mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-08 08:08:37 +00:00
ab78459097
Response transformation crashed with TypeError when counting tokens for multimodal (dict-shaped) embedding inputs, since encoding.encode() was called directly on the dict instead of its text parts. Also removed a dead, equally-buggy duplicate of the same loop in _transform_response. Separately, the embeddings guardrail handler silently skipped multimodal dict inputs instead of scanning them, letting prohibited text/image content bypass the configured guardrail. It now extracts and scans the text parts while leaving image parts untouched.
11 lines
307 B
Python
11 lines
307 B
Python
from cache_unit_tests import LLMCachingUnitTests
|
|
from litellm.caching import LiteLLMCacheType
|
|
|
|
|
|
class TestDiskCacheUnitTests(LLMCachingUnitTests):
|
|
def get_cache_type(self) -> LiteLLMCacheType:
|
|
return LiteLLMCacheType.DISK
|
|
|
|
|
|
# if __name__ == "__main__":
|
|
# pytest.main([__file__, "-v", "-s"])
|