mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 03:04:13 +00:00
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:
parent
c58d542282
commit
7cc12bd5c6
19 changed files with 496 additions and 121 deletions
|
@ -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
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue