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

Merge pull request #4492 from Manouchehri/gemini-context-caching-1

Browse source 
feat(vertex_httpx.py): Support cachedContent.
This commit is contained in:
Krish Dholakia 2024-07-02 14:09:25 -07:00 • committed by GitHub
commit 612af8f5be
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 5 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

5
litellm/llms/vertex_httpx.py
View file

@ -1035,6 +1035,9 @@ class VertexLLM(BaseLLM):
safety_settings: Optional[List[SafetSettingsConfig]] = optional_params.pop( safety_settings: Optional[List[SafetSettingsConfig]] = optional_params.pop(
"safety_settings", None "safety_settings", None
) # type: ignore ) # type: ignore
cached_content: Optional[str] = optional_params.pop(
"cached_content", None
)
generation_config: Optional[GenerationConfig] = GenerationConfig( generation_config: Optional[GenerationConfig] = GenerationConfig(
**optional_params **optional_params
) )
@ -1050,6 +1053,8 @@ class VertexLLM(BaseLLM):
data["safetySettings"] = safety_settings data["safetySettings"] = safety_settings
if generation_config is not None: if generation_config is not None:
data["generationConfig"] = generation_config data["generationConfig"] = generation_config
if cached_content is not None:
data["cachedContent"] = cached_content
headers = { headers = {
"Content-Type": "application/json", "Content-Type": "application/json",