Observability on Qdrant - Vector Database

OpenLLMetry

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

OpenLLMetry

OpenLLMetry from Traceloop is a set of extensions built on top of OpenTelemetry that gives you complete observability over your LLM application.

OpenLLMetry supports instrumenting the qdrant_client Python library and exporting the traces to various observability platforms, as described in their Integrations catalog.

This page assumes you’re using qdrant-client version 1.7.3 or above.

Usage

To set up OpenLLMetry, follow these steps:

Install the SDK:

pip install traceloop-sdk

Instantiate the SDK:

from traceloop.sdk import Traceloop

Traceloop.init()

You’re now tracing your qdrant_client usage with OpenLLMetry!

OpenLIT

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

OpenLIT

OpenLIT is an OpenTelemetry-native LLM Application Observability tool and includes OpenTelemetry auto-instrumentation to monitor Qdrant and provide insights to improve database operations and application performance.

This page assumes you’re using qdrant-client version 1.7.3 or above.

Usage

Step 1: Install OpenLIT

Open your command line or terminal and run:

pip install openlit

Step 2: Initialize OpenLIT in your Application

Integrating OpenLIT into LLM applications is straightforward with just two lines of code:

Datadog

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Datadog is a cloud-based monitoring and analytics platform that offers real-time monitoring of servers, databases, and numerous other tools and services. It provides visibility into the performance of applications and enables businesses to detect issues before they affect users.

You can install the Qdrant integration to get real-time metrics to monitor your Qdrant deployment within Datadog including:

The performance of REST and gRPC interfaces with metrics such as total requests, total failures, and time to serve to identify potential bottlenecks and mitigate them.