Merge branch 'main' into issue-3443-require_approval

llama_stack/apis/agents/agents.py

@@ -694,7 +694,7 @@ class Agents(Protocol):
     #
     # Both of these APIs are inherently stateful.
 
-    @webmethod(route="/openai/v1/responses/{response_id}", method="GET", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/responses/{response_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def get_openai_response(
         self,
         response_id: str,
@@ -706,7 +706,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/responses", method="POST", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/responses", method="POST", level=LLAMA_STACK_API_V1)
     async def create_openai_response(
         self,
         input: str | list[OpenAIResponseInput],
@@ -731,7 +731,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/responses", method="GET", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/responses", method="GET", level=LLAMA_STACK_API_V1)
     async def list_openai_responses(
         self,
         after: str | None = None,
@@ -749,7 +749,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/responses/{response_id}/input_items", method="GET", level=LLAMA_STACK_API_V1)
+    @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,
@@ -771,7 +771,7 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/responses/{response_id}", method="DELETE", level=LLAMA_STACK_API_V1)
+    @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.
 

llama_stack/apis/agents/openai_responses.py

@@ -363,7 +363,6 @@ class OpenAIResponseObject(BaseModel):
     :param text: Text formatting configuration for the response
     :param top_p: (Optional) Nucleus sampling parameter used for generation
     :param truncation: (Optional) Truncation strategy applied to the response
-    :param user: (Optional) User identifier associated with the request
     """
 
     created_at: int
@@ -381,7 +380,6 @@ class OpenAIResponseObject(BaseModel):
     text: OpenAIResponseText = OpenAIResponseText(format=OpenAIResponseTextFormat(type="text"))
     top_p: float | None = None
     truncation: str | None = None
-    user: str | None = None
 
 
 @json_schema_type

llama_stack/apis/batches/batches.py

@@ -43,7 +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)
+    @webmethod(route="/batches", method="POST", level=LLAMA_STACK_API_V1)
     async def create_batch(
         self,
         input_file_id: str,
@@ -63,7 +63,7 @@ class Batches(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/batches/{batch_id}", method="GET", level=LLAMA_STACK_API_V1)
+    @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.
 
@@ -72,7 +72,7 @@ class Batches(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/batches/{batch_id}/cancel", method="POST", level=LLAMA_STACK_API_V1)
+    @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.
 
@@ -81,7 +81,7 @@ class Batches(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/batches", method="GET", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/batches", method="GET", level=LLAMA_STACK_API_V1)
     async def list_batches(
         self,
         after: str | None = None,

llama_stack/apis/files/files.py

@@ -105,14 +105,12 @@ class OpenAIFileDeleteResponse(BaseModel):
 @trace_protocol
 class Files(Protocol):
     # OpenAI Files API Endpoints
-    @webmethod(route="/openai/v1/files", method="POST", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/files", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_upload_file(
         self,
         file: Annotated[UploadFile, File()],
         purpose: Annotated[OpenAIFilePurpose, Form()],
-        expires_after_anchor: Annotated[str | None, Form(alias="expires_after[anchor]")] = None,
-        expires_after_seconds: Annotated[int | None, Form(alias="expires_after[seconds]")] = None,
-        # TODO: expires_after is producing strange openapi spec, params are showing up as a required w/ oneOf being null
+        expires_after: Annotated[ExpiresAfter | None, Form()] = None,
     ) -> OpenAIFileObject:
         """
         Upload a file that can be used across various endpoints.
@@ -120,15 +118,16 @@ class Files(Protocol):
         The file upload should be a multipart form request with:
         - file: The File object (not file name) to be uploaded.
         - purpose: The intended purpose of the uploaded file.
-        - expires_after: Optional form values describing expiration for the file. Expected expires_after[anchor] = "created_at", expires_after[seconds] = {integer}. Seconds must be between 3600 and 2592000 (1 hour to 30 days).
+        - expires_after: Optional form values describing expiration for the file.
 
         :param file: The uploaded file object containing content and metadata (filename, content_type, etc.).
         :param purpose: The intended purpose of the uploaded file (e.g., "assistants", "fine-tune").
+        :param expires_after: Optional form values describing expiration for the file.
         :returns: An OpenAIFileObject representing the uploaded file.
         """
         ...
 
-    @webmethod(route="/openai/v1/files", method="GET", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/files", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_list_files(
         self,
         after: str | None = None,
@@ -147,7 +146,7 @@ class Files(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_retrieve_file(
         self,
         file_id: str,
@@ -160,7 +159,7 @@ class Files(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1)
     async def openai_delete_file(
         self,
         file_id: str,
@@ -173,7 +172,7 @@ class Files(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/files/{file_id}/content", method="GET", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/files/{file_id}/content", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_retrieve_file_content(
         self,
         file_id: str,

llama_stack/apis/inference/inference.py

@@ -17,11 +17,11 @@ from typing import (
 from pydantic import BaseModel, Field, field_validator
 from typing_extensions import TypedDict
 
-from llama_stack.apis.common.content_types import ContentDelta, InterleavedContent, InterleavedContentItem
+from llama_stack.apis.common.content_types import ContentDelta, InterleavedContent
 from llama_stack.apis.common.responses import Order
 from llama_stack.apis.models import Model
 from llama_stack.apis.telemetry import MetricResponseMixin
-from llama_stack.apis.version import LLAMA_STACK_API_V1
+from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1ALPHA
 from llama_stack.models.llama.datatypes import (
     BuiltinTool,
     StopReason,
@@ -1070,27 +1070,7 @@ class InferenceProvider(Protocol):
         """
         ...
 
-    @webmethod(route="/inference/embeddings", method="POST", level=LLAMA_STACK_API_V1)
-    async def embeddings(
-        self,
-        model_id: str,
-        contents: list[str] | list[InterleavedContentItem],
-        text_truncation: TextTruncation | None = TextTruncation.none,
-        output_dimension: int | None = None,
-        task_type: EmbeddingTaskType | None = None,
-    ) -> EmbeddingsResponse:
-        """Generate embeddings for content pieces using the specified model.
-
-        :param model_id: 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 contents: List of contents to generate embeddings for. Each content can be a string or an InterleavedContentItem (and hence can be multimodal). The behavior depends on the model and provider. Some models may only support text.
-        :param output_dimension: (Optional) Output dimensionality for the embeddings. Only supported by Matryoshka models.
-        :param text_truncation: (Optional) Config for how to truncate text for embedding when text is longer than the model's max sequence length.
-        :param task_type: (Optional) How is the embedding being used? This is only supported by asymmetric embedding models.
-        :returns: An array of embeddings, one for each content. Each embedding is a list of floats. The dimensionality of the embedding is model-specific; you can check model metadata using /models/{model_id}.
-        """
-        ...
-
-    @webmethod(route="/inference/rerank", method="POST", experimental=True, level=LLAMA_STACK_API_V1)
+    @webmethod(route="/inference/rerank", method="POST", level=LLAMA_STACK_API_V1ALPHA)
     async def rerank(
         self,
         model: str,
@@ -1109,7 +1089,7 @@ 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)
+    @webmethod(route="/completions", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_completion(
         self,
         # Standard OpenAI completion parameters
@@ -1160,7 +1140,7 @@ class InferenceProvider(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/chat/completions", method="POST", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/chat/completions", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_chat_completion(
         self,
         model: str,
@@ -1216,7 +1196,7 @@ class InferenceProvider(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/embeddings", method="POST", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/embeddings", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_embeddings(
         self,
         model: str,
@@ -1245,7 +1225,7 @@ 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)
+    @webmethod(route="/chat/completions", method="GET", level=LLAMA_STACK_API_V1)
     async def list_chat_completions(
         self,
         after: str | None = None,
@@ -1263,7 +1243,7 @@ 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)
+    @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.
 

llama_stack/apis/models/models.py

@@ -111,14 +111,6 @@ class Models(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/models", method="GET", level=LLAMA_STACK_API_V1)
-    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,

llama_stack/apis/safety/safety.py

@@ -114,7 +114,7 @@ class Safety(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/moderations", method="POST", level=LLAMA_STACK_API_V1)
+    @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.
         :param input: Input (or inputs) to classify.

llama_stack/apis/vector_io/vector_io.py

@@ -473,7 +473,7 @@ class VectorIO(Protocol):
         ...
 
     # OpenAI Vector Stores API endpoints
-    @webmethod(route="/openai/v1/vector_stores", method="POST", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/vector_stores", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_create_vector_store(
         self,
         name: str | None = None,
@@ -499,7 +499,7 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/vector_stores", method="GET", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/vector_stores", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_list_vector_stores(
         self,
         limit: int | None = 20,
@@ -517,7 +517,7 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/vector_stores/{vector_store_id}", method="GET", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/vector_stores/{vector_store_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_retrieve_vector_store(
         self,
         vector_store_id: str,
@@ -529,7 +529,7 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/vector_stores/{vector_store_id}", method="POST", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/vector_stores/{vector_store_id}", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_update_vector_store(
         self,
         vector_store_id: str,
@@ -547,7 +547,7 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/vector_stores/{vector_store_id}", method="DELETE", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/vector_stores/{vector_store_id}", method="DELETE", level=LLAMA_STACK_API_V1)
     async def openai_delete_vector_store(
         self,
         vector_store_id: str,
@@ -559,7 +559,7 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/vector_stores/{vector_store_id}/search", method="POST", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/vector_stores/{vector_store_id}/search", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_search_vector_store(
         self,
         vector_store_id: str,
@@ -585,7 +585,7 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files", method="POST", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/vector_stores/{vector_store_id}/files", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_attach_file_to_vector_store(
         self,
         vector_store_id: str,
@@ -603,7 +603,7 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files", method="GET", level=LLAMA_STACK_API_V1)
+    @webmethod(route="/vector_stores/{vector_store_id}/files", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_list_files_in_vector_store(
         self,
         vector_store_id: str,
@@ -625,9 +625,7 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1
-    )
+    @webmethod(route="/vector_stores/{vector_store_id}/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_retrieve_vector_store_file(
         self,
         vector_store_id: str,
@@ -642,7 +640,7 @@ class VectorIO(Protocol):
         ...
 
     @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}/content",
+        route="/vector_stores/{vector_store_id}/files/{file_id}/content",
         method="GET",
         level=LLAMA_STACK_API_V1,
     )
@@ -659,9 +657,7 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}", method="POST", level=LLAMA_STACK_API_V1
-    )
+    @webmethod(route="/vector_stores/{vector_store_id}/files/{file_id}", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_update_vector_store_file(
         self,
         vector_store_id: str,
@@ -677,9 +673,7 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1
-    )
+    @webmethod(route="/vector_stores/{vector_store_id}/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1)
     async def openai_delete_vector_store_file(
         self,
         vector_store_id: str,