forked from phoenix/litellm-mirror
2.4 KiB
2.4 KiB
Getting Started
import QuickStart from '../src/components/QuickStart.js'
LiteLLM simplifies LLM API calls by mapping them all to the OpenAI ChatCompletion format.
basic usage
By default we provide a free $10 key to try all providers supported on LiteLLM.
from litellm import completion
## set ENV variables
os.environ["OPENAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your openai key
os.environ["COHERE_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with 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("command-nightly", messages)
Next Steps 👉 All supported models
More details 👉
streaming
Same example from before. Just pass in stream=True in the completion args.
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, stream=True)
# cohere call
response = completion("command-nightly", messages, stream=True)
print(response)
More details 👉
exception handling
LiteLLM maps exceptions across all supported providers to the OpenAI exceptions. All our exceptions inherit from OpenAI's exception types, so any error-handling you have for that, should work out of the box with LiteLLM.
from openai.errors import OpenAIError
from litellm import completion
os.environ["ANTHROPIC_API_KEY"] = "bad-key"
try:
# some code
completion(model="claude-instant-1", messages=[{"role": "user", "content": "Hey, how's it going?"}])
except OpenAIError as e:
print(e)
More details 👉