phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-15 23:29:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into dead_code_removal

Browse source
This commit is contained in:
Omar Abdelwahab 2025-10-06 13:21:36 -07:00 • committed by GitHub
commit 9886520b40
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
927 changed files with 171924 additions and 102933 deletions
Download patch file Download diff file Expand all files Collapse all files

33
llama_stack/apis/agents/agents.py
View file

@ -28,7 +28,7 @@ from llama_stack.apis.inference import (
from llama_stack.apis.safety import SafetyViolation
from llama_stack.apis.tools import ToolDef
from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1ALPHA
from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
from llama_stack.schema_utils import ExtraBodyField, json_schema_type, register_schema, webmethod
from .openai_responses import (
ListOpenAIResponseInputItem,
@ -42,6 +42,20 @@ from .openai_responses import (
)
@json_schema_type
class ResponseShieldSpec(BaseModel):
"""Specification for a shield to apply during response generation.
:param type: The type/identifier of the shield.
"""
type: str
# TODO: more fields to be added for shield configuration
ResponseShield = str | ResponseShieldSpec
class Attachment(BaseModel):
"""An attachment to an agent turn.
@ -783,7 +797,7 @@ class Agents(Protocol):
self,
response_id: str,
) -> OpenAIResponseObject:
"""Retrieve an OpenAI response by its ID.
"""Get a model response.
:param response_id: The ID of the OpenAI response to retrieve.
:returns: An OpenAIResponseObject.
@ -805,13 +819,20 @@ class Agents(Protocol):
tools: list[OpenAIResponseInputTool] | None = None,
include: list[str] | None = None,
max_infer_iters: int | None = 10, # this is an extension to the OpenAI API
shields: Annotated[
list[ResponseShield] | None,
ExtraBodyField(
"List of shields to apply during response generation. Shields provide safety and content moderation."
),
] = None,
) -> OpenAIResponseObject | AsyncIterator[OpenAIResponseObjectStream]:
"""Create a new OpenAI response.
"""Create a model response.
:param input: Input message(s) to create the response.
:param model: The underlying LLM used for completions.
:param previous_response_id: (Optional) if specified, the new response will be a continuation of the previous response. This can be used to easily fork-off new responses from existing responses.
:param include: (Optional) Additional fields to include in the response.
:param shields: (Optional) List of shields to apply during response generation. Can be shield IDs (strings) or shield specifications.
:returns: An OpenAIResponseObject.
"""
...
@ -825,7 +846,7 @@ class Agents(Protocol):
model: str | None = None,
order: Order | None = Order.desc,
) -> ListOpenAIResponseObject:
"""List all OpenAI responses.
"""List all responses.
:param after: The ID of the last response to return.
:param limit: The number of responses to return.
@ -848,7 +869,7 @@ class Agents(Protocol):
limit: int | None = 20,
order: Order | None = Order.desc,
) -> ListOpenAIResponseInputItem:
"""List input items for a given OpenAI response.
"""List input items.
:param response_id: The ID of the response to retrieve input items for.
:param after: An item ID to list items after, used for pagination.
@ -863,7 +884,7 @@ class Agents(Protocol):
@webmethod(route="/openai/v1/responses/{response_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
@webmethod(route="/responses/{response_id}", method="DELETE", level=LLAMA_STACK_API_V1)
async def delete_openai_response(self, response_id: str) -> OpenAIDeleteResponseObject:
"""Delete an OpenAI response by its ID.
"""Delete a response.
:param response_id: The ID of the OpenAI response to delete.
:returns: An OpenAIDeleteResponseObject

4
llama_stack/apis/agents/openai_responses.py
View file

@ -888,6 +888,10 @@ class OpenAIResponseObjectWithInput(OpenAIResponseObject):
input: list[OpenAIResponseInput]
def to_response_object(self) -> OpenAIResponseObject:
"""Convert to OpenAIResponseObject by excluding input field."""
return OpenAIResponseObject(**{k: v for k, v in self.model_dump().items() if k != "input"})
@json_schema_type
class ListOpenAIResponseObject(BaseModel):

