mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 18:54:30 +00:00
LiteLLM Minor Fixes & Improvements (11/29/2024) (#6965)
* fix(factory.py): ensure tool call converts image url Fixes https://github.com/BerriAI/litellm/issues/6953 * fix(transformation.py): support mp4 + pdf url's for vertex ai Fixes https://github.com/BerriAI/litellm/issues/6936 * fix(http_handler.py): mask gemini api key in error logs Fixes https://github.com/BerriAI/litellm/issues/6963 * docs(prometheus.md): update prometheus FAQs * feat(auth_checks.py): ensure specific model access > wildcard model access if wildcard model is in access group, but specific model is not - deny access * fix(auth_checks.py): handle auth checks for team based model access groups handles scenario where model access group used for wildcard models * fix(internal_user_endpoints.py): support adding guardrails on `/user/update` Fixes https://github.com/BerriAI/litellm/issues/6942 * fix(key_management_endpoints.py): fix prepare_metadata_fields helper * fix: fix tests * build(requirements.txt): bump openai dep version fixes proxies argument * test: fix tests * fix(http_handler.py): fix error message masking * fix(bedrock_guardrails.py): pass in prepped data * test: fix test * test: fix nvidia nim test * fix(http_handler.py): return original response headers * fix: revert maskedhttpstatuserror * test: update tests * test: cleanup test * fix(key_management_endpoints.py): fix metadata field update logic * fix(key_management_endpoints.py): maintain initial order of guardrails in key update * fix(key_management_endpoints.py): handle prepare metadata * fix: fix linting errors * fix: fix linting errors * fix: fix linting errors * fix: fix key management errors * fix(key_management_endpoints.py): update metadata * test: update test * refactor: add more debug statements * test: skip flaky test * test: fix test * fix: fix test * fix: fix update metadata logic * fix: fix test * ci(config.yml): change db url for e2e ui testing
This commit is contained in:
Krish Dholakia
GitHub
parent
bd59f18809
commit
859b47f08b
37 changed files with 1040 additions and 714 deletions
|
|
@ -17,7 +17,7 @@ import secrets
|
|||
import traceback
|
||||
import uuid
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from typing import List, Optional, Tuple
|
||||
from typing import List, Optional, Tuple, cast
|
||||
|
||||
import fastapi
|
||||
from fastapi import APIRouter, Depends, Header, HTTPException, Query, Request, status
|
||||
|
|
@ -394,7 +394,8 @@ async def generate_key_fn( # noqa: PLR0915
|
|||
}
|
||||
)
|
||||
_budget_id = getattr(_budget, "budget_id", None)
|
||||
data_json = data.json() # type: ignore
|
||||
data_json = data.model_dump(exclude_unset=True, exclude_none=True) # type: ignore
|
||||
|
||||
# if we get max_budget passed to /key/generate, then use it as key_max_budget. Since generate_key_helper_fn is used to make new users
|
||||
if "max_budget" in data_json:
|
||||
data_json["key_max_budget"] = data_json.pop("max_budget", None)
|
||||
|
|
@ -452,12 +453,52 @@ async def generate_key_fn( # noqa: PLR0915
|
|||
raise handle_exception_on_proxy(e)
|
||||
|
||||
|
||||
def prepare_metadata_fields(
|
||||
data: BaseModel, non_default_values: dict, existing_metadata: dict
|
||||
) -> dict:
|
||||
"""
|
||||
Check LiteLLM_ManagementEndpoint_MetadataFields (proxy/_types.py) for fields that are allowed to be updated
|
||||
"""
|
||||
|
||||
if "metadata" not in non_default_values: # allow user to set metadata to none
|
||||
non_default_values["metadata"] = existing_metadata.copy()
|
||||
|
||||
casted_metadata = cast(dict, non_default_values["metadata"])
|
||||
|
||||
data_json = data.model_dump(exclude_unset=True, exclude_none=True)
|
||||
|
||||
try:
|
||||
for k, v in data_json.items():
|
||||
if k == "model_tpm_limit" or k == "model_rpm_limit":
|
||||
if k not in casted_metadata or casted_metadata[k] is None:
|
||||
casted_metadata[k] = {}
|
||||
casted_metadata[k].update(v)
|
||||
|
||||
if k == "tags" or k == "guardrails":
|
||||
if k not in casted_metadata or casted_metadata[k] is None:
|
||||
casted_metadata[k] = []
|
||||
seen = set(casted_metadata[k])
|
||||
casted_metadata[k].extend(
|
||||
x for x in v if x not in seen and not seen.add(x) # type: ignore
|
||||
) # prevent duplicates from being added + maintain initial order
|
||||
|
||||
except Exception as e:
|
||||
verbose_proxy_logger.exception(
|
||||
"litellm.proxy.proxy_server.prepare_metadata_fields(): Exception occured - {}".format(
|
||||
str(e)
|
||||
)
|
||||
)
|
||||
|
||||
non_default_values["metadata"] = casted_metadata
|
||||
return non_default_values
|
||||
|
||||
|
||||
def prepare_key_update_data(
|
||||
data: Union[UpdateKeyRequest, RegenerateKeyRequest], existing_key_row
|
||||
):
|
||||
data_json: dict = data.model_dump(exclude_unset=True)
|
||||
data_json.pop("key", None)
|
||||
_metadata_fields = ["model_rpm_limit", "model_tpm_limit", "guardrails"]
|
||||
_metadata_fields = ["model_rpm_limit", "model_tpm_limit", "guardrails", "tags"]
|
||||
non_default_values = {}
|
||||
for k, v in data_json.items():
|
||||
if k in _metadata_fields:
|
||||
|
|
@ -485,27 +526,9 @@ def prepare_key_update_data(
|
|||
|
||||
_metadata = existing_key_row.metadata or {}
|
||||
|
||||
if data.model_tpm_limit:
|
||||
if "model_tpm_limit" not in _metadata:
|
||||
_metadata["model_tpm_limit"] = {}
|
||||
_metadata["model_tpm_limit"].update(data.model_tpm_limit)
|
||||
non_default_values["metadata"] = _metadata
|
||||
|
||||
if data.model_rpm_limit:
|
||||
if "model_rpm_limit" not in _metadata:
|
||||
_metadata["model_rpm_limit"] = {}
|
||||
_metadata["model_rpm_limit"].update(data.model_rpm_limit)
|
||||
non_default_values["metadata"] = _metadata
|
||||
|
||||
if data.tags:
|
||||
if "tags" not in _metadata:
|
||||
_metadata["tags"] = []
|
||||
_metadata["tags"].extend(data.tags)
|
||||
non_default_values["metadata"] = _metadata
|
||||
|
||||
if data.guardrails:
|
||||
_metadata["guardrails"] = data.guardrails
|
||||
non_default_values["metadata"] = _metadata
|
||||
non_default_values = prepare_metadata_fields(
|
||||
data=data, non_default_values=non_default_values, existing_metadata=_metadata
|
||||
)
|
||||
|
||||
return non_default_values
|
||||
|
||||
|
|
@ -930,11 +953,11 @@ async def generate_key_helper_fn( # noqa: PLR0915
|
|||
request_type: Literal[
|
||||
"user", "key"
|
||||
], # identifies if this request is from /user/new or /key/generate
|
||||
duration: Optional[str],
|
||||
models: list,
|
||||
aliases: dict,
|
||||
config: dict,
|
||||
spend: float,
|
||||
duration: Optional[str] = None,
|
||||
models: list = [],
|
||||
aliases: dict = {},
|
||||
config: dict = {},
|
||||
spend: float = 0.0,
|
||||
key_max_budget: Optional[float] = None, # key_max_budget is used to Budget Per key
|
||||
key_budget_duration: Optional[str] = None,
|
||||
budget_id: Optional[float] = None, # budget id <-> LiteLLM_BudgetTable
|
||||
|
|
@ -963,8 +986,8 @@ async def generate_key_helper_fn( # noqa: PLR0915
|
|||
allowed_cache_controls: Optional[list] = [],
|
||||
permissions: Optional[dict] = {},
|
||||
model_max_budget: Optional[dict] = {},
|
||||
model_rpm_limit: Optional[dict] = {},
|
||||
model_tpm_limit: Optional[dict] = {},
|
||||
model_rpm_limit: Optional[dict] = None,
|
||||
model_tpm_limit: Optional[dict] = None,
|
||||
guardrails: Optional[list] = None,
|
||||
teams: Optional[list] = None,
|
||||
organization_id: Optional[str] = None,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue