Setting up Traceloop Python SDK for Middleware

This guide will walk you through the process of setting up the Traceloop Python SDK to work with Middleware for LLM Observability.

Python

Install and configure Traceloop SDK for Python by following these easy steps to get instant monitoring with Middleware.

1. Install the SDK

Run the following command in your terminal:

pip

pip install traceloop-sdk

2. Initialize the SDK

In your LLM application, initialize the Traceloop tracer:

from traceloop.sdk import Traceloop

Traceloop.init(
    app_name="YOUR_APPLICATION_NAME",
    api_endpoint="https://<MW_UID>.middleware.io:443",
    headers={
        "Authorization": "<MW_API_KEY>",
        "X-Trace-Source": "traceloop",
    },
    resource_attributes={"key": "value"},

Traceloop.init(
    # ... other parameters ...
    disable_batch=True
)

3. Annotate your workflows (Optional)

For complex workflows or chains, you can use Traceloop's decorators to get a better understanding of what's happening:

from traceloop.sdk.decorators import workflow

@workflow(name="suggest_answers")
def suggest_answers(question: str):
    # Your function logic here
    pass

For asynchronous methods, use the @aworkflow decorator.

Viewing Your Traces

After setting up the Traceloop SDK with Middleware, you'll be able to view your LLM application traces in your Middleware LLM Observability Section.

This integration provides instant visibility into everything happening within your LLM, including calls to vector databases or other external services.

For more detailed information on setting up Traceloop with Python, please refer to the Traceloop Python SDK documentation.