31
llama_stack/apis/conversations/__init__.py Normal file
View file

@ -0,0 +1,31 @@
# 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 .conversations import (
Conversation,
ConversationCreateRequest,
ConversationDeletedResource,
ConversationItem,
ConversationItemCreateRequest,
ConversationItemDeletedResource,
ConversationItemList,
Conversations,
ConversationUpdateRequest,
Metadata,
)
__all__ = [
"Conversation",
"ConversationCreateRequest",
"ConversationDeletedResource",
"ConversationItem",
"ConversationItemCreateRequest",
"ConversationItemDeletedResource",
"ConversationItemList",
"Conversations",
"ConversationUpdateRequest",
"Metadata",
]

260
llama_stack/apis/conversations/conversations.py Normal file
View file

@ -0,0 +1,260 @@
# 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 Annotated, Literal, Protocol, runtime_checkable
from openai import NOT_GIVEN
from openai._types import NotGiven
from openai.types.responses.response_includable import ResponseIncludable
from pydantic import BaseModel, Field
from llama_stack.apis.agents.openai_responses import (
OpenAIResponseMessage,
OpenAIResponseOutputMessageFileSearchToolCall,
OpenAIResponseOutputMessageFunctionToolCall,
OpenAIResponseOutputMessageMCPCall,
OpenAIResponseOutputMessageMCPListTools,
OpenAIResponseOutputMessageWebSearchToolCall,
)
from llama_stack.apis.version import LLAMA_STACK_API_V1
from llama_stack.providers.utils.telemetry.trace_protocol import trace_protocol
from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
Metadata = dict[str, str]
@json_schema_type
class Conversation(BaseModel):
"""OpenAI-compatible conversation object."""
id: str = Field(..., description="The unique ID of the conversation.")
object: Literal["conversation"] = Field(
default="conversation", description="The object type, which is always conversation."
)
created_at: int = Field(
..., description="The time at which the conversation was created, measured in seconds since the Unix epoch."
)
metadata: Metadata | None = Field(
default=None,
description="Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.",
)
items: list[dict] | None = Field(
default=None,
description="Initial items to include in the conversation context. You may add up to 20 items at a time.",
)
@json_schema_type
class ConversationMessage(BaseModel):
"""OpenAI-compatible message item for conversations."""
id: str = Field(..., description="unique identifier for this message")
content: list[dict] = Field(..., description="message content")
role: str = Field(..., description="message role")
status: str = Field(..., description="message status")
type: Literal["message"] = "message"
object: Literal["message"] = "message"
ConversationItem = Annotated[
OpenAIResponseMessage
| OpenAIResponseOutputMessageFunctionToolCall
| OpenAIResponseOutputMessageFileSearchToolCall
| OpenAIResponseOutputMessageWebSearchToolCall
| OpenAIResponseOutputMessageMCPCall
| OpenAIResponseOutputMessageMCPListTools,
Field(discriminator="type"),
]
register_schema(ConversationItem, name="ConversationItem")
# Using OpenAI types directly caused issues but some notes for reference:
# Note that ConversationItem is a Annotated Union of the types below:
# from openai.types.responses import *
# from openai.types.responses.response_item import *
# from openai.types.conversations import ConversationItem
# f = [
# ResponseFunctionToolCallItem,
# ResponseFunctionToolCallOutputItem,
# ResponseFileSearchToolCall,
# ResponseFunctionWebSearch,
# ImageGenerationCall,
# ResponseComputerToolCall,
# ResponseComputerToolCallOutputItem,
# ResponseReasoningItem,
# ResponseCodeInterpreterToolCall,
# LocalShellCall,
# LocalShellCallOutput,
# McpListTools,
# McpApprovalRequest,
# McpApprovalResponse,
# McpCall,
# ResponseCustomToolCall,
# ResponseCustomToolCallOutput
# ]
@json_schema_type
class ConversationCreateRequest(BaseModel):
"""Request body for creating a conversation."""
items: list[ConversationItem] | None = Field(
default=[],
description="Initial items to include in the conversation context. You may add up to 20 items at a time.",
max_length=20,
)
metadata: Metadata | None = Field(
default={},
description="Set of 16 key-value pairs that can be attached to an object. Useful for storing additional information",
max_length=16,
)
@json_schema_type
class ConversationUpdateRequest(BaseModel):
"""Request body for updating a conversation."""
metadata: Metadata = Field(
...,
description="Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.",
)
@json_schema_type
class ConversationDeletedResource(BaseModel):
"""Response for deleted conversation."""
id: str = Field(..., description="The deleted conversation identifier")
object: str = Field(default="conversation.deleted", description="Object type")
deleted: bool = Field(default=True, description="Whether the object was deleted")
@json_schema_type
class ConversationItemCreateRequest(BaseModel):
"""Request body for creating conversation items."""
items: list[ConversationItem] = Field(
...,
description="Items to include in the conversation context. You may add up to 20 items at a time.",
max_length=20,
)
@json_schema_type
class ConversationItemList(BaseModel):
"""List of conversation items with pagination."""
object: str = Field(default="list", description="Object type")
data: list[ConversationItem] = Field(..., description="List of conversation items")
first_id: str | None = Field(default=None, description="The ID of the first item in the list")
last_id: str | None = Field(default=None, description="The ID of the last item in the list")
has_more: bool = Field(default=False, description="Whether there are more items available")
@json_schema_type
class ConversationItemDeletedResource(BaseModel):
"""Response for deleted conversation item."""
id: str = Field(..., description="The deleted item identifier")
object: str = Field(default="conversation.item.deleted", description="Object type")
deleted: bool = Field(default=True, description="Whether the object was deleted")
@runtime_checkable
@trace_protocol
class Conversations(Protocol):
"""Protocol for conversation management operations."""
@webmethod(route="/conversations", method="POST", level=LLAMA_STACK_API_V1)
async def create_conversation(
self, items: list[ConversationItem] | None = None, metadata: Metadata | None = None
) -> Conversation:
"""Create a conversation.
:param items: Initial items to include in the conversation context.
:param metadata: Set of key-value pairs that can be attached to an object.
:returns: The created conversation object.
"""
...
@webmethod(route="/conversations/{conversation_id}", method="GET", level=LLAMA_STACK_API_V1)
async def get_conversation(self, conversation_id: str) -> Conversation:
"""Get a conversation with the given ID.
:param conversation_id: The conversation identifier.
:returns: The conversation object.
"""
...
@webmethod(route="/conversations/{conversation_id}", method="POST", level=LLAMA_STACK_API_V1)
async def update_conversation(self, conversation_id: str, metadata: Metadata) -> Conversation:
"""Update a conversation's metadata with the given ID.
:param conversation_id: The conversation identifier.
:param metadata: Set of key-value pairs that can be attached to an object.
:returns: The updated conversation object.
"""
...
@webmethod(route="/conversations/{conversation_id}", method="DELETE", level=LLAMA_STACK_API_V1)
async def openai_delete_conversation(self, conversation_id: str) -> ConversationDeletedResource:
"""Delete a conversation with the given ID.
:param conversation_id: The conversation identifier.
:returns: The deleted conversation resource.
"""
...
@webmethod(route="/conversations/{conversation_id}/items", method="POST", level=LLAMA_STACK_API_V1)
async def add_items(self, conversation_id: str, items: list[ConversationItem]) -> ConversationItemList:
"""Create items in the conversation.
:param conversation_id: The conversation identifier.
:param items: Items to include in the conversation context.
:returns: List of created items.
"""
...
@webmethod(route="/conversations/{conversation_id}/items/{item_id}", method="GET", level=LLAMA_STACK_API_V1)
async def retrieve(self, conversation_id: str, item_id: str) -> ConversationItem:
"""Retrieve a conversation item.
:param conversation_id: The conversation identifier.
:param item_id: The item identifier.
:returns: The conversation item.
"""
...
@webmethod(route="/conversations/{conversation_id}/items", method="GET", level=LLAMA_STACK_API_V1)
async def list(
self,
conversation_id: str,
after: str | NotGiven = NOT_GIVEN,
include: list[ResponseIncludable] | NotGiven = NOT_GIVEN,
limit: int | NotGiven = NOT_GIVEN,
order: Literal["asc", "desc"] | NotGiven = NOT_GIVEN,
) -> ConversationItemList:
"""List items in the conversation.
:param conversation_id: The conversation identifier.
:param after: An item ID to list items after, used in pagination.
:param include: Specify additional output data to include in the response.
:param limit: A limit on the number of objects to be returned (1-100, default 20).
:param order: The order to return items in (asc or desc, default desc).
:returns: List of conversation items.
"""
...
@webmethod(route="/conversations/{conversation_id}/items/{item_id}", method="DELETE", level=LLAMA_STACK_API_V1)
async def openai_delete_conversation_item(
self, conversation_id: str, item_id: str
) -> ConversationItemDeletedResource:
"""Delete a conversation item.
:param conversation_id: The conversation identifier.
:param item_id: The item identifier.
:returns: The deleted item resource.
"""
...

1
llama_stack/apis/datatypes.py
View file

@ -129,6 +129,7 @@ class Api(Enum, metaclass=DynamicApiMeta):
tool_groups = "tool_groups"
files = "files"
prompts = "prompts"
conversations = "conversations"
# built-in API
inspect = "inspect"

20
llama_stack/apis/files/files.py
View file

@ -104,6 +104,11 @@ class OpenAIFileDeleteResponse(BaseModel):
@runtime_checkable
@trace_protocol
class Files(Protocol):
"""Files
This API is used to upload documents that can be used with other Llama Stack APIs.
"""
# OpenAI Files API Endpoints
@webmethod(route="/openai/v1/files", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
@webmethod(route="/files", method="POST", level=LLAMA_STACK_API_V1)
@ -113,7 +118,8 @@ class Files(Protocol):
purpose: Annotated[OpenAIFilePurpose, Form()],
expires_after: Annotated[ExpiresAfter | None, Form()] = None,
) -> OpenAIFileObject:
"""
"""Upload file.
Upload a file that can be used across various endpoints.
The file upload should be a multipart form request with:
@ -137,7 +143,8 @@ class Files(Protocol):
order: Order | None = Order.desc,
purpose: OpenAIFilePurpose | None = None,
) -> ListOpenAIFileResponse:
"""
"""List files.
Returns a list of files that belong to the user's organization.
:param after: A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.
@ -154,7 +161,8 @@ class Files(Protocol):
self,
file_id: str,
) -> OpenAIFileObject:
"""
"""Retrieve file.
Returns information about a specific file.
:param file_id: The ID of the file to use for this request.
@ -168,8 +176,7 @@ class Files(Protocol):
self,
file_id: str,
) -> OpenAIFileDeleteResponse:
"""
Delete a file.
"""Delete file.
:param file_id: The ID of the file to use for this request.
:returns: An OpenAIFileDeleteResponse indicating successful deletion.
@ -182,7 +189,8 @@ class Files(Protocol):
self,
file_id: str,
) -> Response:
"""
"""Retrieve file content.
Returns the contents of the specified file.
:param file_id: The ID of the file to use for this request.

66
llama_stack/apis/inference/inference.py
View file

@ -982,45 +982,6 @@ class InferenceProvider(Protocol):
model_store: ModelStore | None = None
async def chat_completion(
self,
model_id: str,
messages: list[Message],
sampling_params: SamplingParams | None = None,
tools: list[ToolDefinition] | None = None,
tool_choice: ToolChoice | None = ToolChoice.auto,
tool_prompt_format: ToolPromptFormat | None = None,
response_format: ResponseFormat | None = None,
stream: bool | None = False,
logprobs: LogProbConfig | None = None,
tool_config: ToolConfig | None = None,
) -> ChatCompletionResponse | AsyncIterator[ChatCompletionResponseStreamChunk]:
"""Generate a chat completion for the given messages using the specified model.
:param model_id: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint.
:param messages: List of messages in the conversation.
:param sampling_params: Parameters to control the sampling strategy.
:param tools: (Optional) List of tool definitions available to the model.
:param tool_choice: (Optional) Whether tool use is required or automatic. Defaults to ToolChoice.auto.
.. deprecated::
Use tool_config instead.
:param tool_prompt_format: (Optional) Instructs the model how to format tool calls. By default, Llama Stack will attempt to use a format that is best adapted to the model.
- `ToolPromptFormat.json`: The tool calls are formatted as a JSON object.
- `ToolPromptFormat.function_tag`: The tool calls are enclosed in a <function=function_name> tag.
- `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls.
.. deprecated::
Use tool_config instead.
:param response_format: (Optional) Grammar specification for guided (structured) decoding. There are two options:
- `ResponseFormat.json_schema`: The grammar is a JSON schema. Most providers support this format.
- `ResponseFormat.grammar`: The grammar is a BNF grammar. This format is more flexible, but not all providers support it.
:param stream: (Optional) If True, generate an SSE event stream of the response. Defaults to False.
:param logprobs: (Optional) If specified, log probabilities for each token position will be returned.
:param tool_config: (Optional) Configuration for tool use.
:returns: If stream=False, returns a ChatCompletionResponse with the full completion.
If stream=True, returns an SSE event stream of ChatCompletionResponseStreamChunk.
"""
...
@webmethod(route="/inference/rerank", method="POST", level=LLAMA_STACK_API_V1ALPHA)
async def rerank(
self,
@ -1081,7 +1042,9 @@ class InferenceProvider(Protocol):
# for fill-in-the-middle type completion
suffix: str | None = None,
) -> OpenAICompletion:
"""Generate an OpenAI-compatible completion for the given prompt using the specified model.
"""Create completion.
Generate an OpenAI-compatible completion for the given prompt using the specified model.
:param model: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint.
:param prompt: The prompt to generate a completion for.
@ -1138,7 +1101,9 @@ class InferenceProvider(Protocol):
top_p: float | None = None,
user: str | None = None,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
"""Generate an OpenAI-compatible chat completion for the given messages using the specified model.
"""Create chat completions.
Generate an OpenAI-compatible chat completion for the given messages using the specified model.
:param model: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint.
:param messages: List of messages in the conversation.
@ -1182,7 +1147,9 @@ class InferenceProvider(Protocol):
dimensions: int | None = None,
user: str | None = None,
) -> OpenAIEmbeddingsResponse:
"""Generate OpenAI-compatible embeddings for the given input using the specified model.
"""Create embeddings.
Generate OpenAI-compatible embeddings for the given input using the specified model.
:param model: The identifier of the model to use. The model must be an embedding model registered with Llama Stack and available via the /models endpoint.
:param input: Input text to embed, encoded as a string or array of strings. To embed multiple inputs in a single request, pass an array of strings.
@ -1195,7 +1162,9 @@ class InferenceProvider(Protocol):
class Inference(InferenceProvider):
"""Llama Stack Inference API for generating completions, chat completions, and embeddings.
"""Inference
Llama Stack Inference API for generating completions, chat completions, and embeddings.
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate "raw" and "chat" (conversational) completions.
@ -1216,7 +1185,7 @@ class Inference(InferenceProvider):
model: str | None = None,
order: Order | None = Order.desc,
) -> ListOpenAIChatCompletionResponse:
"""List all chat completions.
"""List chat completions.
:param after: The ID of the last chat completion to return.
:param limit: The maximum number of chat completions to return.
@ -1237,10 +1206,11 @@ class Inference(InferenceProvider):
method="GET",
level=LLAMA_STACK_API_V1,
)
async def get_chat_completion(
self, completion_id: str
) -> OpenAICompletionWithInputMessages:
"""Describe a chat completion by its ID.
@webmethod(route="/chat/completions/{completion_id}", method="GET", level=LLAMA_STACK_API_V1)
async def get_chat_completion(self, completion_id: str) -> OpenAICompletionWithInputMessages:
"""Get chat completion.
Describe a chat completion by its ID.
:param completion_id: ID of the chat completion.
:returns: A OpenAICompletionWithInputMessages.

17
llama_stack/apis/inspect/inspect.py
View file

@ -58,9 +58,16 @@ class ListRoutesResponse(BaseModel):
@runtime_checkable
class Inspect(Protocol):
"""Inspect
APIs for inspecting the Llama Stack service, including health status, available API routes with methods and implementing providers.
"""
@webmethod(route="/inspect/routes", method="GET", level=LLAMA_STACK_API_V1)
async def list_routes(self) -> ListRoutesResponse:
"""List all available API routes with their methods and implementing providers.
"""List routes.
List all available API routes with their methods and implementing providers.
:returns: Response containing information about all available routes.
"""
@ -68,7 +75,9 @@ class Inspect(Protocol):
@webmethod(route="/health", method="GET", level=LLAMA_STACK_API_V1)
async def health(self) -> HealthInfo:
"""Get the current health status of the service.
"""Get health status.
Get the current health status of the service.
:returns: Health information indicating if the service is operational.
"""
@ -76,7 +85,9 @@ class Inspect(Protocol):
@webmethod(route="/version", method="GET", level=LLAMA_STACK_API_V1)
async def version(self) -> VersionInfo:
"""Get the version of the service.
"""Get version.
Get the version of the service.
:returns: Version information containing the service version number.
"""

12
llama_stack/apis/models/models.py
View file

@ -124,7 +124,9 @@ class Models(Protocol):
self,
model_id: str,
) -> Model:
"""Get a model by its identifier.
"""Get model.
Get a model by its identifier.
:param model_id: The identifier of the model to get.
:returns: A Model.
@ -140,7 +142,9 @@ class Models(Protocol):
metadata: dict[str, Any] | None = None,
model_type: ModelType | None = None,
) -> Model:
"""Register a model.
"""Register model.
Register a model.
:param model_id: The identifier of the model to register.
:param provider_model_id: The identifier of the model in the provider.
@ -156,7 +160,9 @@ class Models(Protocol):
self,
model_id: str,
) -> None:
"""Unregister a model.
"""Unregister model.
Unregister a model.
:param model_id: The identifier of the model to unregister.
"""

