Find a file
2023-07-27 20:44:52 -07:00
build/lib/litellm now a py package 2023-07-26 17:36:28 -07:00
dist now a py package 2023-07-26 17:36:28 -07:00
litellm Update main.py 2023-07-27 20:44:52 -07:00
litellm.egg-info now a py package 2023-07-26 17:36:28 -07:00
completion_test.py good shit 2023-07-26 17:31:25 -07:00
embedding_test.py good shit 2023-07-26 17:31:25 -07:00
LICENSE Initial commit 2023-07-26 17:09:52 -07:00
README.md Update README.md 2023-07-26 22:18:50 -07:00
setup.py fix pip install bug 2023-07-26 22:32:31 -07:00

litellm

a simple & light 100 line package to call OpenAI, Azure, Cohere, Anthropic API Endpoints

litellm manages:

  • translating inputs to completion and embedding endpoints
  • guarantees consistent output, text responses will always be available at ['choices'][0]['message']['content']

usage

from litellm import completion

## set ENV variables
os.environ["OPENAI_API_KEY"] = "openai key"
os.environ["COHERE_API_KEY"] = "cohere key"

messages = [{ "content": "Hello, how are you?","role": "user"}]

# openai call
response = completion(model="gpt-3.5-turbo", messages=messages)

# cohere call
response = completion("command-nightly", messages)

# azure openai call
response = completion("chatgpt-test", messages, azure=True)

installation

pip install litellm

why did I build this

  • Need for simplicity: My code started to get extremely complicated managing & translating calls between Azure, OpenAI, Cohere

Support

Contact me at ishaan@berri.ai