phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add pyright to ci/cd + Fix remaining type-checking errors (#6082)

Browse source 
* fix: fix type-checking errors

* fix: fix additional type-checking errors

* fix: additional type-checking error fixes

* fix: fix additional type-checking errors

* fix: additional type-check fixes

* fix: fix all type-checking errors + add pyright to ci/cd

* fix: fix incorrect import

* ci(config.yml): use mypy on ci/cd

* fix: fix type-checking errors in utils.py

* fix: fix all type-checking errors on main.py

* fix: fix mypy linting errors

* fix(anthropic/cost_calculator.py): fix linting errors

* fix: fix mypy linting errors

* fix: fix linting errors
This commit is contained in:
Krish Dholakia 2024-10-05 17:04:00 -04:00 • committed by GitHub
parent f7ce1173f3
commit fac3b2ee42
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
65 changed files with 619 additions and 522 deletions
Download patch file Download diff file Expand all files Collapse all files

36
tests/local_testing/test_prompt_caching.py
View file

@ -10,12 +10,40 @@ 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
@pytest.mark.parametrize(
"model",
[
"anthropic/claude-3-5-sonnet-20240620",
"openai/gpt-4o",
"deepseek/deepseek-chat",
# "openai/gpt-4o",
# "deepseek/deepseek-chat",
],
)
def test_prompt_caching_model(model):
@ -66,9 +94,13 @@ def test_prompt_caching_model(model):
max_tokens=10,
)
_usage_format_tests(response.usage)
print("response=", response)
print("response.usage=", response.usage)
_usage_format_tests(response.usage)
assert "prompt_tokens_details" in response.usage
assert response.usage.prompt_tokens_details.cached_tokens > 0