mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-15 06:00:48 +00:00
remove unused CreateBatchRequest, update completion_window to be literal "24h"
This commit is contained in:
parent
95a3ecdffc
commit
44263ce954
4 changed files with 7 additions and 18 deletions
|
@ -4,6 +4,6 @@
|
||||||
# This source code is licensed under the terms described in the LICENSE file in
|
# This source code is licensed under the terms described in the LICENSE file in
|
||||||
# the root directory of this source tree.
|
# the root directory of this source tree.
|
||||||
|
|
||||||
from .batches import Batches, BatchObject, CreateBatchRequest, ListBatchesResponse
|
from .batches import Batches, BatchObject, ListBatchesResponse
|
||||||
|
|
||||||
__all__ = ["Batches", "BatchObject", "CreateBatchRequest", "ListBatchesResponse"]
|
__all__ = ["Batches", "BatchObject", "ListBatchesResponse"]
|
||||||
|
|
|
@ -4,7 +4,7 @@
|
||||||
# This source code is licensed under the terms described in the LICENSE file in
|
# This source code is licensed under the terms described in the LICENSE file in
|
||||||
# the root directory of this source tree.
|
# the root directory of this source tree.
|
||||||
|
|
||||||
from typing import Any, Literal, Protocol, runtime_checkable
|
from typing import Literal, Protocol, runtime_checkable
|
||||||
|
|
||||||
from pydantic import BaseModel, Field
|
from pydantic import BaseModel, Field
|
||||||
|
|
||||||
|
@ -16,16 +16,6 @@ except ImportError as e:
|
||||||
raise ImportError("OpenAI package is required for batches API. Please install it with: pip install openai") from e
|
raise ImportError("OpenAI package is required for batches API. Please install it with: pip install openai") from e
|
||||||
|
|
||||||
|
|
||||||
@json_schema_type
|
|
||||||
class CreateBatchRequest(BaseModel):
|
|
||||||
"""Request to create a new batch."""
|
|
||||||
|
|
||||||
input_file_id: str = Field(..., description="The ID of an uploaded file that contains requests for the new batch")
|
|
||||||
endpoint: str = Field(..., description="The endpoint to be used for all requests in the batch")
|
|
||||||
completion_window: str = Field(..., description="The time window within which the batch should be processed")
|
|
||||||
metadata: dict[str, Any] | None = Field(default=None, description="Optional metadata for the batch")
|
|
||||||
|
|
||||||
|
|
||||||
@json_schema_type
|
@json_schema_type
|
||||||
class ListBatchesResponse(BaseModel):
|
class ListBatchesResponse(BaseModel):
|
||||||
"""Response containing a list of batch objects."""
|
"""Response containing a list of batch objects."""
|
||||||
|
@ -53,7 +43,7 @@ class Batches(Protocol):
|
||||||
self,
|
self,
|
||||||
input_file_id: str,
|
input_file_id: str,
|
||||||
endpoint: str,
|
endpoint: str,
|
||||||
completion_window: str,
|
completion_window: Literal["24h"],
|
||||||
metadata: dict[str, str] | None = None,
|
metadata: dict[str, str] | None = None,
|
||||||
) -> BatchObject:
|
) -> BatchObject:
|
||||||
"""Create a new batch for processing multiple API requests.
|
"""Create a new batch for processing multiple API requests.
|
||||||
|
|
|
@ -10,7 +10,7 @@ import json
|
||||||
import time
|
import time
|
||||||
import uuid
|
import uuid
|
||||||
from io import BytesIO
|
from io import BytesIO
|
||||||
from typing import Any
|
from typing import Any, Literal
|
||||||
|
|
||||||
from openai.types.batch import BatchError, Errors
|
from openai.types.batch import BatchError, Errors
|
||||||
from pydantic import BaseModel
|
from pydantic import BaseModel
|
||||||
|
@ -108,7 +108,7 @@ class ReferenceBatchesImpl(Batches):
|
||||||
self,
|
self,
|
||||||
input_file_id: str,
|
input_file_id: str,
|
||||||
endpoint: str,
|
endpoint: str,
|
||||||
completion_window: str,
|
completion_window: Literal["24h"],
|
||||||
metadata: dict[str, str] | None = None,
|
metadata: dict[str, str] | None = None,
|
||||||
) -> BatchObject:
|
) -> BatchObject:
|
||||||
"""
|
"""
|
||||||
|
|
|
@ -379,9 +379,8 @@ class TestBatchesErrorHandling:
|
||||||
)
|
)
|
||||||
assert exc_info.value.status_code == 400
|
assert exc_info.value.status_code == 400
|
||||||
error_msg = str(exc_info.value).lower()
|
error_msg = str(exc_info.value).lower()
|
||||||
assert "invalid value" in error_msg
|
assert "error" in error_msg
|
||||||
assert "completion_window" in error_msg
|
assert "completion_window" in error_msg
|
||||||
assert "supported values are" in error_msg
|
|
||||||
|
|
||||||
def test_batch_streaming_not_supported(self, openai_client, batch_helper, text_model_id):
|
def test_batch_streaming_not_supported(self, openai_client, batch_helper, text_model_id):
|
||||||
"""Test that streaming responses are not supported in batches."""
|
"""Test that streaming responses are not supported in batches."""
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue