phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

LiteLLM Minor Fixes & Improvements (11/29/2024) (#6965)

Browse source 
* 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 2024-12-01 05:24:11 -08:00 • committed by GitHub
parent bd59f18809
commit 859b47f08b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
37 changed files with 1040 additions and 714 deletions
Download patch file Download diff file Expand all files Collapse all files

102
tests/llm_translation/test_openai_o1.py
View file

@ -2,7 +2,7 @@ import json
import os
import sys
from datetime import datetime
from unittest.mock import AsyncMock
from unittest.mock import AsyncMock, patch, MagicMock
sys.path.insert(
0, os.path.abspath("../..")
@ -18,87 +18,75 @@ from litellm import Choices, Message, ModelResponse
@pytest.mark.asyncio
@pytest.mark.respx
async def test_o1_handle_system_role(respx_mock: MockRouter):
async def test_o1_handle_system_role():
"""
Tests that:
- max_tokens is translated to 'max_completion_tokens'
- role 'system' is translated to 'user'
"""
from openai import AsyncOpenAI
litellm.set_verbose = True
mock_response = ModelResponse(
id="cmpl-mock",
choices=[Choices(message=Message(content="Mocked response", role="assistant"))],
created=int(datetime.now().timestamp()),
model="o1-preview",
)
client = AsyncOpenAI(api_key="fake-api-key")
mock_request = respx_mock.post("https://api.openai.com/v1/chat/completions").mock(
return_value=httpx.Response(200, json=mock_response.dict())
)
with patch.object(
client.chat.completions.with_raw_response, "create"
) as mock_client:
try:
await litellm.acompletion(
model="o1-preview",
max_tokens=10,
messages=[{"role": "system", "content": "Hello!"}],
client=client,
)
except Exception as e:
print(f"Error: {e}")
response = await litellm.acompletion(
model="o1-preview",
max_tokens=10,
messages=[{"role": "system", "content": "Hello!"}],
)
mock_client.assert_called_once()
request_body = mock_client.call_args.kwargs
assert mock_request.called
request_body = json.loads(mock_request.calls[0].request.content)
print("request_body: ", request_body)
print("request_body: ", request_body)
assert request_body == {
"model": "o1-preview",
"max_completion_tokens": 10,
"messages": [{"role": "user", "content": "Hello!"}],
}
print(f"response: {response}")
assert isinstance(response, ModelResponse)
assert request_body["model"] == "o1-preview"
assert request_body["max_completion_tokens"] == 10
assert request_body["messages"] == [{"role": "user", "content": "Hello!"}]
@pytest.mark.asyncio
@pytest.mark.respx
@pytest.mark.parametrize("model", ["gpt-4", "gpt-4-0314", "gpt-4-32k", "o1-preview"])
async def test_o1_max_completion_tokens(respx_mock: MockRouter, model: str):
async def test_o1_max_completion_tokens(model: str):
"""
Tests that:
- max_completion_tokens is passed directly to OpenAI chat completion models
"""
from openai import AsyncOpenAI
litellm.set_verbose = True
mock_response = ModelResponse(
id="cmpl-mock",
choices=[Choices(message=Message(content="Mocked response", role="assistant"))],
created=int(datetime.now().timestamp()),
model=model,
)
client = AsyncOpenAI(api_key="fake-api-key")
mock_request = respx_mock.post("https://api.openai.com/v1/chat/completions").mock(
return_value=httpx.Response(200, json=mock_response.dict())
)
with patch.object(
client.chat.completions.with_raw_response, "create"
) as mock_client:
try:
await litellm.acompletion(
model=model,
max_completion_tokens=10,
messages=[{"role": "user", "content": "Hello!"}],
client=client,
)
except Exception as e:
print(f"Error: {e}")
response = await litellm.acompletion(
model=model,
max_completion_tokens=10,
messages=[{"role": "user", "content": "Hello!"}],
)
mock_client.assert_called_once()
request_body = mock_client.call_args.kwargs
assert mock_request.called
request_body = json.loads(mock_request.calls[0].request.content)
print("request_body: ", request_body)
print("request_body: ", request_body)
assert request_body == {
"model": model,
"max_completion_tokens": 10,
"messages": [{"role": "user", "content": "Hello!"}],
}
print(f"response: {response}")
assert isinstance(response, ModelResponse)
assert request_body["model"] == model
assert request_body["max_completion_tokens"] == 10
assert request_body["messages"] == [{"role": "user", "content": "Hello!"}]
def test_litellm_responses():