargs) -> dict[str, Any]:
return {
"openai_api_key": "${env.OPENAI_API_KEY:+}",
"openai_api_key": "${env.OPENAI_API_KEY:=}",
}

4
llama_stack/providers/inline/vector_io/milvus/config.py
View file

@ -23,9 +23,9 @@ class MilvusVectorIOConfig(BaseModel):
@classmethod
def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]:
return {
"db_path": f"${{env.MILVUS_DB_PATH:={__distro_dir__}/milvus.db}}",
"db_path": "${env.MILVUS_DB_PATH:=" + __distro_dir__ + "}/" + "milvus.db",
"kvstore": SqliteKVStoreConfig.sample_run_config(
__distro_dir__=__distro_dir__,
db_name=f"${{env.MILVUS_KVSTORE_DB_PATH:={__distro_dir__}/milvus_registry.db}}",
db_name="milvus_registry.db",
),
}

2
llama_stack/providers/registry/vector_io.py
View file

@ -520,7 +520,7 @@ Please refer to the inline provider documentation.
Api.vector_io,
AdapterSpec(
adapter_type="milvus",
pip_packages=["pymilvus"],
pip_packages=["pymilvus[marshmallow<3.13.0]"],
module="llama_stack.providers.remote.vector_io.milvus",
config_class="llama_stack.providers.remote.vector_io.milvus.MilvusVectorIOConfig",
description="""

2
llama_stack/providers/remote/datasetio/nvidia/config.py
View file

@ -54,7 +54,7 @@ class NvidiaDatasetIOConfig(BaseModel):
@classmethod
def sample_run_config(cls, **kwargs) -> dict[str, Any]:
return {
"api_key": "${env.NVIDIA_API_KEY:+}",
"api_key": "${env.NVIDIA_API_KEY:=}",
"dataset_namespace": "${env.NVIDIA_DATASET_NAMESPACE:=default}",
"project_id": "${env.NVIDIA_PROJECT_ID:=test-project}",
"datasets_url": "${env.NVIDIA_DATASETS_URL:=http://nemo.test}",

16
llama_stack/providers/remote/inference/nvidia/config.py
View file

@ -40,7 +40,7 @@ class NVIDIAConfig(BaseModel):
description="A base url for accessing the NVIDIA NIM",
)
api_key: SecretStr | None = Field(
default_factory=lambda: os.getenv("NVIDIA_API_KEY"),
default_factory=lambda: SecretStr(os.getenv("NVIDIA_API_KEY")),
description="The NVIDIA API key, only needed of using the hosted service",
)
timeout: int = Field(
@ -53,9 +53,15 @@ class NVIDIAConfig(BaseModel):
)
@classmethod
def sample_run_config(cls, **kwargs) -> dict[str, Any]:
def sample_run_config(
cls,
url: str = "${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}",
api_key: str = "${env.NVIDIA_API_KEY:=}",
append_api_version: bool = "${env.NVIDIA_APPEND_API_VERSION:=True}",
**kwargs,
) -> dict[str, Any]:
return {
"url": "${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}",
"api_key": "${env.NVIDIA_API_KEY:+}",
"append_api_version": "${env.NVIDIA_APPEND_API_VERSION:=True}",
"url": url,
"api_key": api_key,
"append_api_version": append_api_version,
}

17
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -5,6 +5,7 @@
# the root directory of this source tree.
import base64
import uuid
from collections.abc import AsyncGenerator, AsyncIterator
from typing import Any
@ -77,6 +78,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
content_has_media,
convert_image_content_to_url,
interleaved_content_as_str,
localize_image_content,
request_has_media,
)
@ -496,6 +498,21 @@ class OllamaInferenceAdapter(
user: str | None = None,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
model_obj = await self._get_model(model)
# Ollama does not support image urls, so we need to download the image and convert it to base64
async def _convert_message(m: OpenAIMessageParam) -> OpenAIMessageParam:
if isinstance(m.content, list):
for c in m.content:
if c.type == "image_url" and c.image_url and c.image_url.url:
localize_result = await localize_image_content(c.image_url.url)
if localize_result is None:
raise ValueError(f"Failed to localize image content from {c.image_url.url}")
content, format = localize_result
c.image_url.url = f"data:image/{format};base64,{base64.b64encode(content).decode('utf-8')}"
return m
messages = [await _convert_message(m) for m in messages]
params = await prepare_openai_completion_params(
model=model_obj.provider_resource_id,
messages=messages,

4
llama_stack/providers/remote/inference/runpod/config.py
View file

@ -25,6 +25,6 @@ class RunpodImplConfig(BaseModel):
@classmethod
def sample_run_config(cls, **kwargs: Any) -> dict[str, Any]:
return {
"url": "${env.RUNPOD_URL:+}",
"api_token": "${env.RUNPOD_API_TOKEN:+}",
"url": "${env.RUNPOD_URL:=}",
"api_token": "${env.RUNPOD_API_TOKEN:=}",
}

2
llama_stack/providers/remote/inference/together/config.py
View file

@ -26,5 +26,5 @@ class TogetherImplConfig(BaseModel):
def sample_run_config(cls, **kwargs) -> dict[str, Any]:
return {
"url": "https://api.together.xyz/v1",
"api_key": "${env.TOGETHER_API_KEY:+}",
"api_key": "${env.TOGETHER_API_KEY:=}",
}

4
llama_stack/providers/remote/inference/watsonx/config.py
View file

@ -41,6 +41,6 @@ class WatsonXConfig(BaseModel):
def sample_run_config(cls, **kwargs) -> dict[str, Any]:
return {
"url": "${env.WATSONX_BASE_URL:=https://us-south.ml.cloud.ibm.com}",
"api_key": "${env.WATSONX_API_KEY:+}",
"project_id": "${env.WATSONX_PROJECT_ID:+}",
"api_key": "${env.WATSONX_API_KEY:=}",
"project_id": "${env.WATSONX_PROJECT_ID:=}",
}

2
llama_stack/providers/remote/post_training/nvidia/config.py
View file

@ -55,7 +55,7 @@ class NvidiaPostTrainingConfig(BaseModel):
@classmethod
def sample_run_config(cls, **kwargs) -> dict[str, Any]:
return {
"api_key": "${env.NVIDIA_API_KEY:+}",
"api_key": "${env.NVIDIA_API_KEY:=}",
"dataset_namespace": "${env.NVIDIA_DATASET_NAMESPACE:=default}",
"project_id": "${env.NVIDIA_PROJECT_ID:=test-project}",
"customizer_url": "${env.NVIDIA_CUSTOMIZER_URL:=http://nemo.test}",

2
llama_stack/providers/remote/tool_runtime/brave_search/config.py
View file

@ -22,6 +22,6 @@ class BraveSearchToolConfig(BaseModel):
@classmethod
def sample_run_config(cls, __distro_dir__: str) -> dict[str, Any]:
return {
"api_key": "${env.BRAVE_SEARCH_API_KEY:+}",
"api_key": "${env.BRAVE_SEARCH_API_KEY:=}",
"max_results": 3,
}

2
llama_stack/providers/remote/tool_runtime/tavily_search/config.py
View file

@ -22,6 +22,6 @@ class TavilySearchToolConfig(BaseModel):
@classmethod
def sample_run_config(cls, __distro_dir__: str) -> dict[str, Any]:
return {
"api_key": "${env.TAVILY_SEARCH_API_KEY:+}",
"api_key": "${env.TAVILY_SEARCH_API_KEY:=}",
"max_results": 3,
}

2
llama_stack/providers/remote/tool_runtime/wolfram_alpha/config.py
View file

@ -17,5 +17,5 @@ class WolframAlphaToolConfig(BaseModel):
@classmethod
def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]:
return {
"api_key": "${env.WOLFRAM_ALPHA_API_KEY:+}",
"api_key": "${env.WOLFRAM_ALPHA_API_KEY:=}",
}

