Cookbook: Monitor DeepSeek Models with Langfuse Using the OpenAI SDK

%pip install langfuse openai --upgrade

import os
 
# Get keys for your project from the project settings page: https://cloud.langfuse.com
os.environ["LANGFUSE_PUBLIC_KEY"] = "pk-lf-..." 
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..." 
os.environ["LANGFUSE_HOST"] = "https://cloud.langfuse.com" # 🇪🇺 EU region
# os.environ["LANGFUSE_HOST"] = "https://us.cloud.langfuse.com" # 🇺🇸 US region
 
# Your DeepSeek API key (get it from https://platform.deepseek.com/api_keys)
os.environ["DEEPSEEK_API_KEY"] = "sk-..."  # Replace with your DeepSeek API key

# Instead of: import openai
from langfuse.openai import OpenAI
from langfuse import observe

# Initialize the OpenAI client, pointing it to the DeepSeek Inference API
client = OpenAI(
    base_url="https://api.deepseek.com",  # Replace with the DeepSeek model endpoint URL
    api_key=os.getenv('DEEPSEEK_API_KEY'),  # Replace with your DeepSeek API key
)

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)

AI is cool because it automates tasks, enhances creativity, and solves complex problems quickly—making life smarter and easier.

@observe()  # Decorator to automatically create a trace and nest generations
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 token that got lost on its way to the language model. Answer in 100 words or less."}
        ],
        metadata={"genre": "adventure"},
    )
    return completion.choices[0].message.content
 
story = generate_story()
print(story)

**The Lost Token**  

Timmy the Token was excited—today, he’d help the language model craft a story! But as he raced through the data pipeline, he took a wrong turn, tumbling into a forgotten cache.  

"Hello?" Timmy echoed. Only silence replied.  

Days passed. The model stuttered without him. Then, a cleanup script swept through. "Gotcha!" it chirped, rescuing Timmy.  

Back in the prompt, Timmy gleamed. The model sparked to life: *"Once, a token got lost…"*  

And so, Timmy’s adventure became the very story he was meant to tell.  

(100 words exactly)

from langfuse import get_client
 
langfuse = get_client()
 
# Trace attributes must be set on enclosing span
with langfuse.start_as_current_span(name="math-tutor") as span:
    span.update_trace(
        session_id="session_123",
        user_id="user_456",
        tags=["math"]
    )
 
    result = client.chat.completions.create(
        model="deepseek-chat",
        messages=[
            {"role": "system", "content": "You are a math tutor."},
            {"role": "user", "content": "Help me understand the Pythagorean theorem. Answer in 100 words or less."}
        ],
        name="test-chat",
        metadata={"someMetadataKey": "someValue"},
    )
 
print(result.choices[0].message.content)

The Pythagorean theorem states that in a right-angled triangle, the square of the hypotenuse (the side opposite the right angle) is equal to the sum of the squares of the other two sides. Mathematically, if \( a \) and \( b \) are the legs, and \( c \) is the hypotenuse, then:  

\[ a^2 + b^2 = c^2 \]  

This theorem helps calculate distances, solve geometry problems, and is foundational in trigonometry. For example, if \( a = 3 \) and \( b = 4 \), then \( c = 5 \) because \( 3^2 + 4^2 = 5^2 \).

from langfuse import get_client, observe
langfuse = get_client()
 
@observe()
def technical_explanation():
    # Your main application logic
    response = client.chat.completions.create(
        name="tech-explainer",
        model="deepseek-chat",
        messages=[
            {"role": "user", "content": "Explain how blockchain technology works. Answer in 30 words or less."}
        ],
    ).choices[0].message.content
 
    # Update the current trace with additional information
    langfuse.update_current_trace(
        name="Blockchain Explanation",
        session_id="session_xyz789",
        user_id="user_tech_42",
        tags=["technology", "blockchain"],
        metadata={"topic": "blockchain", "difficulty": "intermediate"},
    )
 
    return response
 
result = technical_explanation()
print(result)

Blockchain is a decentralized digital ledger that records transactions across a network of computers. Each block contains transaction data, linked securely to the previous one, ensuring transparency and immutability. (30 words)

from langfuse import get_client
 
langfuse = get_client()
 
# Trace attributes must be set on enclosing span
with langfuse.start_as_current_span(name="math-tutor") as span:
 
    result = client.chat.completions.create(
        model="deepseek-chat",
        messages=[
            {"role": "system", "content": "You are a math tutor."},
            {"role": "user", "content": "Help me understand the Pythagorean theorem. Answer in 100 words or less."}
        ],
        name="test-chat",
        metadata={"someMetadataKey": "someValue"},
    )
 
    # Score this specific span
    span.score(name="conciseness", value=0.8, data_type="NUMERIC")
 
    # Score the overall trace
    span.score_trace(name="feedback", value="positive", data_type="CATEGORICAL")
 
print(result.choices[0].message.content)

The Pythagorean theorem states that in a right-angled triangle, the square of the hypotenuse (the side opposite the right angle) is equal to the sum of the squares of the other two sides. Mathematically, it’s written as:  

\[ a^2 + b^2 = c^2 \]  

Here, \(a\) and \(b\) are the legs, and \(c\) is the hypotenuse. For example, if \(a = 3\) and \(b = 4\), then \(c = 5\) because \(3^2 + 4^2 = 9 + 16 = 25 = 5^2\). This theorem helps calculate distances and solve geometry problems involving right triangles.