forked from phoenix/litellm-mirror
4b9c66ea59
* 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
89 lines
2.6 KiB
Python
89 lines
2.6 KiB
Python
import json
|
|
import os
|
|
import sys
|
|
from datetime import datetime
|
|
from unittest.mock import AsyncMock
|
|
|
|
sys.path.insert(
|
|
0, os.path.abspath("../..")
|
|
) # Adds the parent directory to the system path
|
|
|
|
|
|
import httpx
|
|
import pytest
|
|
from respx import MockRouter
|
|
from unittest.mock import patch, MagicMock, AsyncMock
|
|
|
|
import litellm
|
|
from litellm import Choices, Message, ModelResponse, EmbeddingResponse, Usage
|
|
from litellm import completion
|
|
|
|
|
|
def test_completion_nvidia_nim():
|
|
from openai import OpenAI
|
|
|
|
litellm.set_verbose = True
|
|
model_name = "nvidia_nim/databricks/dbrx-instruct"
|
|
client = OpenAI(
|
|
api_key="fake-api-key",
|
|
)
|
|
|
|
with patch.object(
|
|
client.chat.completions.with_raw_response, "create"
|
|
) as mock_client:
|
|
try:
|
|
completion(
|
|
model=model_name,
|
|
messages=[
|
|
{
|
|
"role": "user",
|
|
"content": "What's the weather like in Boston today in Fahrenheit?",
|
|
}
|
|
],
|
|
presence_penalty=0.5,
|
|
frequency_penalty=0.1,
|
|
client=client,
|
|
)
|
|
except Exception as e:
|
|
print(e)
|
|
# Add any assertions here to check the response
|
|
|
|
mock_client.assert_called_once()
|
|
request_body = mock_client.call_args.kwargs
|
|
|
|
print("request_body: ", request_body)
|
|
|
|
assert request_body["messages"] == [
|
|
{
|
|
"role": "user",
|
|
"content": "What's the weather like in Boston today in Fahrenheit?",
|
|
},
|
|
]
|
|
assert request_body["model"] == "databricks/dbrx-instruct"
|
|
assert request_body["frequency_penalty"] == 0.1
|
|
assert request_body["presence_penalty"] == 0.5
|
|
|
|
|
|
def test_embedding_nvidia_nim():
|
|
litellm.set_verbose = True
|
|
from openai import OpenAI
|
|
|
|
client = OpenAI(
|
|
api_key="fake-api-key",
|
|
)
|
|
with patch.object(client.embeddings.with_raw_response, "create") as mock_client:
|
|
try:
|
|
litellm.embedding(
|
|
model="nvidia_nim/nvidia/nv-embedqa-e5-v5",
|
|
input="What is the meaning of life?",
|
|
input_type="passage",
|
|
client=client,
|
|
)
|
|
except Exception as e:
|
|
print(e)
|
|
mock_client.assert_called_once()
|
|
request_body = mock_client.call_args.kwargs
|
|
print("request_body: ", request_body)
|
|
assert request_body["input"] == "What is the meaning of life?"
|
|
assert request_body["model"] == "nvidia/nv-embedqa-e5-v5"
|
|
assert request_body["extra_body"]["input_type"] == "passage"
|