Skip to main content

Documentation Index

Fetch the complete documentation index at: https://narev.ai/docs/llms.txt

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

Use your production traces as test datasets. Instead of guessing which model works better, test against the prompts your users are actually sending.

​
Prerequisites

  • An active Langfuse account with production traces
  • Langfuse API credentials (Secret Key and Public Key)
  • Production traces in your Langfuse project

​
Setup

  1. Create a new A/B test
  2. Navigate to Setup tab
  3. In the Data Source section select Import from traces
  4. Select Langfuse as provider
  5. Enter your credentials:
    • Project Name: Your Langfuse project identifier
    • Secret Key: Your Langfuse secret key (for example, sk-lf-<token>)
    • Public Key: Your Langfuse public key (for example, pk-lf-<token>)
    • Host: Your Langfuse instance URL (default: https://cloud.langfuse.com)
  6. Select your Date Range (default: last 7 days)
  7. Click Save Project to import traces
Import traces from Langfuse interface

​
Self-hosted support

Narev supports both Langfuse Cloud and self-hosted instances. When connecting your project, update the Host field to your self-hosted Langfuse URL.

​
Common questions

No. Narev reads from your existing Langfuse project without any changes to your instrumentation.
Yes. Narev imports prompts and usage patterns from Langfuse, then lets you test any supported model provider on those same prompts.
No. Narev imports traces to run experiments but doesn’t write back to Langfuse.
Yes. Narev imports all types of Langfuse operations including nested traces, generations, and individual LLM calls.