Skip to main content

Library to easily interface with LLM API providers

Project description

🚅 LiteLLM

Call all LLM APIs using the OpenAI format [Anthropic, Huggingface, Cohere, TogetherAI, Azure, OpenAI, etc.]

PyPI Version Stable Version CircleCI Downloads Y Combinator W23 git commit activity

Open In Colab

100+ Supported Models | Docs | Demo Website

LiteLLM manages

  • Translating inputs to the provider's completion and embedding endpoints
  • Guarantees consistent output, text responses will always be available at ['choices'][0]['message']['content']
  • Exception mapping - common exceptions across providers are mapped to the OpenAI exception types

🤝 Schedule a 1-on-1 Session: Book a 1-on-1 session with Krrish and Ishaan, the founders, to discuss any issues, provide feedback, or explore how we can improve LiteLLM for you.

Usage

Open In Colab
pip install litellm
from litellm import completion
import os
## set ENV variables
os.environ["OPENAI_API_KEY"] = "openai key"
os.environ["COHERE_API_KEY"] = "cohere key"
os.environ["ANTHROPIC_API_KEY"] = "anthropic key"

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

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

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

# anthropic
response = completion(model="claude-2", messages=messages)

Stable version

pip install litellm==0.1.424

Streaming

liteLLM supports streaming the model response back, pass stream=True to get a streaming iterator in response. Streaming is supported for OpenAI, Azure, Anthropic, Huggingface models

response = completion(model="gpt-3.5-turbo", messages=messages, stream=True)
for chunk in response:
    print(chunk['choices'][0]['delta'])

# claude 2
result = completion('claude-2', messages, stream=True)
for chunk in result:
  print(chunk['choices'][0]['delta'])

Support / talk with founders

Why did we build this

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

Contributors

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

litellm-0.1.595.tar.gz (86.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

litellm-0.1.595-py3-none-any.whl (109.7 kB view details)

Uploaded Python 3

File details

Details for the file litellm-0.1.595.tar.gz.

File metadata

  • Download URL: litellm-0.1.595.tar.gz
  • Upload date:
  • Size: 86.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.18

File hashes

Hashes for litellm-0.1.595.tar.gz
Algorithm Hash digest
SHA256 a54d3f212a0da5be930a2422bcac5dbedc9b65ad002b3ba7acbb0e640f3a9ce0
MD5 84a8e969e4483eac121aebcec01400c6
BLAKE2b-256 41cea4f22c309b0bb010ffca59645a3d6ce7c4319bbe9fcb9c15e74343220f4b

See more details on using hashes here.

File details

Details for the file litellm-0.1.595-py3-none-any.whl.

File metadata

  • Download URL: litellm-0.1.595-py3-none-any.whl
  • Upload date:
  • Size: 109.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.18

File hashes

Hashes for litellm-0.1.595-py3-none-any.whl
Algorithm Hash digest
SHA256 2e2a96fbe28262a8c4cabcdbec1e1ccf4f82c5edacdc913cf96133d56901b5be
MD5 ca5a6737479296c127b93be689f24ce5
BLAKE2b-256 9764c06f50bd61d19654404569415b753f181fbedd0764f38615f308e7c9da7e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page