phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

feat(caching.py): enable caching on provider-specific optional params

Browse source 
Closes https://github.com/BerriAI/litellm/issues/5049
This commit is contained in:
Krrish Dholakia 2024-08-05 11:18:59 -07:00
parent cd94c3adc1
commit 3c4c78a71f
7 changed files with 172 additions and 74 deletions
Download patch file Download diff file Expand all files Collapse all files

62
litellm/types/utils.py
View file

@ -1052,6 +1052,68 @@ class ResponseFormatChunk(TypedDict, total=False):
response_schema: dict
all_litellm_params = [
"metadata",
"tags",
"acompletion",
"atext_completion",
"text_completion",
"caching",
"mock_response",
"api_key",
"api_version",
"api_base",
"force_timeout",
"logger_fn",
"verbose",
"custom_llm_provider",
"litellm_logging_obj",
"litellm_call_id",
"use_client",
"id",
"fallbacks",
"azure",
"headers",
"model_list",
"num_retries",
"context_window_fallback_dict",
"retry_policy",
"roles",
"final_prompt_value",
"bos_token",
"eos_token",
"request_timeout",
"complete_response",
"self",
"client",
"rpm",
"tpm",
"max_parallel_requests",
"input_cost_per_token",
"output_cost_per_token",
"input_cost_per_second",
"output_cost_per_second",
"hf_model_name",
"model_info",
"proxy_server_request",
"preset_cache_key",
"caching_groups",
"ttl",
"cache",
"no-log",
"base_model",
"stream_timeout",
"supports_system_message",
"region_name",
"allowed_model_region",
"model_config",
"fastest_response",
"cooldown_time",
"cache_key",
"max_retries",
]
class LoggedLiteLLMParams(TypedDict, total=False):
force_timeout: Optional[float]
custom_llm_provider: Optional[str]