Call all LLM APIs using the OpenAI format [Bedrock, Huggingface, Cohere, TogetherAI, Azure, OpenAI, etc.]
LiteLLM manages
- Translating inputs to the provider's
completion
andembedding
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.
- Load-balance across multiple deployments (e.g. Azure/OpenAI) -
Router
Usage (Docs)
Important
LiteLLM v1.0.0 is now requires openai>=1.0.0
. Migration guide here
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 all models (Bedrock, Huggingface, TogetherAI, Azure, OpenAI, etc.)
from litellm import completion
response = completion(model="gpt-3.5-turbo", messages=messages, stream=True)
for part in response:
print(part.choices[0].delta.content or "")
# claude 2
response = completion('claude-2', messages, stream=True)
for part in response:
print(part.choices[0].delta.content or "")
Router - load balancing(Docs)
LiteLLM allows you to load balance between multiple deployments (Azure, OpenAI). It picks the deployment which is below rate-limit and has the least amount of tokens used.
from litellm import Router
model_list = [{ # list of model deployments
"model_name": "gpt-3.5-turbo", # model alias
"litellm_params": { # params for litellm completion/embedding call
"model": "azure/chatgpt-v-2", # actual model name
"api_key": os.getenv("AZURE_API_KEY"),
"api_version": os.getenv("AZURE_API_VERSION"),
"api_base": os.getenv("AZURE_API_BASE")
}
}, {
"model_name": "gpt-3.5-turbo",
"litellm_params": { # params for litellm completion/embedding call
"model": "azure/chatgpt-functioncalling",
"api_key": os.getenv("AZURE_API_KEY"),
"api_version": os.getenv("AZURE_API_VERSION"),
"api_base": os.getenv("AZURE_API_BASE")
}
}, {
"model_name": "gpt-3.5-turbo",
"litellm_params": { # params for litellm completion/embedding call
"model": "gpt-3.5-turbo",
"api_key": os.getenv("OPENAI_API_KEY"),
}
}]
router = Router(model_list=model_list)
# openai.ChatCompletion.create replacement
response = router.completion(model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hey, how's it going?"}])
print(response)
OpenAI Proxy - (Docs)
If you want to use non-openai models in an openai code base, you can use litellm proxy. Create a server to call 100+ LLMs (Huggingface/Bedrock/TogetherAI/etc) in the OpenAI ChatCompletions & Completions format
$ litellm --model huggingface/bigcode/starcoder
#INFO: Proxy running on http:https://0.0.0.0:8000
import openai # openai v1.0.0+
client = openai.OpenAI(api_key="anything",base_url="http:https://0.0.0.0:8000") # set proxy to base_url
# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
{
"role": "user",
"content": "this is a test request, write a short poem"
}
])
print(response)
Logging Observability (Docs)
LiteLLM exposes pre defined callbacks to send data to Langfuse, LLMonitor, Helicone, Promptlayer, Traceloop, Slack
from litellm import completion
## set env variables for logging tools
os.environ["LANGFUSE_PUBLIC_KEY"] = ""
os.environ["LANGFUSE_SECRET_KEY"] = ""
os.environ["LLMONITOR_APP_ID"] = "your-llmonitor-app-id"
os.environ["OPENAI_API_KEY"]
# set callbacks
litellm.success_callback = ["langfuse", "llmonitor"] # log input/output to langfuse, llmonitor, supabase
#openai call
response = completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hi π - i'm openai"}])
Supported Provider (Docs)
Provider | Completion | Streaming | Async Completion | Async Streaming |
---|---|---|---|---|
openai | β | β | β | β |
azure | β | β | β | β |
aws - sagemaker | β | β | β | β |
aws - bedrock | β | β | β | β |
cohere | β | β | β | β |
anthropic | β | β | β | β |
huggingface | β | β | β | β |
replicate | β | β | β | β |
together_ai | β | β | β | β |
openrouter | β | β | β | β |
google - vertex_ai | β | β | β | β |
google - palm | β | β | β | β |
ai21 | β | β | β | β |
baseten | β | β | β | β |
vllm | β | β | β | β |
nlp_cloud | β | β | β | β |
aleph alpha | β | β | β | β |
petals | β | β | β | β |
ollama | β | β | β | β |
deepinfra | β | β | β | β |
perplexity-ai | β | β | β | β |
anyscale | β | β | β | β |
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! π
- push your fork to your GitHub repo
- submit a PR from there
- Schedule Demo π
- Community Discord π
- Our numbers π +1 (770) 8783-106 / β+1 (412) 618-6238β¬
- Our emails βοΈ [email protected] / [email protected]
- Need for simplicity: Our code started to get extremely complicated managing & translating calls between Azure, OpenAI and Cohere.