forked from phoenix/litellm-mirror
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
GitHub
parent
c58d542282
commit
7cc12bd5c6
19 changed files with 496 additions and 121 deletions
|
|
@ -84,13 +84,41 @@ def test_bedrock_optional_params_embeddings():
|
|||
],
|
||||
)
|
||||
def test_bedrock_optional_params_completions(model):
|
||||
litellm.drop_params = True
|
||||
tools = [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "structure_output",
|
||||
"description": "Send structured output back to the user",
|
||||
"strict": True,
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"reasoning": {"type": "string"},
|
||||
"sentiment": {"type": "string"},
|
||||
},
|
||||
"required": ["reasoning", "sentiment"],
|
||||
"additionalProperties": False,
|
||||
},
|
||||
"additionalProperties": False,
|
||||
},
|
||||
}
|
||||
]
|
||||
optional_params = get_optional_params(
|
||||
model=model, max_tokens=10, temperature=0.1, custom_llm_provider="bedrock"
|
||||
model=model,
|
||||
max_tokens=10,
|
||||
temperature=0.1,
|
||||
tools=tools,
|
||||
custom_llm_provider="bedrock",
|
||||
)
|
||||
print(f"optional_params: {optional_params}")
|
||||
assert len(optional_params) == 3
|
||||
assert optional_params == {"maxTokens": 10, "stream": False, "temperature": 0.1}
|
||||
assert len(optional_params) == 4
|
||||
assert optional_params == {
|
||||
"maxTokens": 10,
|
||||
"stream": False,
|
||||
"temperature": 0.1,
|
||||
"tools": tools,
|
||||
}
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
|
|
|
|||
File diff suppressed because one or more lines are too long
|
|
@ -993,3 +993,29 @@ async def test_allow_access_by_email(public_jwt_key, user_email, should_work):
|
|||
): # Replace with the actual exception raised on failure
|
||||
resp = await user_api_key_auth(request=request, api_key=bearer_token)
|
||||
print(resp)
|
||||
|
||||
|
||||
def test_get_public_key_from_jwk_url():
|
||||
import litellm
|
||||
from litellm.proxy.auth.handle_jwt import JWTHandler
|
||||
|
||||
jwt_handler = JWTHandler()
|
||||
|
||||
jwk_response = [
|
||||
{
|
||||
"kty": "RSA",
|
||||
"alg": "RS256",
|
||||
"kid": "RaPJB8QVptWHjHcoHkVlUWO4f0D3BtcY6iSDXgGVBgk",
|
||||
"use": "sig",
|
||||
"e": "AQAB",
|
||||
"n": "zgLDu57gLpkzzIkKrTKQVyjK8X40hvu6X_JOeFjmYmI0r3bh7FTOmre5rTEkDOL-1xvQguZAx4hjKmCzBU5Kz84FbsGiqM0ug19df4kwdTS6XOM6YEKUZrbaw4P7xTPsbZj7W2G_kxWNm3Xaxq6UKFdUF7n9snnBKKD6iUA-cE6HfsYmt9OhYZJfy44dbAbuanFmAsWw97SHrPFL3ueh3Ixt19KgpF4iSsXNg3YvoesdFM8psmivgePyyHA8k7pK1Yq7rNQX1Q9nzhvP-F7ocFbP52KYPlaSTu30YwPTVTFKYpDNmHT1fZ7LXZZNLrP_7-NSY76HS2ozSpzjsGVelQ",
|
||||
}
|
||||
]
|
||||
|
||||
public_key = jwt_handler.parse_keys(
|
||||
keys=jwk_response,
|
||||
kid="RaPJB8QVptWHjHcoHkVlUWO4f0D3BtcY6iSDXgGVBgk",
|
||||
)
|
||||
|
||||
assert public_key is not None
|
||||
assert public_key == jwk_response[0]
|
||||
|
|
|
|||
|
|
@ -833,3 +833,17 @@ def test_is_base64_encoded():
|
|||
from litellm.utils import is_base64_encoded
|
||||
|
||||
assert is_base64_encoded(s=base64_image) is True
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"model, expected_bool", [("gpt-3.5-turbo", False), ("gpt-4o-audio-preview", True)]
|
||||
)
|
||||
def test_supports_audio_input(model, expected_bool):
|
||||
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
|
||||
litellm.model_cost = litellm.get_model_cost_map(url="")
|
||||
|
||||
from litellm.utils import supports_audio_input, supports_audio_output
|
||||
|
||||
supports_pc = supports_audio_input(model=model)
|
||||
|
||||
assert supports_pc == expected_bool
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue