🚅 LiteLLM

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

Bug Report · Feature Request

Docs

100+ Supported Models

Demo Video

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

🚨 Seeing errors?

05/10/2023: LiteLLM is adopting Semantic Versioning for all commits. Learn more

Usage

pip install litellm

from litellm import completion
import os

## set ENV variables 
os.environ["OPENAI_API_KEY"] = "your-openai-key" 
os.environ["COHERE_API_KEY"] = "your-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(model="command-nightly", messages=messages)
print(response)

Streaming (Docs)

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'])

Caching (Docs)

LiteLLM supports caching completion() and embedding() calls for all LLMs. Hosted Cache LiteLLM API

import litellm
from litellm.caching import Cache
import os

litellm.cache = Cache()
os.environ['OPENAI_API_KEY'] = ""
# add to cache
response1 = litellm.completion(
    model="gpt-3.5-turbo",
    messages=[{"role": "user", "content": "why is LiteLLM amazing?"}], 
    caching=True
)
# returns cached response
response2 = litellm.completion(
    model="gpt-3.5-turbo", 
    messages=[{"role": "user", "content": "why is LiteLLM amazing?"}], 
    caching=True
)

print(f"response1: {response1}")
print(f"response2: {response2}")

OpenAI Proxy Server (Docs)

Spin up a local server to translate openai api calls to any non-openai model (e.g. Huggingface, TogetherAI, Ollama, etc.)

This works for async + streaming as well.

litellm --model <model_name>

Running your model locally or on a custom endpoint ? Set the --api-base parameter see how

Supported Provider (Docs)

Provider	Completion	Streaming	Async Completion	Async Streaming
openai	✅	✅	✅	✅
cohere	✅	✅	✅	✅
anthropic	✅	✅	✅	✅
replicate	✅	✅	✅	✅
huggingface	✅	✅	✅	✅
together_ai	✅	✅	✅	✅
openrouter	✅	✅	✅	✅
vertex_ai	✅	✅	✅	✅
palm	✅	✅	✅	✅
ai21	✅	✅	✅	✅
baseten	✅	✅	✅	✅
azure	✅	✅	✅	✅
sagemaker	✅	✅	✅	✅
bedrock	✅	✅	✅	✅
vllm	✅	✅	✅	✅
nlp_cloud	✅	✅	✅	✅
aleph alpha	✅	✅	✅	✅
petals	✅	✅	✅	✅
ollama	✅	✅	✅	✅
deepinfra	✅	✅	✅	✅

Read the Docs

Contributing

To contribute: Clone the repo locally -> Make a change -> Submit a PR with the change.

Here's how to modify the repo locally: Step 1: Clone the repo

git clone https://github.com/BerriAI/litellm.git

Step 2: Navigate into the project, and install dependencies:

cd litellm
poetry install

Step 3: Test your change:

cd litellm/tests # pwd: Documents/litellm/litellm/tests
pytest .

Step 4: Submit a PR with your changes! 🚀

• push your fork to your GitHub repo
• submit a PR from there

Learn more on how to make a PR

Support / talk with founders

• Schedule Demo 👋
• Community Discord 💭
• Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
• Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

Why did we build this

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

Contributors