mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 11:14:04 +00:00
(Feat) add `"/v1/batches/{batch_id:path}/cancel" endpoint (#7406)
* use 1 file for azure batches handling * add cancel_batch endpoint * add a cancel batch on open ai * add cancel_batch endpoint * add cancel batches to test * remove unused imports * test_batches_operations * update test_batches_operations
This commit is contained in:
Ishaan Jaff
GitHub
parent
440009fb32
commit
54cb64d03d
7 changed files with 589 additions and 304 deletions
|
|
@ -20,11 +20,16 @@ import httpx
|
|||
|
||||
import litellm
|
||||
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
|
||||
from litellm.llms.azure.azure import AzureBatchesAPI
|
||||
from litellm.llms.azure.batches.handler import AzureBatchesAPI
|
||||
from litellm.llms.openai.openai import OpenAIBatchesAPI
|
||||
from litellm.llms.vertex_ai.batches.handler import VertexAIBatchPrediction
|
||||
from litellm.secret_managers.main import get_secret_str
|
||||
from litellm.types.llms.openai import Batch, CreateBatchRequest, RetrieveBatchRequest
|
||||
from litellm.types.llms.openai import (
|
||||
Batch,
|
||||
CancelBatchRequest,
|
||||
CreateBatchRequest,
|
||||
RetrieveBatchRequest,
|
||||
)
|
||||
from litellm.types.router import GenericLiteLLMParams
|
||||
from litellm.utils import client, get_litellm_params, supports_httpx_timeout
|
||||
|
||||
|
|
@ -582,9 +587,163 @@ def list_batches(
|
|||
raise e
|
||||
|
||||
|
||||
def cancel_batch():
|
||||
pass
|
||||
async def acancel_batch(
|
||||
batch_id: str,
|
||||
custom_llm_provider: Literal["openai", "azure"] = "openai",
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
extra_headers: Optional[Dict[str, str]] = None,
|
||||
extra_body: Optional[Dict[str, str]] = None,
|
||||
**kwargs,
|
||||
) -> Batch:
|
||||
"""
|
||||
Async: Cancels a batch.
|
||||
|
||||
LiteLLM Equivalent of POST https://api.openai.com/v1/batches/{batch_id}/cancel
|
||||
"""
|
||||
try:
|
||||
loop = asyncio.get_event_loop()
|
||||
kwargs["acancel_batch"] = True
|
||||
|
||||
# Use a partial function to pass your keyword arguments
|
||||
func = partial(
|
||||
cancel_batch,
|
||||
batch_id,
|
||||
custom_llm_provider,
|
||||
metadata,
|
||||
extra_headers,
|
||||
extra_body,
|
||||
**kwargs,
|
||||
)
|
||||
# Add the context to the function
|
||||
ctx = contextvars.copy_context()
|
||||
func_with_context = partial(ctx.run, func)
|
||||
init_response = await loop.run_in_executor(None, func_with_context)
|
||||
if asyncio.iscoroutine(init_response):
|
||||
response = await init_response
|
||||
else:
|
||||
response = init_response
|
||||
|
||||
return response
|
||||
except Exception as e:
|
||||
raise e
|
||||
|
||||
|
||||
async def acancel_batch():
|
||||
pass
|
||||
def cancel_batch(
|
||||
batch_id: str,
|
||||
custom_llm_provider: Literal["openai", "azure"] = "openai",
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
extra_headers: Optional[Dict[str, str]] = None,
|
||||
extra_body: Optional[Dict[str, str]] = None,
|
||||
**kwargs,
|
||||
) -> Union[Batch, Coroutine[Any, Any, Batch]]:
|
||||
"""
|
||||
Cancels a batch.
