QT/sure

mirror of https://github.com/we-promise/sure.git synced 2026-04-07 14:31:25 +00:00

Files

Juan José Mata f6dde1a098 Add Langfuse-based LLM observability (#86 )

* Add Langfuse-based LLM observability

* Document Langfuse configuration

* Don't hardcode model in use

2025-08-06 23:23:07 +02:00

1.2 KiB

Raw Blame History

Langfuse

This app can send traces of all LLM interactions to Langfuse for debugging and usage analytics. Find them here on GitHub and look at their Open Source statement.

Prerequisites

Create a Langfuse project (self‑hosted or using their cloud offering).
Copy the public key and secret key from the project's settings.

Configuration

Set the following environment variables for the Rails app:

LANGFUSE_PUBLIC_KEY=your_public_key
LANGFUSE_SECRET_KEY=your_secret_key
# Optional if self‑hosting or using a non‑default domain
LANGFUSE_HOST=https://your-langfuse-domain.com

In Docker setups, add the variables to compose.yml and the accompanying .env file.

The initializer reads these values on boot and automatically enables tracing. If the keys are absent, the app runs normally without Langfuse.

What Gets Tracked

chat_response
auto_categorize
auto_detect_merchants

Each call records the prompt, model, response, and token usage when available.

Viewing Traces

After starting the app with the variables set, visit your Langfuse dashboard to see traces and generations grouped under the openai.* traces.

1.2 KiB Raw Blame History Unescape Escape