Musterby Elitery
Integrations

DeepSeek

Trace DeepSeek calls in Muster via the OpenAI-compatible API.

The DeepSeek API is OpenAI-compatible. Trace it in Muster by pointing the Muster OpenAI wrapper at the DeepSeek base URL.

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["DEEPSEEK_API_KEY"] = "sk-..."
from langfuse.openai import OpenAI
from langfuse import observe

client = OpenAI(
    base_url="https://api.deepseek.com",
    api_key=os.environ["DEEPSEEK_API_KEY"],
)

Basic chat completion

completion = client.chat.completions.create(
    model="deepseek-chat",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Why is AI cool? Answer in 20 words or less."},
    ],
)
print(completion.choices[0].message.content)

Wrap with @observe()

@observe()
def generate_story():
    completion = client.chat.completions.create(
        name="story-generator",
        model="deepseek-chat",
        messages=[
            {"role": "system", "content": "You are a creative storyteller."},
            {"role": "user", "content": "Tell me a short story about a curious robot."},
        ],
        metadata={"genre": "adventure"},
    )
    return completion.choices[0].message.content

story = generate_story()

See also