mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00

History

Krish Dholakia 9a9c78e9b7 Update README.md		2023-11-07 12:08:59 -08:00
..
.gitignore	fix(gitmodules): remapping to new proxy	2023-10-12 21:23:53 -07:00
__init__.py	update proxy cli	2023-09-28 16:24:41 -07:00
api_log.json	bump: version 0.8.4 → 0.8.5	2023-10-14 16:43:06 -07:00
config.yaml	refactor(proxy_server.py): print statement showing how to add debug for logs	2023-11-03 17:41:14 -07:00
cost.log	feat(proxy_server): adds create-proxy feature	2023-10-12 18:27:07 -07:00
costs.json	(feat) proxy_server new cost.json on litellm. Track daily cost & num_requests	2023-10-12 11:37:35 -07:00
openapi.json	(feat) add swagger.json for litellm proxy	2023-10-13 20:41:04 -07:00
proxy_cli.py	(fix) proxy server remove bloat	2023-11-06 15:55:18 -08:00
proxy_server.py	(fix) proxy server - print error msg on exceptions	2023-11-06 17:55:33 -08:00
README.md	Update README.md	2023-11-07 12:08:59 -08:00
start.sh	Refactor start script and Dockerfile, switch to bash entrypoint	2023-10-17 22:53:06 +08:00

README.md

litellm-proxy

A local, fast, and lightweight OpenAI-compatible server to call 100+ LLM APIs.

usage

$ pip install litellm

$ litellm --model ollama/codellama 

#INFO: Ollama running on http://0.0.0.0:8000

replace openai base

import openai 

openai.api_base = "http://0.0.0.0:8000"

print(openai.ChatCompletion.create(model="test", messages=[{"role":"user", "content":"Hey!"}]))

See how to call Huggingface,Bedrock,TogetherAI,Anthropic, etc.