phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into litellm_load_balancing_transcription_endpoints

Browse source
This commit is contained in:
Krish Dholakia 2024-03-08 23:08:47 -08:00 • committed by GitHub
commit f461352908
22 changed files with 704 additions and 233 deletions
Download patch file Download diff file Expand all files Collapse all files

51
litellm/llms/azure.py
View file

@ -15,6 +15,7 @@ import litellm, json
import httpx
from .custom_httpx.azure_dall_e_2 import CustomHTTPTransport, AsyncCustomHTTPTransport
from openai import AzureOpenAI, AsyncAzureOpenAI
import uuid
class AzureOpenAIError(Exception):
@ -271,6 +272,14 @@ class AzureChatCompletion(BaseLLM):
azure_client = AzureOpenAI(**azure_client_params)
else:
azure_client = client
if api_version is not None and isinstance(
azure_client._custom_query, dict
):
# set api_version to version passed by user
azure_client._custom_query.setdefault(
"api-version", api_version
)
response = azure_client.chat.completions.create(**data, timeout=timeout) # type: ignore
stringified_response = response.model_dump()
## LOGGING
@ -334,10 +343,17 @@ class AzureChatCompletion(BaseLLM):
azure_client_params["api_key"] = api_key
elif azure_ad_token is not None:
azure_client_params["azure_ad_token"] = azure_ad_token
# setting Azure client
if client is None:
azure_client = AsyncAzureOpenAI(**azure_client_params)
else:
azure_client = client
if api_version is not None and isinstance(
azure_client._custom_query, dict
):
# set api_version to version passed by user
azure_client._custom_query.setdefault("api-version", api_version)
## LOGGING
logging_obj.pre_call(
input=data["messages"],
@ -402,6 +418,9 @@ class AzureChatCompletion(BaseLLM):
azure_client = AzureOpenAI(**azure_client_params)
else:
azure_client = client
if api_version is not None and isinstance(azure_client._custom_query, dict):
# set api_version to version passed by user
azure_client._custom_query.setdefault("api-version", api_version)
## LOGGING
logging_obj.pre_call(
input=data["messages"],
@ -455,6 +474,11 @@ class AzureChatCompletion(BaseLLM):
azure_client = AsyncAzureOpenAI(**azure_client_params)
else:
azure_client = client
if api_version is not None and isinstance(
azure_client._custom_query, dict
):
# set api_version to version passed by user
azure_client._custom_query.setdefault("api-version", api_version)
## LOGGING
logging_obj.pre_call(
input=data["messages"],
@ -813,6 +837,19 @@ class AzureChatCompletion(BaseLLM):
azure_client = AzureOpenAI(http_client=litellm.client_session, **azure_client_params) # type: ignore
else:
azure_client = client
## LOGGING
logging_obj.pre_call(
input=f"audio_file_{uuid.uuid4()}",
api_key=azure_client.api_key,
additional_args={
"headers": {"Authorization": f"Bearer {azure_client.api_key}"},
"api_base": azure_client._base_url._uri_reference,
"atranscription": True,
"complete_input_dict": data,
},
)
response = azure_client.audio.transcriptions.create(
**data, timeout=timeout # type: ignore
)
@ -850,6 +887,20 @@ class AzureChatCompletion(BaseLLM):
else:
async_azure_client = client
## LOGGING
logging_obj.pre_call(
input=f"audio_file_{uuid.uuid4()}",
api_key=async_azure_client.api_key,
additional_args={
"headers": {
"Authorization": f"Bearer {async_azure_client.api_key}"
},
"api_base": async_azure_client._base_url._uri_reference,
"atranscription": True,
"complete_input_dict": data,
},
)
response = await async_azure_client.audio.transcriptions.create(
**data, timeout=timeout
) # type: ignore