26
llama_stack/providers/utils/inference/prompt_adapter.py
View file

@ -180,11 +180,10 @@ def request_has_media(request: ChatCompletionRequest | CompletionRequest):
return content_has_media(request.content)
async def localize_image_content(media: ImageContentItem) -> tuple[bytes, str]:
image = media.image
if image.url and image.url.uri.startswith("http"):
async def localize_image_content(uri: str) -> tuple[bytes, str] | None:
if uri.startswith("http"):
async with httpx.AsyncClient() as client:
r = await client.get(image.url.uri)
r = await client.get(uri)
content = r.content
content_type = r.headers.get("content-type")
if content_type:
@ -194,11 +193,7 @@ async def localize_image_content(media: ImageContentItem) -> tuple[bytes, str]:
return content, format
else:
# data is a base64 encoded string, decode it to bytes first
# TODO(mf): do this more efficiently, decode less
data_bytes = base64.b64decode(image.data)
pil_image = PIL_Image.open(io.BytesIO(data_bytes))
return data_bytes, pil_image.format
return None
async def convert_image_content_to_url(
@ -208,7 +203,18 @@ async def convert_image_content_to_url(
if image.url and (not download or image.url.uri.startswith("data")):
return image.url.uri
content, format = await localize_image_content(media)
if image.data:
# data is a base64 encoded string, decode it to bytes first
# TODO(mf): do this more efficiently, decode less
content = base64.b64decode(image.data)
pil_image = PIL_Image.open(io.BytesIO(content))
format = pil_image.format
else:
localize_result = await localize_image_content(image.url.uri)
if localize_result is None:
raise ValueError(f"Failed to localize image content from {image.url.uri}")
content, format = localize_result
if include_format:
return f"data:image/{format};base64," + base64.b64encode(content).decode("utf-8")
else:

9
llama_stack/providers/utils/vector_io/chunk_utils.py
View file

@ -9,6 +9,11 @@ import uuid
def generate_chunk_id(document_id: str, chunk_text: str) -> str:
"""Generate a unique chunk ID using a hash of document ID and chunk text."""
"""
Generate a unique chunk ID using a hash of the document ID and chunk text.
Note: MD5 is used only to calculate an identifier, not for security purposes.
Adding usedforsecurity=False for compatibility with FIPS environments.
"""
hash_input = f"{document_id}:{chunk_text}".encode()
return str(uuid.UUID(hashlib.md5(hash_input).hexdigest()))
return str(uuid.UUID(hashlib.md5(hash_input, usedforsecurity=False).hexdigest()))

6
llama_stack/templates/bedrock/run.yaml
View file

@ -78,17 +78,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

6
llama_stack/templates/cerebras/run.yaml
View file

@ -77,7 +77,7 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
openai_api_key: ${env.OPENAI_API_KEY:=}
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -89,12 +89,12 @@ providers:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

6
llama_stack/templates/ci-tests/run.yaml
View file

@ -81,17 +81,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

6
llama_stack/templates/dell/run-with-safety.yaml
View file

@ -84,17 +84,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

6
llama_stack/templates/dell/run.yaml
View file

@ -80,17 +80,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

8
llama_stack/templates/fireworks/run-with-safety.yaml
View file

@ -90,7 +90,7 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
openai_api_key: ${env.OPENAI_API_KEY:=}
files:
- provider_id: meta-reference-files
provider_type: inline::localfs
@ -103,17 +103,17 @@ providers:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:+}
api_key: ${env.WOLFRAM_ALPHA_API_KEY:=}
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}

8
llama_stack/templates/fireworks/run.yaml
View file

@ -85,7 +85,7 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
openai_api_key: ${env.OPENAI_API_KEY:=}
files:
- provider_id: meta-reference-files
provider_type: inline::localfs
@ -98,17 +98,17 @@ providers:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:+}
api_key: ${env.WOLFRAM_ALPHA_API_KEY:=}
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}

6
llama_stack/templates/groq/run.yaml
View file

@ -84,17 +84,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

6
llama_stack/templates/hf-endpoint/run-with-safety.yaml
View file

@ -89,17 +89,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

6
llama_stack/templates/hf-endpoint/run.yaml
View file

@ -84,17 +84,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

6
llama_stack/templates/hf-serverless/run-with-safety.yaml
View file

@ -89,17 +89,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

6
llama_stack/templates/hf-serverless/run.yaml
View file

@ -84,17 +84,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

10
llama_stack/templates/llama_api/llama_api.py
View file

@ -41,7 +41,7 @@ def get_inference_providers() -> tuple[list[Provider], list[ModelInput]]:
(
"llama-openai-compat",
LLLAMA_MODEL_ENTRIES,
LlamaCompatConfig.sample_run_config(api_key="${env.LLAMA_API_KEY:+}"),
LlamaCompatConfig.sample_run_config(api_key="${env.LLAMA_API_KEY:=}"),
),
]
inference_providers = []
@ -87,15 +87,15 @@ def get_distribution_template() -> DistributionTemplate:
Provider(
provider_id="${env.ENABLE_CHROMADB:+chromadb}",
provider_type="remote::chromadb",
config=ChromaVectorIOConfig.sample_run_config(url="${env.CHROMADB_URL:+}"),
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="${env.PGVECTOR_PASSWORD:+}",
db="${env.PGVECTOR_DB:=}",
user="${env.PGVECTOR_USER:=}",
password="${env.PGVECTOR_PASSWORD:=}",
),
),
]