|
||||
|
||||
LiteLLM Equivalent of POST https://api.openai.com/v1/batches/{batch_id}/cancel
|
||||
"""
|
||||
try:
|
||||
optional_params = GenericLiteLLMParams(**kwargs)
|
||||
### TIMEOUT LOGIC ###
|
||||
timeout = optional_params.timeout or kwargs.get("request_timeout", 600) or 600
|
||||
# set timeout for 10 minutes by default
|
||||
|
||||
if (
|
||||
timeout is not None
|
||||
and isinstance(timeout, httpx.Timeout)
|
||||
and supports_httpx_timeout(custom_llm_provider) is False
|
||||
):
|
||||
read_timeout = timeout.read or 600
|
||||
timeout = read_timeout # default 10 min timeout
|
||||
elif timeout is not None and not isinstance(timeout, httpx.Timeout):
|
||||
timeout = float(timeout) # type: ignore
|
||||
elif timeout is None:
|
||||
timeout = 600.0
|
||||
|
||||
_cancel_batch_request = CancelBatchRequest(
|
||||
batch_id=batch_id,
|
||||
extra_headers=extra_headers,
|
||||
extra_body=extra_body,
|
||||
)
|
||||
|
||||
_is_async = kwargs.pop("acancel_batch", False) is True
|
||||
api_base: Optional[str] = None
|
||||
if custom_llm_provider == "openai":
|
||||
api_base = (
|
||||
optional_params.api_base
|
||||
or litellm.api_base
|
||||
or os.getenv("OPENAI_API_BASE")
|
||||
or "https://api.openai.com/v1"
|
||||
)
|
||||
organization = (
|
||||
optional_params.organization
|
||||
or litellm.organization
|
||||
or os.getenv("OPENAI_ORGANIZATION", None)
|
||||
or None
|
||||
)
|
||||
api_key = (
|
||||
optional_params.api_key
|
||||
or litellm.api_key
|
||||
or litellm.openai_key
|
||||
or os.getenv("OPENAI_API_KEY")
|
||||
)
|
||||
|
||||
response = openai_batches_instance.cancel_batch(
|
||||
_is_async=_is_async,
|
||||
cancel_batch_data=_cancel_batch_request,
|
||||
api_base=api_base,
|
||||
api_key=api_key,
|
||||
organization=organization,
|
||||
timeout=timeout,
|
||||
max_retries=optional_params.max_retries,
|
||||
)
|
||||
elif custom_llm_provider == "azure":
|
||||
api_base = (
|
||||
optional_params.api_base
|
||||
or litellm.api_base
|
||||
or get_secret_str("AZURE_API_BASE")
|
||||
)
|
||||
api_version = (
|
||||
optional_params.api_version
|
||||
or litellm.api_version
|
||||
or get_secret_str("AZURE_API_VERSION")
|
||||
)
|
||||
|
||||
api_key = (
|
||||
optional_params.api_key
|
||||
or litellm.api_key
|
||||
or litellm.azure_key
|
||||
or get_secret_str("AZURE_OPENAI_API_KEY")
|
||||
or get_secret_str("AZURE_API_KEY")
|
||||
)
|
||||
|
||||
extra_body = optional_params.get("extra_body", {})
|
||||
if extra_body is not None:
|
||||
extra_body.pop("azure_ad_token", None)
|
||||
else:
|
||||
get_secret_str("AZURE_AD_TOKEN") # type: ignore
|
||||
|
||||
response = azure_batches_instance.cancel_batch(
|
||||
_is_async=_is_async,
|
||||
api_base=api_base,
|
||||
api_key=api_key,
|
||||
api_version=api_version,
|
||||
timeout=timeout,
|
||||
max_retries=optional_params.max_retries,
|
||||
cancel_batch_data=_cancel_batch_request,
|
||||
)
|
||||
else:
|
||||
raise litellm.exceptions.BadRequestError(
|
||||
message="LiteLLM doesn't support {} for 'cancel_batch'. Only 'openai' and 'azure' are supported.".format(
|
||||
custom_llm_provider
|
||||
),
|
||||
model="n/a",
|
||||
llm_provider=custom_llm_provider,
|
||||
response=httpx.Response(
|
||||
status_code=400,
|
||||
content="Unsupported provider",
|
||||
request=httpx.Request(method="cancel_batch", url="https://github.com/BerriAI/litellm"), # type: ignore
|
||||
),
|
||||
)
|
||||
return response
|
||||
except Exception as e:
|
||||
raise e
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue