mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 10:44:24 +00:00
78879c68a9
* test: initial commit fixing gemini logprobs Fixes https://github.com/BerriAI/litellm/issues/9888 * fix(vertex_and_google_ai_studio.py): Revert avglogprobs change Fixes https://github.com/BerriAI/litellm/issues/8890 * build(model_prices_and_context_window.json): add gpt-4o-realtime-preview cost to model cost map Fixes https://github.com/BerriAI/litellm/issues/9814 * test: add cost calculation unit testing * test: fix test * test: update test
87 lines
2.9 KiB
Python
87 lines
2.9 KiB
Python
import os
|
|
import sys
|
|
|
|
import pytest
|
|
|
|
sys.path.insert(
|
|
0, os.path.abspath("../..")
|
|
) # Adds the parent directory to the system paths
|
|
|
|
from base_llm_unit_tests import BaseLLMChatTest
|
|
from litellm.llms.vertex_ai.context_caching.transformation import (
|
|
separate_cached_messages,
|
|
)
|
|
import litellm
|
|
from litellm import completion
|
|
|
|
class TestGoogleAIStudioGemini(BaseLLMChatTest):
|
|
def get_base_completion_call_args(self) -> dict:
|
|
return {"model": "gemini/gemini-2.0-flash"}
|
|
|
|
def test_tool_call_no_arguments(self, tool_call_no_arguments):
|
|
"""Test that tool calls with no arguments is translated correctly. Relevant issue: https://github.com/BerriAI/litellm/issues/6833"""
|
|
from litellm.litellm_core_utils.prompt_templates.factory import (
|
|
convert_to_gemini_tool_call_invoke,
|
|
)
|
|
|
|
result = convert_to_gemini_tool_call_invoke(tool_call_no_arguments)
|
|
print(result)
|
|
|
|
|
|
def test_gemini_context_caching_separate_messages():
|
|
messages = [
|
|
# System Message
|
|
{
|
|
"role": "system",
|
|
"content": [
|
|
{
|
|
"type": "text",
|
|
"text": "Here is the full text of a complex legal agreement" * 400,
|
|
"cache_control": {"type": "ephemeral"},
|
|
}
|
|
],
|
|
},
|
|
# marked for caching with the cache_control parameter, so that this checkpoint can read from the previous cache.
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{
|
|
"type": "text",
|
|
"text": "What are the key terms and conditions in this agreement?",
|
|
"cache_control": {"type": "ephemeral"},
|
|
}
|
|
],
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "Certainly! the key terms and conditions are the following: the contract is 1 year long for $10/mo",
|
|
},
|
|
# The final turn is marked with cache-control, for continuing in followups.
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{
|
|
"type": "text",
|
|
"text": "What are the key terms and conditions in this agreement?",
|
|
"cache_control": {"type": "ephemeral"},
|
|
}
|
|
],
|
|
},
|
|
]
|
|
cached_messages, non_cached_messages = separate_cached_messages(messages)
|
|
print(cached_messages)
|
|
print(non_cached_messages)
|
|
assert len(cached_messages) > 0, "Cached messages should be present"
|
|
assert len(non_cached_messages) > 0, "Non-cached messages should be present"
|
|
|
|
|
|
def test_gemini_image_generation():
|
|
# litellm._turn_on_debug()
|
|
response = completion(
|
|
model="gemini/gemini-2.0-flash-exp-image-generation",
|
|
messages=[{"role": "user", "content": "Generate an image of a cat"}],
|
|
modalities=["image", "text"],
|
|
)
|
|
assert response.choices[0].message.content is not None
|
|
|
|
|