phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

LiteLLM Minor Fixes & Improvements (09/25/2024) (#5893)

Browse source 
* fix(langfuse.py): support new langfuse prompt_chat class init params

* fix(langfuse.py): handle new init values on prompt chat + prompt text templates

fixes error caused during langfuse logging

* docs(openai_compatible.md): clarify `openai/` handles correct routing for `/v1/completions` route

Fixes https://github.com/BerriAI/litellm/issues/5876

* fix(utils.py): handle unmapped gemini model optional param translation

Fixes https://github.com/BerriAI/litellm/issues/5888

* fix(o1_transformation.py): fix o-1 validation, to not raise error if temperature=1

Fixes https://github.com/BerriAI/litellm/issues/5884

* fix(prisma_client.py): refresh iam token

Fixes https://github.com/BerriAI/litellm/issues/5896

* fix: pass drop params where required

* fix(utils.py): pass drop_params correctly

* fix(types/vertex_ai.py): fix generation config

* test(test_max_completion_tokens.py): fix test

* fix(vertex_and_google_ai_studio_gemini.py): fix map openai params
This commit is contained in:
Krish Dholakia 2024-09-26 16:41:44 -07:00 • committed by GitHub
parent 16c0307eab
commit a1d9e96b31
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
22 changed files with 755 additions and 292 deletions
Download patch file Download diff file Expand all files Collapse all files

27
litellm/proxy/utils.py
View file

@ -65,11 +65,13 @@ from litellm.proxy.db.create_views import (
create_missing_views,
should_create_missing_views,
)
from litellm.proxy.db.prisma_client import PrismaWrapper
from litellm.proxy.hooks.cache_control_check import _PROXY_CacheControlCheck
from litellm.proxy.hooks.max_budget_limiter import _PROXY_MaxBudgetLimiter
from litellm.proxy.hooks.parallel_request_limiter import (
_PROXY_MaxParallelRequestsHandler,
)
from litellm.secret_managers.main import str_to_bool
from litellm.types.utils import CallTypes, LoggedLiteLLMParams
if TYPE_CHECKING:
@ -1017,6 +1019,9 @@ class PrismaClient:
)
## init logging object
self.proxy_logging_obj = proxy_logging_obj
self.iam_token_db_auth: Optional[bool] = str_to_bool(
os.getenv("IAM_TOKEN_DB_AUTH")
)
try:
from prisma import Prisma # type: ignore
except Exception as e:
@ -1043,9 +1048,23 @@ class PrismaClient:
from prisma import Prisma # type: ignore
verbose_proxy_logger.debug("Connecting Prisma Client to DB..")
if http_client is not None:
self.db = Prisma(http=http_client)
self.db = PrismaWrapper(
original_prisma=Prisma(http=http_client),
iam_token_db_auth=(
self.iam_token_db_auth
if self.iam_token_db_auth is not None
else False
),
)
else:
self.db = Prisma() # Client to connect to Prisma db
self.db = PrismaWrapper(
original_prisma=Prisma(),
iam_token_db_auth=(
self.iam_token_db_auth
if self.iam_token_db_auth is not None
else False
),
) # Client to connect to Prisma db
verbose_proxy_logger.debug("Success - Connected Prisma Client to DB")
def hash_token(self, token: str):
@ -1141,9 +1160,9 @@ class PrismaClient:
"LiteLLM_VerificationTokenView Created in DB!"
)
else:
should_create_views = await should_create_missing_views(db=self.db)
should_create_views = await should_create_missing_views(db=self.db.db) # type: ignore
if should_create_views:
await create_missing_views(db=self.db)
await create_missing_views(db=self.db) # type: ignore
else:
# don't block execution if these views are missing
# Convert lists to sets for efficient difference calculation