2023-07-26 17:50:27 -07:00
2023-07-26 17:36:28 -07:00
2023-07-26 17:36:28 -07:00
2023-07-26 17:36:28 -07:00
2023-07-26 17:36:28 -07:00
2023-07-26 17:31:25 -07:00
2023-07-26 17:31:25 -07:00
2023-07-26 17:09:52 -07:00
2023-07-26 17:50:27 -07:00
2023-07-26 17:36:28 -07:00

litellm

a simple, fast, 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

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
S
Description
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
Readme MIT 1.1 GiB
Languages
Python 81%
TypeScript 12.2%
JavaScript 5.9%
HTML 0.5%
HCL 0.2%