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

Litellm dev 01 10 2025 p3 (#7682)

Browse source 
* feat(langfuse.py): log the used prompt when prompt management used

* test: fix test

* docs(self_serve.md): add doc on restricting personal key creation on ui

* feat(s3.py): support s3 logging with team alias prefixes (if available)

New preview feature

* fix(main.py): remove old if block - simplify to just await if coroutine returned

fixes lm_studio async embedding error

* fix(langfuse.py): handle get prompt check
This commit is contained in:
Krish Dholakia 2025-01-10 21:56:42 -08:00 • committed by GitHub
parent e54d23c919
commit 953c021aa7
11 changed files with 148 additions and 112 deletions
Download patch file Download diff file Expand all files Collapse all files

55
litellm/main.py
View file

@ -3055,52 +3055,17 @@ async def aembedding(*args, **kwargs) -> EmbeddingResponse:
model=model, api_base=kwargs.get("api_base", None)
)
# Await normally
init_response = await loop.run_in_executor(None, func_with_context)
response: Optional[EmbeddingResponse] = None
if (
custom_llm_provider == "openai"
or custom_llm_provider == "azure"
or custom_llm_provider == "xinference"
or custom_llm_provider == "voyage"
or custom_llm_provider == "mistral"
or custom_llm_provider == "custom_openai"
or custom_llm_provider == "triton"
or custom_llm_provider == "anyscale"
or custom_llm_provider == "openrouter"
or custom_llm_provider == "deepinfra"
or custom_llm_provider == "perplexity"
or custom_llm_provider == "groq"
or custom_llm_provider == "nvidia_nim"
or custom_llm_provider == "cerebras"
or custom_llm_provider == "sambanova"
or custom_llm_provider == "ai21_chat"
or custom_llm_provider == "volcengine"
or custom_llm_provider == "deepseek"
or custom_llm_provider == "fireworks_ai"
or custom_llm_provider == "ollama"
or custom_llm_provider == "vertex_ai"
or custom_llm_provider == "gemini"
or custom_llm_provider == "databricks"
or custom_llm_provider == "watsonx"
or custom_llm_provider == "cohere"
or custom_llm_provider == "huggingface"
or custom_llm_provider == "bedrock"
or custom_llm_provider == "azure_ai"
or custom_llm_provider == "together_ai"
or custom_llm_provider == "openai_like"
or custom_llm_provider == "jina_ai"
or custom_llm_provider == "voyage"
): # currently implemented aiohttp calls for just azure and openai, soon all.
# Await normally
init_response = await loop.run_in_executor(None, func_with_context)
if isinstance(init_response, dict):
response = EmbeddingResponse(**init_response)
elif isinstance(init_response, EmbeddingResponse): ## CACHING SCENARIO
response = init_response
elif asyncio.iscoroutine(init_response):
response = await init_response # type: ignore
else:
# Call the synchronous function using run_in_executor
response = await loop.run_in_executor(None, func_with_context)
if isinstance(init_response, dict):
response = EmbeddingResponse(**init_response)
elif isinstance(init_response, EmbeddingResponse): ## CACHING SCENARIO
response = init_response
elif asyncio.iscoroutine(init_response):
response = await init_response # type: ignore
if (
response is not None
and isinstance(response, EmbeddingResponse)