Integrations

Cerebras

Trace Cerebras Inference calls in Muster via the OpenAI-compatible API.

Cerebras Inference serves Llama 3 and other open-weights models on its custom wafer-scale hardware via an OpenAI-compatible endpoint.

Setup

%pip install langfuse openai --upgrade

import os

os.environ["LANGFUSE_PUBLIC_KEY"] = "pk-lf-..."
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..."
os.environ["LANGFUSE_BASE_URL"] = "https://app.getmuster.io"
os.environ["CEREBRAS_API_KEY"] = "..."

from langfuse.openai import OpenAI

client = OpenAI(
    base_url="https://api.cerebras.ai/v1",
    api_key=os.environ["CEREBRAS_API_KEY"],
)

response = client.chat.completions.create(
    model="llama3.1-8b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Cerebras

Setup

See also

On this page