LiteLLM Minor Fixes & Improvements (10/18/2024) (#6320)

* fix(converse_transformation.py): handle cross region model name when getting openai param support

Fixes https://github.com/BerriAI/litellm/issues/6291

* LiteLLM Minor Fixes & Improvements (10/17/2024)  (#6293)

* fix(ui_sso.py): fix faulty admin only check

Fixes https://github.com/BerriAI/litellm/issues/6286

* refactor(sso_helper_utils.py): refactor /sso/callback to use helper utils, covered by unit testing

Prevent future regressions

* feat(prompt_factory): support 'ensure_alternating_roles' param

Closes https://github.com/BerriAI/litellm/issues/6257

* fix(proxy/utils.py): add dailytagspend to expected views

* feat(auth_utils.py): support setting regex for clientside auth credentials

Fixes https://github.com/BerriAI/litellm/issues/6203

* build(cookbook): add tutorial for mlflow + langchain + litellm proxy tracing

* feat(argilla.py): add argilla logging integration

Closes https://github.com/BerriAI/litellm/issues/6201

* fix: fix linting errors

* fix: fix ruff error

* test: fix test

* fix: update vertex ai assumption - parts not always guaranteed (#6296)

* docs(configs.md): add argila env var to docs

* docs(user_keys.md): add regex doc for clientside auth params

* docs(argilla.md): add doc on argilla logging

* docs(argilla.md): add sampling rate to argilla calls

* bump: version 1.49.6 → 1.49.7

* add gpt-4o-audio models to model cost map (#6306)

* (code quality) add ruff check PLR0915 for `too-many-statements`  (#6309)

* ruff add PLR0915

* add noqa for PLR0915

* fix noqa

* add # noqa: PLR0915

* # noqa: PLR0915

* # noqa: PLR0915

* # noqa: PLR0915

* add # noqa: PLR0915

* # noqa: PLR0915

* # noqa: PLR0915

* # noqa: PLR0915

* # noqa: PLR0915

* doc fix Turn on / off caching per Key. (#6297)

* (feat) Support `audio`,  `modalities` params (#6304)

* add audio, modalities param

* add test for gpt audio models

* add get_supported_openai_params for GPT audio models

* add supported params for audio

* test_audio_output_from_model

* bump openai to openai==1.52.0

* bump openai on pyproject

* fix audio test

* fix test mock_chat_response

* handle audio for Message

* fix handling audio for OAI compatible API endpoints

* fix linting

* fix mock dbrx test

* (feat) Support audio param in responses streaming (#6312)

* add audio, modalities param

* add test for gpt audio models

* add get_supported_openai_params for GPT audio models

* add supported params for audio

* test_audio_output_from_model

* bump openai to openai==1.52.0

* bump openai on pyproject

* fix audio test

* fix test mock_chat_response

* handle audio for Message

* fix handling audio for OAI compatible API endpoints

* fix linting

* fix mock dbrx test

* add audio to Delta

* handle model_response.choices.delta.audio

* fix linting

* build(model_prices_and_context_window.json): add gpt-4o-audio audio token cost tracking

* refactor(model_prices_and_context_window.json): refactor 'supports_audio' to be 'supports_audio_input' and 'supports_audio_output'

Allows for flag to be used for openai + gemini models (both support audio input)

* feat(cost_calculation.py): support cost calc for audio model

Closes https://github.com/BerriAI/litellm/issues/6302

* feat(utils.py): expose new `supports_audio_input` and `supports_audio_output` functions

Closes https://github.com/BerriAI/litellm/issues/6303

* feat(handle_jwt.py): support single dict list

* fix(cost_calculator.py): fix linting errors

* fix: fix linting error

* fix(cost_calculator): move to using standard openai usage cached tokens value

* test: fix test

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
This commit is contained in:
Krish Dholakia 2024-10-19 22:23:27 -07:00 committed by GitHub
parent c58d542282
commit 7cc12bd5c6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 496 additions and 121 deletions

View file

@ -8,7 +8,7 @@ JWT token must have 'litellm_proxy_admin' in scope.
import json
import os
from typing import Optional
from typing import Optional, cast
from cryptography import x509
from cryptography.hazmat.backends import default_backend
@ -17,7 +17,7 @@ from cryptography.hazmat.primitives import serialization
from litellm._logging import verbose_proxy_logger
from litellm.caching.caching import DualCache
from litellm.llms.custom_httpx.httpx_handler import HTTPHandler
from litellm.proxy._types import LiteLLM_JWTAuth, LiteLLM_UserTable
from litellm.proxy._types import JWKKeyValue, JWTKeyItem, LiteLLM_JWTAuth
from litellm.proxy.utils import PrismaClient
@ -174,7 +174,7 @@ class JWTHandler:
response_json = response.json()
if "keys" in response_json:
keys = response.json()["keys"]
keys: JWKKeyValue = response.json()["keys"]
else:
keys = response_json
@ -186,27 +186,35 @@ class JWTHandler:
else:
keys = cached_keys
public_key: Optional[dict] = None
if len(keys) == 1:
if kid is None or keys["kid"] == kid:
public_key = keys[0]
elif len(keys) > 1:
for key in keys:
if kid is not None and key == kid:
public_key = keys[key]
elif (
kid is not None
and isinstance(key, dict)
and key.get("kid", None) is not None
and key["kid"] == kid
):
public_key = key
public_key = self.parse_keys(keys=keys, kid=kid)
if public_key is None:
raise Exception(
f"No matching public key found. kid={kid}, keys_url={keys_url}, cached_keys={cached_keys}, len(keys)={len(keys)}"
)
return cast(dict, public_key)
def parse_keys(self, keys: JWKKeyValue, kid: Optional[str]) -> Optional[JWTKeyItem]:
public_key: Optional[JWTKeyItem] = None
if len(keys) == 1:
if isinstance(keys, dict) and (keys.get("kid", None) == kid or kid is None):
public_key = keys
elif isinstance(keys, list) and (
keys[0].get("kid", None) == kid or kid is None
):
public_key = keys[0]
elif len(keys) > 1:
for key in keys:
if isinstance(key, dict):
key_kid = key.get("kid", None)
else:
key_kid = None
if (
kid is not None
and isinstance(key, dict)
and key_kid is not None
and key_kid == kid
):
public_key = key
return public_key