LiteLLM Minor Fixes & Improvements (10/16/2024) (#6265)

* fix(caching_handler.py): handle positional arguments in add cache logic

Fixes https://github.com/BerriAI/litellm/issues/6264

* feat(litellm_pre_call_utils.py): allow forwarding openai org id to backend client

https://github.com/BerriAI/litellm/issues/6237

* docs(configs.md): add 'forward_openai_org_id' to docs

* fix(proxy_server.py): return model info if user_model is set

Fixes https://github.com/BerriAI/litellm/issues/6233

* fix(hosted_vllm/chat/transformation.py): don't set tools unless non-none

* fix(openai.py): improve debug log for openai 'str' error

Addresses https://github.com/BerriAI/litellm/issues/6272

* fix(proxy_server.py): fix linting error

* fix(proxy_server.py): fix linting errors

* test: skip WIP test

* docs(openai.md): add docs on passing openai org id from client to openai
This commit is contained in:
Krish Dholakia 2024-10-16 22:16:23 -07:00 committed by GitHub
parent 43878bd2a0
commit 38a9a106d2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 371 additions and 47 deletions

View file

@ -28,7 +28,8 @@ class HostedVLLMChatConfig(OpenAIGPTConfig):
_tools = _remove_additional_properties(_tools)
# remove 'strict' from tools
_tools = _remove_strict_from_schema(_tools)
non_default_params["tools"] = _tools
if _tools is not None:
non_default_params["tools"] = _tools
return super().map_openai_params(
non_default_params, optional_params, model, drop_params
)