phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 10:44:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(feat) cost tracking for azure llms

Browse source
This commit is contained in:
ishaan-jaff 2023-11-23 21:41:36 -08:00
parent 9a44433844
commit 19fb24cd15
3 changed files with 21 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/llms/azure.py
View file

@ -157,6 +157,7 @@ class AzureChatCompletion(BaseLLM):
azure_client_params["azure_ad_token"] = azure_ad_token
azure_client = AzureOpenAI(**azure_client_params)
response = azure_client.chat.completions.create(**data) # type: ignore
response.model = "azure/" + str(response.model)
return convert_to_model_response_object(response_object=json.loads(response.model_dump_json()), model_response_object=model_response)
except AzureOpenAIError as e:
exception_mapping_worked = True
@ -193,6 +194,7 @@ class AzureChatCompletion(BaseLLM):
azure_client_params["azure_ad_token"] = azure_ad_token
azure_client = AsyncAzureOpenAI(**azure_client_params)
response = await azure_client.chat.completions.create(**data)
response.model = "azure" + str(response.model)
return convert_to_model_response_object(response_object=json.loads(response.model_dump_json()), model_response_object=model_response)
except Exception as e:
if isinstance(e,httpx.TimeoutException):
@ -335,7 +337,7 @@ class AzureChatCompletion(BaseLLM):
)
model_response["object"] = "list"
model_response["data"] = output_data
model_response["model"] = model
model_response["model"] = "azure/" + model
model_response["usage"] = embedding_response["usage"]
return model_response
except AzureOpenAIError as e: