Integrate Langfuse with LlamaIndex

This notebook provides a step-by-step guide on integrating Langfuse with LlamaIndex to achieve observability and debugging for your LLM applications.

What is LlamaIndex? LlamaIndex (GitHub) is an advanced “data framework” tailored for augmenting LLMs with private data. It streamlines the integration of diverse data sources and formats (APIs, PDFs, docs, SQL, etc.) through versatile data connectors and structures data into indices and graphs for LLM compatibility. The platform offers a sophisticated retrieval/query interface for enriching LLM inputs with context-specific outputs.

What is Langfuse? Langfuse is a an open-source LLM engineering platform. It offers tracing and monitoring capabilities for AI applications. Langfuse helps developers debug, analyze, and optimize their AI systems by providing detailed insights and integrating with a wide array of tools and frameworks through native integrations, OpenTelemetry, and dedicated SDKs.

Getting Started

Let’s walk through a practical example of using LlamaIndex and integrating it with Langfuse for comprehensive tracing.

%pip install langfuse openinference-instrumentation-llama-index llama-index-llms-openai llama-index -U
 

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 OpenAI key
os.environ["OPENAI_API_KEY"] = "sk-proj-..."
 

from langfuse import get_client
 
langfuse = get_client()
 
# Verify connection
if langfuse.auth_check():
    print("Langfuse client is authenticated and ready!")
else:
    print("Authentication failed. Please check your credentials and host.")
 

from openinference.instrumentation.llama_index import LlamaIndexInstrumentor
 
# Initialize LlamaIndex instrumentation
LlamaIndexInstrumentor().instrument()

from llama_index.llms.openai import OpenAI
 
llm = OpenAI(model="gpt-4o")
 
with langfuse.start_as_current_span(name="llama-index-trace"):
    response = llm.complete("Hello, world!")
    print(response)
 
langfuse.flush()

Add Additional Attributes

Langfuse allows you to pass additional attributes to your spans. These can include user_id, tags, session_id, and custom metadata. Enriching traces with these details is important for analysis, debugging, and monitoring of your application’s behavior across different users or sessions.

The following code demonstrates how to start a custom span with langfuse.start_as_current_span and then update the trace associated with this span using span.update_trace().

→ Learn more about Updating Trace and Span Attributes.

with langfuse.start_as_current_span(
    name="llama-index-trace",
    ) as span:
    
    # Run your application here
    question = "What is Langfuse?"
    response = llm.complete(question)
    print(response)
 
    # Pass additional attributes to the span
    span.update_trace(
        input=question,
        output=response.text,
        user_id="user_123",
        session_id="session_abc",
        tags=["rag", "llama-index"],
        metadata={"email": "[email protected]"},
        version="1.0.0"
        )
 
# Flush events in short-lived applications
langfuse.flush()
 

Score Traces and Spans

Langfuse lets you ingest custom scores for individual spans or entire traces. This scoring workflow enables you to implement custom quality checks at runtime or facilitate human-in-the-loop evaluation processes.

In the example below, we demonstrate how to score a specific span for relevance (a numeric score) and the overall trace for feedback (a categorical score). This helps in systematically assessing and improving your application.

→ Learn more about Custom Scores in Langfuse.

with langfuse.start_as_current_span(
    name="llama-index-trace",
    ) as span:
    
    # Run your application here
    question = "What is Langfuse?"
    response = llm.complete(question)
    print(response)
    
    # Score this specific span
    span.score(name="relevance", value=0.9, data_type="NUMERIC")
 
    # Score the overall trace
    span.score_trace(name="feedback", value="positive", data_type="CATEGORICAL")
 
# Flush events in short-lived applications
langfuse.flush()
 

Manage Prompts with Langfuse

Langfuse Prompt Management allows you to collaboratively create, version, and deploy prompts. You can manage prompts either through the Langfuse SDK or directly within the Langfuse UI. These managed prompts can then be fetched into your application at runtime.

The code below illustrates fetching a prompt named answer-question from Langfuse, compiling it with an input variable (country), and then using this compiled prompt in the application.

→ Get started with Langfuse Prompt Management.

# Fetch the prompt from langfuse
langfuse_prompt = langfuse.get_prompt(name="answer-question")
 
# Compile the prompt with the input
compiled_prompt = langfuse_prompt.compile(country = "France")
 
# Run your application
with langfuse.start_as_current_span(
    name="llama-index-trace",
    ) as span:
    
    # Run your application here
    response = llm.complete(compiled_prompt)
    print(response)
 
# Flush events in short-lived applications
langfuse.flush()
 

Dataset Experiments

Offline evaluation using datasets is a critical part of the LLM development lifecycle. Langfuse supports this through Dataset Experiments. The typical workflow involves:

1. Benchmark Dataset: Defining a dataset with input prompts and their corresponding expected outputs.
2. Application Run: Running your LLM application against each item in the dataset.
3. Evaluation: Comparing the generated outputs against the expected results or using other scoring mechanisms (e.g., model-based evaluation) to assess performance.

The following example demonstrates how to use a pre-existing dataset containing countries and their capitals to run an experiment.

→ Learn more about Langfuse Dataset Experiments.

from langfuse import get_client
 
langfuse = get_client()
 
# Fetch an existing dataset
dataset = langfuse.get_dataset(name="capital_cities_11")
for item in dataset.items:
    print(f"Input: {item.input['country']}, Expected Output: {item.expected_output}")
 

Next, we iterate through each item in the dataset, run our LlamaIndex application (your_application) with the item’s input, and log the results as a run associated with that dataset item in Langfuse. This allows for structured evaluation and comparison of different application versions or prompt configurations.

The item.run() context manager is used to create a new trace for each dataset item processed in the experiment. Optionally you can score the dataset runs.

from langfuse import get_client
 
langfuse = get_client()
dataset_name = "capital_cities_11"
current_run_name = "capital_cities_run-llama-index_01" # Identifies this specific evaluation run
current_run_metadata={"model_provider": "OpenAI", "temperature_setting": 0.7}
current_run_description="Evaluation run for Q&A model on June 4th"
 
# Assume 'your_application' is your instrumented application function
def your_application(question):
    with langfuse.start_as_current_span(name="llama-index-trace") as span:
 
        response = llm.complete(question)
        print(response)
 
        # Update the trace with the input and output
        span.update_trace(
            input=question,
            output=response.text,
        )
 
        return response.text
 
dataset = langfuse.get_dataset(name=dataset_name) # Fetch your pre-populated dataset
 
for item in dataset.items:
    print(f"Running evaluation for item: {item.id} (Input: {item.input['country']})")
 
    # Use the item.run() context manager
    with item.run(
        run_name=current_run_name,
        run_metadata=current_run_metadata,
        run_description=current_run_description
    ) as root_span: 
        # All subsequent langfuse operations within this block are part of this trace.
        generated_answer = your_application(
            question="What is the capital of " + item.input["country"] + "? Just answer with the name of the city.",
        )
 
        # Optionally, score the result against the expected output
        if item.expected_output and generated_answer == item.expected_output:
            root_span.score_trace(name="exact_match", value=1.0)
        else:
            root_span.score_trace(name="exact_match", value=0.0)
 
print(f"\nFinished processing dataset '{dataset_name}' for run '{current_run_name}'.")
 

Explore More Langfuse Features

Langfuse offers more features to enhance your LLM development and observability workflow:

• LLM-as-a-Judge Evaluators
• Custom Dashboards
• LLM Playground
• Prompt Management
• Prompt Experiments
• More Integrations