Why?
To enhance and improve the OpenLIT experience, we have introduced a telemetry feature that collects anonymous usage data. This data helps us understand how users interact with OpenLIT and identify areas for improvement. We assure you that all collected data is completely anonymous and is used solely for the purpose of enhancing our services.What do we track?
OpenLIT collects anonymous events from both the OpenLIT and the OpenLIT SDK to analyze usage. Events include:- User Interactions: Counts of login attempts, registrations, and page visits.
- Database Configurations: Counts of additions, updates, and action changes.
- Profile Management: Counts of profile updates, whether successful or failed.
- API Key Management: Counts of added API keys and any failures.
- Prompt Operations: Success/failure count on prompt additions and versioning.
- Vault Actions: Counts of secret additions and updates.
- Openground Evaluations: Counts of the success and failure of evaluations.
- SDK Operations: Success/failure count in fetching prompts and vault secrets.
How to disable the collection of usage metrics
Usage metrics collection in OpenLIT is enabled by default, but you can opt-out at any time. To disable usage metrics collection, set theTELEMETRY_ENABLED=false
environment variable when starting OpenLIT.
Where are usage metrics stored?
We use Posthog to securely store and visualize usage metrics, providing essential insights into how OpenLIT is used.Create a dashboard
Create custom visualizations with flexible widgets, queries, and real-time AI monitoring
Manage prompts
Version, deploy, and collaborate on prompts with centralized management and tracking
LLM playground
Compare cost, duration, and response tokens across different LLMs to find the most efficient model
Running in Kubernetes? Try the OpenLIT Operator
Automatically inject instrumentation into existing workloads without modifying pod specs, container images, or application code.