Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs-v1.latitude.so/llms.txt

Use this file to discover all available pages before exploring further.

This integration is only available in the Python SDK.

​
Overview

This guide shows you how to integrate Latitude Telemetry into an existing application that uses LiteLLM — a unified interface to call 100+ LLM providers. After completing these steps:
  • Every LiteLLM call (e.g. completion, acompletion) can be captured as a log in Latitude.
  • Logs are grouped under a prompt, identified by a path, inside a Latitude project.
  • You can inspect inputs/outputs, measure latency, and debug LiteLLM-powered features from the Latitude dashboard.
You’ll keep calling LiteLLM exactly as you do today — Telemetry simply observes and enriches those calls.

​
Requirements

Before you start, make sure you have:
  • A Latitude account and API key
  • A Latitude project ID
  • A Python-based project that uses LiteLLM
That’s it — prompts do not need to be created ahead of time.

​
Steps

1

Install requirements

Add the Latitude Telemetry package to your project:
pip install latitude-telemetry
2

Wrap your LiteLLM-powered feature

Initialize Latitude Telemetry and wrap the code that calls LiteLLM using telemetry.capture.You can use the capture method as a decorator (recommended) or as a context manager:
Using decorator (recommended)
import os
import litellm
from latitude_telemetry import Telemetry, Instrumentors, TelemetryOptions

telemetry = Telemetry(
    os.environ["LATITUDE_API_KEY"],
    TelemetryOptions(instrumentors=[Instrumentors.LiteLLM]),
)

@telemetry.capture(
    project_id=123,  # The ID of your project in Latitude
    path="generate-support-reply",  # Add a path to identify this prompt in Latitude
)
def generate_support_reply(input: str) -> str:
    response = litellm.completion(
        model="gpt-4o",  # or "anthropic/claude-3-sonnet", "ollama/llama3", etc.
        messages=[{"role": "user", "content": input}],
    )
    return response.choices[0].message.content
Using context manager
import os
import litellm
from latitude_telemetry import Telemetry, Instrumentors, TelemetryOptions

telemetry = Telemetry(
    os.environ["LATITUDE_API_KEY"],
    TelemetryOptions(instrumentors=[Instrumentors.LiteLLM]),
)

def generate_support_reply(input: str) -> str:
    with telemetry.capture(
        project_id=123,  # The ID of your project in Latitude
        path="generate-support-reply",  # Add a path to identify this prompt in Latitude
    ):
        response = litellm.completion(
            model="gpt-4o",
            messages=[{"role": "user", "content": input}],
        )
        return response.choices[0].message.content
The path:
  • Identifies the prompt in Latitude
  • Can be new or existing
  • Should not contain spaces or special characters (use letters, numbers, - _ / .)

​
Streaming responses

When using streaming (stream=True), use a generator function with the decorator. The SDK keeps the span open until all chunks are yielded: 
@telemetry.capture(project_id=123, path="generate-support-reply")
async def stream_support_reply(input: str):
    response = litellm.completion(
        model="gpt-4o",
        messages=[{"role": "user", "content": input}],
        stream=True,
    )
    for chunk in response:
        if chunk.choices[0].delta.content:
            yield chunk.choices[0].delta.content

​
Seeing your logs in Latitude

Once your feature is wrapped, logs will appear automatically.
  1. Open the prompt in your Latitude dashboard (identified by path)
  2. Go to the Traces section
  3. Each execution will show:
    • Input and output messages
    • Model and token usage
    • Latency and errors
    • One trace per feature invocation
Each LiteLLM call appears as a child span under the captured prompt execution, giving you a full, end-to-end view of what happened.

​
That’s it

No changes to your LiteLLM calls, no special return values, and no extra plumbing — just wrap the feature you want to observe.