Find a file
ishaan-jaff a168cf8b9c add v4
2023-07-29 07:12:19 -07:00
build/lib/litellm Added openrouter.ai support 2023-07-28 11:44:08 +03:00
dist fixed a pip install bug 2023-07-29 06:57:30 -07:00
docs add v4 2023-07-29 07:12:19 -07:00
litellm Added openrouter.ai support 2023-07-28 11:44:08 +03:00
litellm.egg-info fixed a pip install bug 2023-07-29 06:57:30 -07:00
.DS_Store trying to add docs 2023-07-29 07:06:56 -07:00
.env.example Added openrouter.ai support 2023-07-28 11:44:08 +03:00
.gitignore Added openrouter.ai support 2023-07-28 11:44:08 +03:00
.readthedocs.yaml Create .readthedocs.yaml 2023-07-28 18:05:26 -07:00
completion_test.py Uncommented the tests 2023-07-28 19:49:40 +03:00
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 2023-07-28 15:02:51 -07:00
setup.py fixed a pip install bug 2023-07-29 06:57:30 -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

hosted version

why did I build this

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

Support

Contact us at ishaan@berri.ai / krrish@berri.ai