mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 19:24:27 +00:00
feat(batches): add azure openai batches endpoint support
Closes https://github.com/BerriAI/litellm/issues/5073
This commit is contained in:
Krrish Dholakia
parent
2f9f01e72c
commit
a9b5d5271f
7 changed files with 584 additions and 173 deletions
|
|
@ -87,6 +87,24 @@ def file_retrieve(
|
|||
"""
|
||||
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
|
||||
|
||||
_is_async = kwargs.pop("is_async", False) is True
|
||||
|
||||
if custom_llm_provider == "openai":
|
||||
# for deepinfra/perplexity/anyscale/groq we check in get_llm_provider and pass in the api base from there
|
||||
api_base = (
|
||||
|
|
@ -108,25 +126,6 @@ def file_retrieve(
|
|||
or litellm.openai_key
|
||||
or os.getenv("OPENAI_API_KEY")
|
||||
)
|
||||
### 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) == 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
|
||||
|
||||
_is_async = kwargs.pop("is_async", False) is True
|
||||
|
||||
response = openai_files_instance.retrieve_file(
|
||||
file_id=file_id,
|
||||
|
|
@ -137,9 +136,41 @@ def file_retrieve(
|
|||
max_retries=optional_params.max_retries,
|
||||
organization=organization,
|
||||
)
|
||||
elif custom_llm_provider == "azure":
|
||||
api_base = optional_params.api_base or litellm.api_base or get_secret("AZURE_API_BASE") # type: ignore
|
||||
api_version = (
|
||||
optional_params.api_version
|
||||
or litellm.api_version
|
||||
or get_secret("AZURE_API_VERSION")
|
||||
) # type: ignore
|
||||
|
||||
api_key = (
|
||||
optional_params.api_key
|
||||
or litellm.api_key
|
||||
or litellm.azure_key
|
||||
or get_secret("AZURE_OPENAI_API_KEY")
|
||||
or get_secret("AZURE_API_KEY")
|
||||
) # type: ignore
|
||||
|
||||
extra_body = optional_params.get("extra_body", {})
|
||||
azure_ad_token: Optional[str] = None
|
||||
if extra_body is not None:
|
||||
azure_ad_token = extra_body.pop("azure_ad_token", None)
|
||||
else:
|
||||
azure_ad_token = get_secret("AZURE_AD_TOKEN") # type: ignore
|
||||
|
||||
response = azure_files_instance.retrieve_file(
|
||||
_is_async=_is_async,
|
||||
api_base=api_base,
|
||||
api_key=api_key,
|
||||
api_version=api_version,
|
||||
timeout=timeout,
|
||||
max_retries=optional_params.max_retries,
|
||||
file_id=file_id,
|
||||
)
|
||||
else:
|
||||
raise litellm.exceptions.BadRequestError(
|
||||
message="LiteLLM doesn't support {} for 'create_batch'. Only 'openai' is supported.".format(
|
||||
message="LiteLLM doesn't support {} for 'file_retrieve'. Only 'openai' and 'azure' are supported.".format(
|
||||
custom_llm_provider
|
||||
),
|
||||
model="n/a",
|
||||
|
|
@ -361,6 +392,23 @@ def file_list(
|
|||
"""
|
||||
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) == 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
|
||||
|
||||
_is_async = kwargs.pop("is_async", False) is True
|
||||
if custom_llm_provider == "openai":
|
||||
# for deepinfra/perplexity/anyscale/groq we check in get_llm_provider and pass in the api base from there
|
||||
api_base = (
|
||||
|
|
@ -382,25 +430,6 @@ def file_list(
|
|||
or litellm.openai_key
|
||||
or os.getenv("OPENAI_API_KEY")
|
||||
)
|
||||
### 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) == 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
|
||||
|
||||
_is_async = kwargs.pop("is_async", False) is True
|
||||
|
||||
response = openai_files_instance.list_files(
|
||||
purpose=purpose,
|
||||
|
|
@ -411,9 +440,41 @@ def file_list(
|
|||
max_retries=optional_params.max_retries,
|
||||
organization=organization,
|
||||
)
|
||||
elif custom_llm_provider == "azure":
|
||||
api_base = optional_params.api_base or litellm.api_base or get_secret("AZURE_API_BASE") # type: ignore
|
||||
api_version = (
|
||||
optional_params.api_version
|
||||
or litellm.api_version
|
||||
or get_secret("AZURE_API_VERSION")
|
||||
) # type: ignore
|
||||
|
||||
api_key = (
|
||||
optional_params.api_key
|
||||
or litellm.api_key
|
||||
or litellm.azure_key
|
||||
or get_secret("AZURE_OPENAI_API_KEY")
|
||||
or get_secret("AZURE_API_KEY")
|
||||
) # type: ignore
|
||||
|
||||
extra_body = optional_params.get("extra_body", {})
|
||||
azure_ad_token: Optional[str] = None
|
||||
if extra_body is not None:
|
||||
azure_ad_token = extra_body.pop("azure_ad_token", None)
|
||||
else:
|
||||
azure_ad_token = get_secret("AZURE_AD_TOKEN") # type: ignore
|
||||
|
||||
response = azure_files_instance.list_files(
|
||||
_is_async=_is_async,
|
||||
api_base=api_base,
|
||||
api_key=api_key,
|
||||
api_version=api_version,
|
||||
timeout=timeout,
|
||||
max_retries=optional_params.max_retries,
|
||||
purpose=purpose,
|
||||
)
|
||||
else:
|
||||
raise litellm.exceptions.BadRequestError(
|
||||
message="LiteLLM doesn't support {} for 'file_list'. Only 'openai' is supported.".format(
|
||||
message="LiteLLM doesn't support {} for 'file_list'. Only 'openai' and 'azure' are supported.".format(
|
||||
custom_llm_provider
|
||||
),
|
||||
model="n/a",
|
||||
|
|
@ -645,6 +706,29 @@ def file_content(
|
|||
"""
|
||||
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) == 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
|
||||
|
||||
_file_content_request = FileContentRequest(
|
||||
file_id=file_id,
|
||||
extra_headers=extra_headers,
|
||||
extra_body=extra_body,
|
||||
)
|
||||
|
||||
_is_async = kwargs.pop("afile_content", False) is True
|
||||
if custom_llm_provider == "openai":
|
||||
# for deepinfra/perplexity/anyscale/groq we check in get_llm_provider and pass in the api base from there
|
||||
api_base = (
|
||||
|
|
@ -666,31 +750,6 @@ def file_content(
|
|||
or litellm.openai_key
|
||||
or os.getenv("OPENAI_API_KEY")
|
||||
)
|
||||
### 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) == 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
|
||||
|
||||
_file_content_request = FileContentRequest(
|
||||
file_id=file_id,
|
||||
extra_headers=extra_headers,
|
||||
extra_body=extra_body,
|
||||
)
|
||||
|
||||
_is_async = kwargs.pop("afile_content", False) is True
|
||||
|
||||
response = openai_files_instance.file_content(
|
||||
_is_async=_is_async,
|
||||
|
|
@ -701,9 +760,41 @@ def file_content(
|
|||
max_retries=optional_params.max_retries,
|
||||
organization=organization,
|
||||
)
|
||||
elif custom_llm_provider == "azure":
|
||||
api_base = optional_params.api_base or litellm.api_base or get_secret("AZURE_API_BASE") # type: ignore
|
||||
api_version = (
|
||||
optional_params.api_version
|
||||
or litellm.api_version
|
||||
or get_secret("AZURE_API_VERSION")
|
||||
) # type: ignore
|
||||
|
||||
api_key = (
|
||||
optional_params.api_key
|
||||
or litellm.api_key
|
||||
or litellm.azure_key
|
||||
or get_secret("AZURE_OPENAI_API_KEY")
|
||||
or get_secret("AZURE_API_KEY")
|
||||
) # type: ignore
|
||||
|
||||
extra_body = optional_params.get("extra_body", {})
|
||||
azure_ad_token: Optional[str] = None
|
||||
if extra_body is not None:
|
||||
azure_ad_token = extra_body.pop("azure_ad_token", None)
|
||||
else:
|
||||
azure_ad_token = get_secret("AZURE_AD_TOKEN") # type: ignore
|
||||
|
||||
response = azure_files_instance.file_content(
|
||||
_is_async=_is_async,
|
||||
api_base=api_base,
|
||||
api_key=api_key,
|
||||
api_version=api_version,
|
||||
timeout=timeout,
|
||||
max_retries=optional_params.max_retries,
|
||||
file_content_request=_file_content_request,
|
||||
)
|
||||
else:
|
||||
raise litellm.exceptions.BadRequestError(
|
||||
message="LiteLLM doesn't support {} for 'create_batch'. Only 'openai' is supported.".format(
|
||||
message="LiteLLM doesn't support {} for 'file_content'. Only 'openai' and 'azure' are supported.".format(
|
||||
custom_llm_provider
|
||||
),
|
||||
model="n/a",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue