phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

LiteLLM Minor fixes + improvements (08/03/2024) (#5488)

Browse source 
* fix(internal_user_endpoints.py): set budget_reset_at for /user/update

* fix(vertex_and_google_ai_studio_gemini.py): handle accumulated json

Fixes https://github.com/BerriAI/litellm/issues/5479

* fix(vertex_ai_and_gemini.py): fix assistant message function call when content is not None

Fixes https://github.com/BerriAI/litellm/issues/5490

* fix(proxy_server.py): generic state uuid for okta sso

* fix(lago.py): improve debug logs

Debugging for https://github.com/BerriAI/litellm/issues/5477

* docs(bedrock.md): add bedrock cross-region inferencing to docs

* fix(azure.py): return azure response headers on aembedding call

* feat(azure.py): return azure response headers for `/audio/transcription`

* fix(types/utils.py): standardize deepseek / anthropic prompt caching usage information

Closes https://github.com/BerriAI/litellm/issues/5285

* docs(usage.md): add docs on litellm usage object

* test(test_completion.py): mark flaky test
This commit is contained in:
Krish Dholakia 2024-09-03 21:21:34 -07:00 • committed by GitHub
parent 59042511c9
commit be3c7b401e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 736 additions and 81 deletions
Download patch file Download diff file Expand all files Collapse all files

9
litellm/proxy/proxy_server.py
View file

@ -3703,6 +3703,7 @@ async def embeddings(
api_base = hidden_params.get("api_base", None) or ""
response_cost = hidden_params.get("response_cost", None) or ""
litellm_call_id = hidden_params.get("litellm_call_id", None) or ""
additional_headers: dict = hidden_params.get("additional_headers", {}) or {}
fastapi_response.headers.update(
get_custom_headers(
@ -3715,6 +3716,7 @@ async def embeddings(
model_region=getattr(user_api_key_dict, "allowed_model_region", ""),
call_id=litellm_call_id,
request_data=data,
**additional_headers,
)
)
await check_response_size_is_safe(response=response)
@ -4090,6 +4092,7 @@ async def audio_transcriptions(
api_base = hidden_params.get("api_base", None) or ""
response_cost = hidden_params.get("response_cost", None) or ""
litellm_call_id = hidden_params.get("litellm_call_id", None) or ""
additional_headers: dict = hidden_params.get("additional_headers", {}) or {}
fastapi_response.headers.update(
get_custom_headers(
@ -4102,6 +4105,7 @@ async def audio_transcriptions(
model_region=getattr(user_api_key_dict, "allowed_model_region", ""),
call_id=litellm_call_id,
request_data=data,
**additional_headers,
)
)
@ -8019,8 +8023,13 @@ async def google_login(request: Request):
# SSO providers do not allow stateless verification
redirect_params = {}
state = os.getenv("GENERIC_CLIENT_STATE", None)
if state:
redirect_params["state"] = state
elif "okta" in generic_authorization_endpoint:
redirect_params["state"] = (
uuid.uuid4().hex
) # set state param for okta - required
return await generic_sso.get_login_redirect(**redirect_params) # type: ignore
elif ui_username is not None:
# No Google, Microsoft SSO