mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-06 04:34:57 +00:00
Merge branch 'main' into remove-deprecated-chat-completion
This commit is contained in:
commit
ee6a502289
209 changed files with 109297 additions and 8828 deletions
|
@ -772,6 +772,12 @@ class Agents(Protocol):
|
|||
#
|
||||
# Both of these APIs are inherently stateful.
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/responses/{response_id}",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(route="/responses/{response_id}", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def get_openai_response(
|
||||
self,
|
||||
|
@ -784,6 +790,7 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/responses", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/responses", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def create_openai_response(
|
||||
self,
|
||||
|
@ -809,6 +816,7 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/responses", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/responses", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def list_openai_responses(
|
||||
self,
|
||||
|
@ -828,10 +836,9 @@ class Agents(Protocol):
|
|||
...
|
||||
|
||||
@webmethod(
|
||||
route="/responses/{response_id}/input_items",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
route="/openai/v1/responses/{response_id}/input_items", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
|
||||
)
|
||||
@webmethod(route="/responses/{response_id}/input_items", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def list_openai_response_input_items(
|
||||
self,
|
||||
response_id: str,
|
||||
|
@ -853,6 +860,7 @@ 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.
|
||||
|
|
|
@ -43,6 +43,7 @@ class Batches(Protocol):
|
|||
Note: This API is currently under active development and may undergo changes.
|
||||
"""
|
||||
|
||||
@webmethod(route="/openai/v1/batches", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/batches", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def create_batch(
|
||||
self,
|
||||
|
@ -63,6 +64,7 @@ class Batches(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/batches/{batch_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/batches/{batch_id}", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def retrieve_batch(self, batch_id: str) -> BatchObject:
|
||||
"""Retrieve information about a specific batch.
|
||||
|
@ -72,6 +74,7 @@ class Batches(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/batches/{batch_id}/cancel", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/batches/{batch_id}/cancel", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def cancel_batch(self, batch_id: str) -> BatchObject:
|
||||
"""Cancel a batch that is in progress.
|
||||
|
@ -81,6 +84,7 @@ class Batches(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/batches", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/batches", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def list_batches(
|
||||
self,
|
||||
|
|
|
@ -105,6 +105,7 @@ class OpenAIFileDeleteResponse(BaseModel):
|
|||
@trace_protocol
|
||||
class Files(Protocol):
|
||||
# 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)
|
||||
async def openai_upload_file(
|
||||
self,
|
||||
|
@ -127,6 +128,7 @@ class Files(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/files", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/files", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_list_files(
|
||||
self,
|
||||
|
@ -146,6 +148,7 @@ class Files(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_retrieve_file(
|
||||
self,
|
||||
|
@ -159,6 +162,7 @@ class Files(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1)
|
||||
async def openai_delete_file(
|
||||
self,
|
||||
|
@ -172,6 +176,7 @@ class Files(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/files/{file_id}/content", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/files/{file_id}/content", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_retrieve_file_content(
|
||||
self,
|
||||
|
|
|
@ -27,14 +27,12 @@ from llama_stack.models.llama.datatypes import (
|
|||
StopReason,
|
||||
ToolCall,
|
||||
ToolDefinition,
|
||||
ToolParamDefinition,
|
||||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.providers.utils.telemetry.trace_protocol import trace_protocol
|
||||
from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
|
||||
|
||||
register_schema(ToolCall)
|
||||
register_schema(ToolParamDefinition)
|
||||
register_schema(ToolDefinition)
|
||||
|
||||
from enum import StrEnum
|
||||
|
@ -1027,6 +1025,7 @@ class InferenceProvider(Protocol):
|
|||
raise NotImplementedError("Reranking is not implemented")
|
||||
return # this is so mypy's safe-super rule will consider the method concrete
|
||||
|
||||
@webmethod(route="/openai/v1/completions", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/completions", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def openai_completion(
|
||||
self,
|
||||
|
@ -1078,6 +1077,7 @@ class InferenceProvider(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/chat/completions", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/chat/completions", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def openai_chat_completion(
|
||||
self,
|
||||
|
@ -1134,6 +1134,7 @@ class InferenceProvider(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/embeddings", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/embeddings", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def openai_embeddings(
|
||||
self,
|
||||
|
@ -1163,6 +1164,7 @@ class Inference(InferenceProvider):
|
|||
- Embedding models: these models generate embeddings to be used for semantic search.
