Show HN: Litellm – simple library to standardize OpenAI, Cohere, Azure LLM I/O
I built this library because langchain was too bloated and I needed a simple abstraction to call multiple LLM APIs. litellm has two functions - completion(), embedding()
(
17 comments
| on HN
)
Why like this?
Retries w exponential backoff, Caching, Streaming output, Function-calling support
Streaming output and function-calling support is interesting
why would you cache the openai call instead of the endpoint that's receiving the user call?
On a side note - I love how quickly your team is shipping! Do keep it going!