16
llama_stack/templates/llama_api/run.yaml
View file

@ -16,7 +16,7 @@ providers:
provider_type: remote::llama-openai-compat
config:
openai_compat_api_base: https://api.llama.com/compat/v1/
api_key: ${env.LLAMA_API_KEY:+}
api_key: ${env.LLAMA_API_KEY:=}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
@ -28,15 +28,15 @@ providers:
- provider_id: ${env.ENABLE_CHROMADB:+chromadb}
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:+}
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:+}
db: ${env.PGVECTOR_DB:=}
user: ${env.PGVECTOR_USER:=}
password: ${env.PGVECTOR_PASSWORD:=}
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
@ -93,17 +93,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

6
llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
View file

@ -99,17 +99,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

6
llama_stack/templates/meta-reference-gpu/run.yaml
View file

@ -89,17 +89,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

6
llama_stack/templates/nvidia/run-with-safety.yaml
View file

@ -17,7 +17,7 @@ providers:
provider_type: remote::nvidia
config:
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
api_key: ${env.NVIDIA_API_KEY:+}
api_key: ${env.NVIDIA_API_KEY:=}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
- provider_id: nvidia
provider_type: remote::nvidia
@ -65,7 +65,7 @@ providers:
- provider_id: nvidia
provider_type: remote::nvidia
config:
api_key: ${env.NVIDIA_API_KEY:+}
api_key: ${env.NVIDIA_API_KEY:=}
dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:=http://nemo.test}
@ -80,7 +80,7 @@ providers:
- provider_id: nvidia
provider_type: remote::nvidia
config:
api_key: ${env.NVIDIA_API_KEY:+}
api_key: ${env.NVIDIA_API_KEY:=}
dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
datasets_url: ${env.NVIDIA_DATASETS_URL:=http://nemo.test}

6
llama_stack/templates/nvidia/run.yaml
View file

@ -17,7 +17,7 @@ providers:
provider_type: remote::nvidia
config:
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
api_key: ${env.NVIDIA_API_KEY:+}
api_key: ${env.NVIDIA_API_KEY:=}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
vector_io:
- provider_id: faiss
@ -60,7 +60,7 @@ providers:
- provider_id: nvidia
provider_type: remote::nvidia
config:
api_key: ${env.NVIDIA_API_KEY:+}
api_key: ${env.NVIDIA_API_KEY:=}
dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:=http://nemo.test}
@ -68,7 +68,7 @@ providers:
- provider_id: nvidia
provider_type: remote::nvidia
config:
api_key: ${env.NVIDIA_API_KEY:+}
api_key: ${env.NVIDIA_API_KEY:=}
dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
datasets_url: ${env.NVIDIA_DATASETS_URL:=http://nemo.test}

8
llama_stack/templates/ollama/run-with-safety.yaml
View file

@ -85,7 +85,7 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
openai_api_key: ${env.OPENAI_API_KEY:=}
files:
- provider_id: meta-reference-files
provider_type: inline::localfs
@ -105,12 +105,12 @@ providers:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime
@ -121,7 +121,7 @@ providers:
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:+}
api_key: ${env.WOLFRAM_ALPHA_API_KEY:=}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/registry.db

8
llama_stack/templates/ollama/run.yaml
View file

@ -83,7 +83,7 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
openai_api_key: ${env.OPENAI_API_KEY:=}
files:
- provider_id: meta-reference-files
provider_type: inline::localfs
@ -103,12 +103,12 @@ providers:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime
@ -119,7 +119,7 @@ providers:
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:+}
api_key: ${env.WOLFRAM_ALPHA_API_KEY:=}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/registry.db