|
||||
"""
|
||||
|
||||
@webmethod(route="/openai/v1/chat/completions", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/chat/completions", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def list_chat_completions(
|
||||
self,
|
||||
|
@ -1181,6 +1183,9 @@ class Inference(InferenceProvider):
|
|||
"""
|
||||
raise NotImplementedError("List chat completions is not implemented")
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/chat/completions/{completion_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
|
||||
)
|
||||
@webmethod(route="/chat/completions/{completion_id}", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def get_chat_completion(self, completion_id: str) -> OpenAICompletionWithInputMessages:
|
||||
"""Describe a chat completion by its ID.
|
||||
|
|
|
@ -111,6 +111,14 @@ class Models(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/models", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
async def openai_list_models(self) -> OpenAIListModelsResponse:
|
||||
"""List models using the OpenAI API.
|
||||
|
||||
:returns: A OpenAIListModelsResponse.
|
||||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/models/{model_id:path}", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def get_model(
|
||||
self,
|
||||
|
|
|
@ -114,6 +114,7 @@ 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.
|
||||
|
|
|
@ -7,7 +7,7 @@
|
|||
from enum import Enum
|
||||
from typing import Any, Literal, Protocol
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel
|
||||
from typing_extensions import runtime_checkable
|
||||
|
||||
from llama_stack.apis.common.content_types import URL, InterleavedContent
|
||||
|
@ -19,59 +19,23 @@ from llama_stack.schema_utils import json_schema_type, webmethod
|
|||
from .rag_tool import RAGToolRuntime
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class ToolParameter(BaseModel):
|
||||
"""Parameter definition for a tool.
|
||||
|
||||
:param name: Name of the parameter
|
||||
:param parameter_type: Type of the parameter (e.g., string, integer)
|
||||
:param description: Human-readable description of what the parameter does
|
||||
:param required: Whether this parameter is required for tool invocation
|
||||
:param items: Type of the elements when parameter_type is array
|
||||
:param title: (Optional) Title of the parameter
|
||||
:param default: (Optional) Default value for the parameter if not provided
|
||||
"""
|
||||
|
||||
name: str
|
||||
parameter_type: str
|
||||
description: str
|
||||
required: bool = Field(default=True)
|
||||
items: dict | None = None
|
||||
title: str | None = None
|
||||
default: Any | None = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class Tool(Resource):
|
||||
"""A tool that can be invoked by agents.
|
||||
|
||||
:param type: Type of resource, always 'tool'
|
||||
:param toolgroup_id: ID of the tool group this tool belongs to
|
||||
:param description: Human-readable description of what the tool does
|
||||
:param parameters: List of parameters this tool accepts
|
||||
:param metadata: (Optional) Additional metadata about the tool
|
||||
"""
|
||||
|
||||
type: Literal[ResourceType.tool] = ResourceType.tool
|
||||
toolgroup_id: str
|
||||
description: str
|
||||
parameters: list[ToolParameter]
|
||||
metadata: dict[str, Any] | None = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class ToolDef(BaseModel):
|
||||
"""Tool definition used in runtime contexts.
|
||||
|
||||
:param name: Name of the tool
|
||||
:param description: (Optional) Human-readable description of what the tool does
|
||||
:param parameters: (Optional) List of parameters this tool accepts
|
||||
:param input_schema: (Optional) JSON Schema for tool inputs (MCP inputSchema)
|
||||
:param output_schema: (Optional) JSON Schema for tool outputs (MCP outputSchema)
|
||||
:param metadata: (Optional) Additional metadata about the tool
|
||||
:param toolgroup_id: (Optional) ID of the tool group this tool belongs to
|
||||
"""
|
||||
|
||||
toolgroup_id: str | None = None
|
||||
name: str
|
||||
description: str | None = None
|
||||
parameters: list[ToolParameter] | None = None
|
||||
input_schema: dict[str, Any] | None = None
|
||||
output_schema: dict[str, Any] | None = None
|
||||
metadata: dict[str, Any] | None = None
|
||||
|
||||
|
||||
|
@ -122,7 +86,7 @@ class ToolInvocationResult(BaseModel):
|
|||
|
||||
|
||||
class ToolStore(Protocol):
|
||||
async def get_tool(self, tool_name: str) -> Tool: ...
|
||||
async def get_tool(self, tool_name: str) -> ToolDef: ...
|
||||
async def get_tool_group(self, toolgroup_id: str) -> ToolGroup: ...
|
||||
|
||||
|
||||
|
@ -135,15 +99,6 @@ class ListToolGroupsResponse(BaseModel):
|
|||
data: list[ToolGroup]
|
||||
|
||||
|
||||
class ListToolsResponse(BaseModel):
|
||||
"""Response containing a list of tools.
|
||||
|
||||
:param data: List of tools
|
||||
"""
|
||||
|
||||
data: list[Tool]
|
||||
|
||||
|
||||
class ListToolDefsResponse(BaseModel):
|
||||
"""Response containing a list of tool definitions.
|
||||
|
||||
|
@ -194,11 +149,11 @@ class ToolGroups(Protocol):
|
|||
...
|
||||
|
||||
@webmethod(route="/tools", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def list_tools(self, toolgroup_id: str | None = None) -> ListToolsResponse:
|
||||
async def list_tools(self, toolgroup_id: str | None = None) -> ListToolDefsResponse:
|
||||
"""List tools with optional tool group.
|
||||
|
||||
:param toolgroup_id: The ID of the tool group to list tools for.
|
||||
:returns: A ListToolsResponse.
|
||||
:returns: A ListToolDefsResponse.
|
||||
"""
|
||||
...
|
||||
|
||||
|
@ -206,11 +161,11 @@ class ToolGroups(Protocol):
|
|||
async def get_tool(
|
||||
self,
|
||||
tool_name: str,
|
||||
) -> Tool:
|
||||
) -> ToolDef:
|
||||
"""Get a tool by its name.
|
||||
|
||||
:param tool_name: The name of the tool to get.
|
||||
:returns: A Tool.
|
||||
:returns: A ToolDef.
|
||||
"""
|
||||
...
|
||||
|
||||
|
|
|
@ -512,6 +512,7 @@ class VectorIO(Protocol):
|
|||
...
|
||||
|
||||
# OpenAI Vector Stores API endpoints
|
||||
@webmethod(route="/openai/v1/vector_stores", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/vector_stores", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def openai_create_vector_store(
|
||||
self,
|
||||
|
@ -538,6 +539,7 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/vector_stores", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_list_vector_stores(
|
||||
self,
|
||||
|
@ -556,6 +558,9 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
|
||||
)
|
||||
@webmethod(route="/vector_stores/{vector_store_id}", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_retrieve_vector_store(
|
||||
self,
|
||||
|
@ -568,6 +573,9 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}", method="POST", level=LLAMA_STACK_API_V1, deprecated=True
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}",
|
||||
method="POST",
|
||||
|
@ -590,6 +598,9 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}",
|
||||
method="DELETE",
|
||||
|
@ -606,6 +617,12 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/search",
|
||||
method="POST",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/search",
|
||||
method="POST",
|
||||
|
@ -638,6 +655,12 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files",
|
||||
method="POST",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/files",
|
||||
method="POST",
|
||||
|
@ -660,6 +683,12 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/files",
|
||||
method="GET",
|
||||
|
@ -686,6 +715,12 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/files/{file_id}",
|
||||
method="GET",
|
||||
|
@ -704,6 +739,12 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}/content",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/files/{file_id}/content",
|
||||
method="GET",
|
||||
|
@ -722,6 +763,12 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}",
|
||||
method="POST",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/files/{file_id}",
|
||||
method="POST",
|
||||
|
@ -742,6 +789,12 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}",
|
||||
method="DELETE",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/files/{file_id}",
|
||||
method="DELETE",
|
||||
|
@ -765,6 +818,12 @@ class VectorIO(Protocol):
|
|||
method="POST",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/file_batches",
|
||||
method="POST",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
async def openai_create_vector_store_file_batch(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
|
@ -787,6 +846,12 @@ class VectorIO(Protocol):
|
|||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
async def openai_retrieve_vector_store_file_batch(
|
||||
self,
|
||||
batch_id: str,
|
||||
|
@ -800,6 +865,12 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/files",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/file_batches/{batch_id}/files",
|
||||
method="GET",
|
||||
|
@ -828,6 +899,12 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel",
|
||||
method="POST",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel",
|
||||
method="POST",
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue