Log requests to your DB to analyze, evaluate, & monitor. Just two lines of code to get started.
Warehouse every model request to your PostgreSQL database. Use logs to analyze, evaluate, and monitor models.
We store a customizable JSON object so you can granularly monitor usage, calculate cost, run evaluations, and fine-tune models.
Sample logs and test features in production. Version models and configuration, and get alerts when you need to take action.
"We experiment with LLM models, settings, and optimizations. Velvet made it easy to implement logging and caching. And we're storing training sets to eventually fine-tune our own models.
"Velvet gives us a source of truth for what's happening between the Revo copilot, and the LLMs it orchestrates. We have the data we need to run evaluations, calculate costs, and quickly resolve issues."
"Our engineers use Velvet daily. It monitors AI features in production, even opaque APIs like batch. The caching feature reduces costs significantly. And, we use the logs to observe, test, and fine-tune."
Log requests to your database. Secure and compliant.
Query data with SQL to analyze usage, cost, and metrics.
Optimize costs and latency with request caching.
Configure evaluations to test your models, settings, and metrics.
Run evals on subsets of logs, or continuous testing in production.
Export datasets for fine-tuning models and other batch workflows.
AI-powered B2B search engine logged 1,500 requests per second.
Use Velvet to identify and export a fine-tuning dataset.
Return results in milliseconds and don't waste calls on identical requests.