28
llama_stack/apis/prompts/prompts.py
View file

@ -94,7 +94,9 @@ class ListPromptsResponse(BaseModel):
@runtime_checkable
@trace_protocol
class Prompts(Protocol):
"""Protocol for prompt management operations."""
"""Prompts
Protocol for prompt management operations."""
@webmethod(route="/prompts", method="GET", level=LLAMA_STACK_API_V1)
async def list_prompts(self) -> ListPromptsResponse:
@ -109,7 +111,9 @@ class Prompts(Protocol):
self,
prompt_id: str,
) -> ListPromptsResponse:
"""List all versions of a specific prompt.
"""List prompt versions.
List all versions of a specific prompt.
:param prompt_id: The identifier of the prompt to list versions for.
:returns: A ListPromptsResponse containing all versions of the prompt.
@ -122,7 +126,9 @@ class Prompts(Protocol):
prompt_id: str,
version: int | None = None,
) -> Prompt:
"""Get a prompt by its identifier and optional version.
"""Get prompt.
Get a prompt by its identifier and optional version.
:param prompt_id: The identifier of the prompt to get.
:param version: The version of the prompt to get (defaults to latest).
@ -136,7 +142,9 @@ class Prompts(Protocol):
prompt: str,
variables: list[str] | None = None,
) -> Prompt:
"""Create a new prompt.
"""Create prompt.
Create a new prompt.
:param prompt: The prompt text content with variable placeholders.
:param variables: List of variable names that can be used in the prompt template.
@ -153,7 +161,9 @@ class Prompts(Protocol):
variables: list[str] | None = None,
set_as_default: bool = True,
) -> Prompt:
"""Update an existing prompt (increments version).
"""Update prompt.
Update an existing prompt (increments version).
:param prompt_id: The identifier of the prompt to update.
:param prompt: The updated prompt text content.
@ -169,7 +179,9 @@ class Prompts(Protocol):
self,
prompt_id: str,
) -> None:
"""Delete a prompt.
"""Delete prompt.
Delete a prompt.
:param prompt_id: The identifier of the prompt to delete.
"""
@ -181,7 +193,9 @@ class Prompts(Protocol):
prompt_id: str,
version: int,
) -> Prompt:
"""Set which version of a prompt should be the default in get_prompt (latest).
"""Set prompt version.
Set which version of a prompt should be the default in get_prompt (latest).
:param prompt_id: The identifier of the prompt.
:param version: The version to set as default.

11
llama_stack/apis/providers/providers.py
View file

@ -42,13 +42,16 @@ class ListProvidersResponse(BaseModel):
@runtime_checkable
class Providers(Protocol):
"""
"""Providers
Providers API for inspecting, listing, and modifying providers and their configurations.
"""
@webmethod(route="/providers", method="GET", level=LLAMA_STACK_API_V1)
async def list_providers(self) -> ListProvidersResponse:
"""List all available providers.
"""List providers.
List all available providers.
:returns: A ListProvidersResponse containing information about all providers.
"""
@ -56,7 +59,9 @@ class Providers(Protocol):
@webmethod(route="/providers/{provider_id}", method="GET", level=LLAMA_STACK_API_V1)
async def inspect_provider(self, provider_id: str) -> ProviderInfo:
"""Get detailed information about a specific provider.
"""Get provider.
Get detailed information about a specific provider.
:param provider_id: The ID of the provider to inspect.
:returns: A ProviderInfo object containing the provider's details.

13
llama_stack/apis/safety/safety.py
View file

@ -96,6 +96,11 @@ class ShieldStore(Protocol):
@runtime_checkable
@trace_protocol
class Safety(Protocol):
"""Safety
OpenAI-compatible Moderations API.
"""
shield_store: ShieldStore
@webmethod(route="/safety/run-shield", method="POST", level=LLAMA_STACK_API_V1)
@ -105,7 +110,9 @@ class Safety(Protocol):
messages: list[Message],
params: dict[str, Any],
) -> RunShieldResponse:
"""Run a shield.
"""Run shield.
Run a shield.
:param shield_id: The identifier of the shield to run.
:param messages: The messages to run the shield on.
@ -117,7 +124,9 @@ class Safety(Protocol):
@webmethod(route="/openai/v1/moderations", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
@webmethod(route="/moderations", method="POST", level=LLAMA_STACK_API_V1)
async def run_moderation(self, input: str | list[str], model: str) -> ModerationObject:
"""Classifies if text and/or image inputs are potentially harmful.
"""Create moderation.
Classifies if text and/or image inputs are potentially harmful.
:param input: Input (or inputs) to classify.
Can be a single string, an array of strings, or an array of multi-modal input objects similar to other models.
:param model: The content moderation model you would like to use.