18
llama_stack/templates/open-benchmark/open_benchmark.py
View file

@ -46,7 +46,7 @@ def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderMo
model_type=ModelType.llm,
)
],
OpenAIConfig.sample_run_config(api_key="${env.OPENAI_API_KEY:+}"),
OpenAIConfig.sample_run_config(api_key="${env.OPENAI_API_KEY:=}"),
),
(
"anthropic",
@ -56,7 +56,7 @@ def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderMo
model_type=ModelType.llm,
)
],
AnthropicConfig.sample_run_config(api_key="${env.ANTHROPIC_API_KEY:+}"),
AnthropicConfig.sample_run_config(api_key="${env.ANTHROPIC_API_KEY:=}"),
),
(
"gemini",
@ -66,17 +66,17 @@ def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderMo
model_type=ModelType.llm,
)
],
GeminiConfig.sample_run_config(api_key="${env.GEMINI_API_KEY:+}"),
GeminiConfig.sample_run_config(api_key="${env.GEMINI_API_KEY:=}"),
),
(
"groq",
[],
GroqConfig.sample_run_config(api_key="${env.GROQ_API_KEY:+}"),
GroqConfig.sample_run_config(api_key="${env.GROQ_API_KEY:=}"),
),
(
"together",
[],
TogetherImplConfig.sample_run_config(api_key="${env.TOGETHER_API_KEY:+}"),
TogetherImplConfig.sample_run_config(api_key="${env.TOGETHER_API_KEY:=}"),
),
]
inference_providers = []
@ -122,15 +122,15 @@ def get_distribution_template() -> DistributionTemplate:
Provider(
provider_id="${env.ENABLE_CHROMADB:+chromadb}",
provider_type="remote::chromadb",
config=ChromaVectorIOConfig.sample_run_config(url="${env.CHROMADB_URL:+}"),
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="${env.PGVECTOR_PASSWORD:+}",
db="${env.PGVECTOR_DB:=}",
user="${env.PGVECTOR_USER:=}",
password="${env.PGVECTOR_PASSWORD:=}",
),
),
]

24
llama_stack/templates/open-benchmark/run.yaml
View file

@ -15,25 +15,25 @@ providers:
- provider_id: openai
provider_type: remote::openai
config:
api_key: ${env.OPENAI_API_KEY:+}
api_key: ${env.OPENAI_API_KEY:=}
- provider_id: anthropic
provider_type: remote::anthropic
config:
api_key: ${env.ANTHROPIC_API_KEY:+}
api_key: ${env.ANTHROPIC_API_KEY:=}
- provider_id: gemini
provider_type: remote::gemini
config:
api_key: ${env.GEMINI_API_KEY:+}
api_key: ${env.GEMINI_API_KEY:=}
- provider_id: groq
provider_type: remote::groq
config:
url: https://api.groq.com
api_key: ${env.GROQ_API_KEY:+}
api_key: ${env.GROQ_API_KEY:=}
- provider_id: together
provider_type: remote::together
config:
url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY:+}
api_key: ${env.TOGETHER_API_KEY:=}
vector_io:
- provider_id: sqlite-vec
provider_type: inline::sqlite-vec
@ -42,15 +42,15 @@ providers:
- provider_id: ${env.ENABLE_CHROMADB:+chromadb}
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:+}
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:+}
db: ${env.PGVECTOR_DB:=}
user: ${env.PGVECTOR_USER:=}
password: ${env.PGVECTOR_PASSWORD:=}
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
@ -107,17 +107,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

8
llama_stack/templates/passthrough/run-with-safety.yaml
View file

@ -89,22 +89,22 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:+}
api_key: ${env.WOLFRAM_ALPHA_API_KEY:=}
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}

8
llama_stack/templates/passthrough/run.yaml
View file

@ -84,22 +84,22 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:+}
api_key: ${env.WOLFRAM_ALPHA_API_KEY:=}
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}

4
llama_stack/templates/postgres-demo/postgres_demo.py
View file

@ -52,7 +52,7 @@ def get_distribution_template() -> DistributionTemplate:
Provider(
provider_id="${env.ENABLE_CHROMADB:+chromadb}",
provider_type="remote::chromadb",
config=ChromaVectorIOConfig.sample_run_config(url="${env.CHROMADB_URL:+}"),
config=ChromaVectorIOConfig.sample_run_config(url="${env.CHROMADB_URL:=}"),
),
]
default_tool_groups = [
@ -114,7 +114,7 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="meta-reference",
provider_type="inline::meta-reference",
config=dict(
service_name="${env.OTEL_SERVICE_NAME:+}",
service_name="${env.OTEL_SERVICE_NAME:=}",
sinks="${env.TELEMETRY_SINKS:=console,otel_trace}",
otel_trace_endpoint="${env.OTEL_TRACE_ENDPOINT:=http://localhost:4318/v1/traces}",
),

8
llama_stack/templates/postgres-demo/run.yaml
View file

@ -23,7 +23,7 @@ providers:
- provider_id: ${env.ENABLE_CHROMADB:+chromadb}
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:+}
url: ${env.CHROMADB_URL:=}
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
@ -51,19 +51,19 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: ${env.OTEL_SERVICE_NAME:+}
service_name: ${env.OTEL_SERVICE_NAME:=}
sinks: ${env.TELEMETRY_SINKS:=console,otel_trace}
otel_trace_endpoint: ${env.OTEL_TRACE_ENDPOINT:=http://localhost:4318/v1/traces}
tool_runtime:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

8
llama_stack/templates/remote-vllm/run-with-safety.yaml
View file

@ -86,7 +86,7 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
openai_api_key: ${env.OPENAI_API_KEY:=}
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -98,12 +98,12 @@ providers:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime
@ -114,7 +114,7 @@ providers:
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:+}
api_key: ${env.WOLFRAM_ALPHA_API_KEY:=}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/remote-vllm}/registry.db

8
llama_stack/templates/remote-vllm/run.yaml
View file

@ -79,7 +79,7 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
openai_api_key: ${env.OPENAI_API_KEY:=}
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -91,12 +91,12 @@ providers:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime
@ -107,7 +107,7 @@ providers:
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:+}
api_key: ${env.WOLFRAM_ALPHA_API_KEY:=}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/remote-vllm}/registry.db

14
llama_stack/templates/sambanova/run.yaml
View file

@ -28,15 +28,15 @@ providers:
- provider_id: ${env.ENABLE_CHROMADB:+chromadb}
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:+}
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:+}
db: ${env.PGVECTOR_DB:=}
user: ${env.PGVECTOR_USER:=}
password: ${env.PGVECTOR_PASSWORD:=}
safety:
- provider_id: sambanova
provider_type: remote::sambanova
@ -65,12 +65,12 @@ providers:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime
@ -81,7 +81,7 @@ providers:
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:+}
api_key: ${env.WOLFRAM_ALPHA_API_KEY:=}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/sambanova}/registry.db

8
llama_stack/templates/sambanova/sambanova.py
View file

@ -75,15 +75,15 @@ def get_distribution_template() -> DistributionTemplate:
Provider(
provider_id="${env.ENABLE_CHROMADB:+chromadb}",
provider_type="remote::chromadb",
config=ChromaVectorIOConfig.sample_run_config(url="${env.CHROMADB_URL:+}"),
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="${env.PGVECTOR_PASSWORD:+}",
db="${env.PGVECTOR_DB:=}",
user="${env.PGVECTOR_USER:=}",
password="${env.PGVECTOR_PASSWORD:=}",
),
),
]

32
llama_stack/templates/starter/run.yaml
View file

@ -16,17 +16,17 @@ providers:
- provider_id: openai
provider_type: remote::openai
config:
api_key: ${env.OPENAI_API_KEY:+}
api_key: ${env.OPENAI_API_KEY:=}
- provider_id: fireworks
provider_type: remote::fireworks
config:
url: https://api.fireworks.ai/inference/v1
api_key: ${env.FIREWORKS_API_KEY:+}
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:+}
api_key: ${env.TOGETHER_API_KEY:=}
- provider_id: ollama
provider_type: remote::ollama
config:
@ -35,21 +35,21 @@ providers:
- provider_id: anthropic
provider_type: remote::anthropic
config:
api_key: ${env.ANTHROPIC_API_KEY:+}
api_key: ${env.ANTHROPIC_API_KEY:=}
- provider_id: gemini
provider_type: remote::gemini
config:
api_key: ${env.GEMINI_API_KEY:+}
api_key: ${env.GEMINI_API_KEY:=}
- provider_id: groq
provider_type: remote::groq
config:
url: https://api.groq.com
api_key: ${env.GROQ_API_KEY:+}
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:+}
api_key: ${env.SAMBANOVA_API_KEY:=}
- provider_id: vllm
provider_type: remote::vllm
config:
@ -75,23 +75,23 @@ providers:
- provider_id: ${env.ENABLE_MILVUS:+milvus}
provider_type: inline::milvus
config:
db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/starter/milvus.db}
db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/starter}/milvus.db
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/${env.MILVUS_KVSTORE_DB_PATH:=~/.llama/distributions/starter/milvus_registry.db}
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/milvus_registry.db
- provider_id: ${env.ENABLE_CHROMADB:+chromadb}
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:+}
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:+}
db: ${env.PGVECTOR_DB:=}
user: ${env.PGVECTOR_USER:=}
password: ${env.PGVECTOR_PASSWORD:=}
files:
- provider_id: meta-reference-files
provider_type: inline::localfs
@ -156,17 +156,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

22
llama_stack/templates/starter/starter.py
View file

@ -72,17 +72,17 @@ def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderMo
(
"openai",
OPENAI_MODEL_ENTRIES,
OpenAIConfig.sample_run_config(api_key="${env.OPENAI_API_KEY:+}"),
OpenAIConfig.sample_run_config(api_key="${env.OPENAI_API_KEY:=}"),
),
(
"fireworks",
FIREWORKS_MODEL_ENTRIES,
FireworksImplConfig.sample_run_config(api_key="${env.FIREWORKS_API_KEY:+}"),
FireworksImplConfig.sample_run_config(api_key="${env.FIREWORKS_API_KEY:=}"),
),
(
"together",
TOGETHER_MODEL_ENTRIES,
TogetherImplConfig.sample_run_config(api_key="${env.TOGETHER_API_KEY:+}"),
TogetherImplConfig.sample_run_config(api_key="${env.TOGETHER_API_KEY:=}"),
),
(
"ollama",
@ -106,22 +106,22 @@ def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderMo
(
"anthropic",
ANTHROPIC_MODEL_ENTRIES,
AnthropicConfig.sample_run_config(api_key="${env.ANTHROPIC_API_KEY:+}"),
AnthropicConfig.sample_run_config(api_key="${env.ANTHROPIC_API_KEY:=}"),
),
(
"gemini",
GEMINI_MODEL_ENTRIES,
GeminiConfig.sample_run_config(api_key="${env.GEMINI_API_KEY:+}"),
GeminiConfig.sample_run_config(api_key="${env.GEMINI_API_KEY:=}"),
),
(
"groq",
GROQ_MODEL_ENTRIES,
GroqConfig.sample_run_config(api_key="${env.GROQ_API_KEY:+}"),
GroqConfig.sample_run_config(api_key="${env.GROQ_API_KEY:=}"),
),
(
"sambanova",
SAMBANOVA_MODEL_ENTRIES,
SambaNovaImplConfig.sample_run_config(api_key="${env.SAMBANOVA_API_KEY:+}"),
SambaNovaImplConfig.sample_run_config(api_key="${env.SAMBANOVA_API_KEY:=}"),
),
(
"vllm",
@ -190,15 +190,15 @@ def get_distribution_template() -> DistributionTemplate:
Provider(
provider_id="${env.ENABLE_CHROMADB:+chromadb}",
provider_type="remote::chromadb",
config=ChromaVectorIOConfig.sample_run_config(url="${env.CHROMADB_URL:+}"),
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="${env.PGVECTOR_PASSWORD:+}",
db="${env.PGVECTOR_DB:=}",
user="${env.PGVECTOR_USER:=}",
password="${env.PGVECTOR_PASSWORD:=}",
),
),
]

6
llama_stack/templates/tgi/run-with-safety.yaml
View file

@ -84,17 +84,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

6
llama_stack/templates/tgi/run.yaml
View file

@ -83,17 +83,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

10
llama_stack/templates/together/run-with-safety.yaml
View file

@ -16,7 +16,7 @@ providers:
provider_type: remote::together
config:
url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY:+}
api_key: ${env.TOGETHER_API_KEY:=}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
@ -89,17 +89,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime
@ -110,7 +110,7 @@ providers:
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:+}
api_key: ${env.WOLFRAM_ALPHA_API_KEY:=}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/together}/registry.db

10
llama_stack/templates/together/run.yaml
View file

@ -16,7 +16,7 @@ providers:
provider_type: remote::together
config:
url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY:+}
api_key: ${env.TOGETHER_API_KEY:=}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
@ -84,17 +84,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime
@ -105,7 +105,7 @@ providers:
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:+}
api_key: ${env.WOLFRAM_ALPHA_API_KEY:=}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/together}/registry.db

6
llama_stack/templates/vllm-gpu/run.yaml
View file

@ -88,17 +88,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime

10
llama_stack/templates/watsonx/run.yaml
View file

@ -16,8 +16,8 @@ providers:
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:+}
api_key: ${env.WATSONX_API_KEY:=}
project_id: ${env.WATSONX_PROJECT_ID:=}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
@ -85,17 +85,17 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:+}
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:+}
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:+}
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime