Revert "feat: add batches API with OpenAI compatibility" (#3149)

Reverts llamastack/llama-stack#3088

The PR broke integration tests.

llama_stack/apis/batches/__init__.py

@@ -1,9 +0,0 @@
-# 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 .batches import Batches, BatchObject, ListBatchesResponse
-
-__all__ = ["Batches", "BatchObject", "ListBatchesResponse"]

llama_stack/apis/batches/batches.py

@@ -1,89 +0,0 @@
-# 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 Literal, Protocol, runtime_checkable
-
-from pydantic import BaseModel, Field
-
-from llama_stack.schema_utils import json_schema_type, webmethod
-
-try:
-    from openai.types import Batch as BatchObject
-except ImportError as e:
-    raise ImportError("OpenAI package is required for batches API. Please install it with: pip install openai") from e
-
-
-@json_schema_type
-class ListBatchesResponse(BaseModel):
-    """Response containing a list of batch objects."""
-
-    object: Literal["list"] = "list"
-    data: list[BatchObject] = Field(..., description="List of batch objects")
-    first_id: str | None = Field(default=None, description="ID of the first batch in the list")
-    last_id: str | None = Field(default=None, description="ID of the last batch in the list")
-    has_more: bool = Field(default=False, description="Whether there are more batches available")
-
-
-@runtime_checkable
-class Batches(Protocol):
-    """Protocol for batch processing API operations.
-
-    The Batches API enables efficient processing of multiple requests in a single operation,
-    particularly useful for processing large datasets, batch evaluation workflows, and
-    cost-effective inference at scale.
-
-    Note: This API is currently under active development and may undergo changes.
-    """
-
-    @webmethod(route="/openai/v1/batches", method="POST")
-    async def create_batch(
-        self,
-        input_file_id: str,
-        endpoint: str,
-        completion_window: Literal["24h"],
-        metadata: dict[str, str] | None = None,
-    ) -> BatchObject:
-        """Create a new batch for processing multiple API requests.
-
-        :param input_file_id: The ID of an uploaded file containing requests for the batch.
-        :param endpoint: The endpoint to be used for all requests in the batch.
-        :param completion_window: The time window within which the batch should be processed.
-        :param metadata: Optional metadata for the batch.
-        :returns: The created batch object.
-        """
-        ...
-
-    @webmethod(route="/openai/v1/batches/{batch_id}", method="GET")
-    async def retrieve_batch(self, batch_id: str) -> BatchObject:
-        """Retrieve information about a specific batch.
-
-        :param batch_id: The ID of the batch to retrieve.
-        :returns: The batch object.
-        """
-        ...
-
-    @webmethod(route="/openai/v1/batches/{batch_id}/cancel", method="POST")
-    async def cancel_batch(self, batch_id: str) -> BatchObject:
-        """Cancel a batch that is in progress.
-
-        :param batch_id: The ID of the batch to cancel.
-        :returns: The updated batch object.
-        """
-        ...
-
-    @webmethod(route="/openai/v1/batches", method="GET")
-    async def list_batches(
-        self,
-        after: str | None = None,
-        limit: int = 20,
-    ) -> ListBatchesResponse:
-        """List all batches for the current user.
-
-        :param after: A cursor for pagination; returns batches after this batch ID.
-        :param limit: Number of batches to return (default 20, max 100).
-        :returns: A list of batch objects.
-        """
-        ...

llama_stack/apis/common/errors.py

@@ -64,12 +64,6 @@ class SessionNotFoundError(ValueError):
         super().__init__(message)
 
 
-class ConflictError(ValueError):
-    """raised when an operation cannot be performed due to a conflict with the current state"""
-
-    pass
-
-
 class ModelTypeError(TypeError):
     """raised when a model is present but not the correct type"""
 

llama_stack/apis/datatypes.py

@@ -86,7 +86,6 @@ class Api(Enum, metaclass=DynamicApiMeta):
     :cvar inference: Text generation, chat completions, and embeddings
     :cvar safety: Content moderation and safety shields
     :cvar agents: Agent orchestration and execution
-    :cvar batches: Batch processing for asynchronous API requests
     :cvar vector_io: Vector database operations and queries
     :cvar datasetio: Dataset input/output operations
     :cvar scoring: Model output evaluation and scoring
@@ -109,7 +108,6 @@ class Api(Enum, metaclass=DynamicApiMeta):
     inference = "inference"
     safety = "safety"
     agents = "agents"
-    batches = "batches"
     vector_io = "vector_io"
     datasetio = "datasetio"
     scoring = "scoring"

llama_stack/apis/files/files.py

@@ -22,7 +22,6 @@ class OpenAIFilePurpose(StrEnum):
     """
 
     ASSISTANTS = "assistants"
-    BATCH = "batch"
     # TODO: Add other purposes as needed