mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 02:34:29 +00:00
61b35c12bb
* fix(together_ai/chat): only return response_format + tools for supported models Fixes https://github.com/BerriAI/litellm/issues/6972 * feat(bedrock/rerank): initial working commit for bedrock rerank api support Closes https://github.com/BerriAI/litellm/issues/7021 * feat(bedrock/rerank): async bedrock rerank api support Addresses https://github.com/BerriAI/litellm/issues/7021 * build(model_prices_and_context_window.json): add 'supports_prompt_caching' for bedrock models + cleanup cross-region from model list (duplicate information - lead to inconsistencies ) * docs(json_mode.md): clarify model support for json schema Closes https://github.com/BerriAI/litellm/issues/6998 * fix(_service_logger.py): handle dd callback in list ensure failed spend tracking is logged to datadog * feat(converse_transformation.py): translate from anthropic format to bedrock format Closes https://github.com/BerriAI/litellm/issues/7030 * fix: fix linting errors * test: fix test
46 lines
1.1 KiB
Python
46 lines
1.1 KiB
Python
"""Asserts that prompt caching information is correctly returned for Anthropic, OpenAI, and Deepseek"""
|
|
|
|
import io
|
|
import os
|
|
import sys
|
|
|
|
sys.path.insert(0, os.path.abspath("../.."))
|
|
|
|
import litellm
|
|
import pytest
|
|
|
|
|
|
def _usage_format_tests(usage: litellm.Usage):
|
|
"""
|
|
OpenAI prompt caching
|
|
- prompt_tokens = sum of non-cache hit tokens + cache-hit tokens
|
|
- total_tokens = prompt_tokens + completion_tokens
|
|
|
|
Example
|
|
```
|
|
"usage": {
|
|
"prompt_tokens": 2006,
|
|
"completion_tokens": 300,
|
|
"total_tokens": 2306,
|
|
"prompt_tokens_details": {
|
|
"cached_tokens": 1920
|
|
},
|
|
"completion_tokens_details": {
|
|
"reasoning_tokens": 0
|
|
}
|
|
# ANTHROPIC_ONLY #
|
|
"cache_creation_input_tokens": 0
|
|
}
|
|
```
|
|
"""
|
|
assert usage.total_tokens == usage.prompt_tokens + usage.completion_tokens
|
|
|
|
assert usage.prompt_tokens > usage.prompt_tokens_details.cached_tokens
|
|
|
|
|
|
def test_supports_prompt_caching():
|
|
from litellm.utils import supports_prompt_caching
|
|
|
|
supports_pc = supports_prompt_caching(model="anthropic/claude-3-5-sonnet-20240620")
|
|
|
|
assert supports_pc
|