Navin

How to Configure Langfuse Observability for navin

navin can trace supported OpenAI-compatible provider calls through Langfuse's OpenAI SDK wrapper.

What you will build

  • Langfuse installed in the same Python environment as navin
  • Langfuse environment variables set before startup
  • one traced navin model call

When to use this

Use Langfuse when you need observability for model requests, latency, errors, cost, or prompt behavior during development or production operation.

Install

Install navin and prove the agent works:

python -m pip install navin-ai
navin webui   # configure provider & model in the platform (Settings → Providers)
navin agent -m "Hello!"

Install Langfuse:

python -m pip install langfuse

Minimal working example

Set credentials before starting navin:

export LANGFUSE_SECRET_KEY="sk-lf-..."
export LANGFUSE_PUBLIC_KEY="pk-lf-..."
export LANGFUSE_BASE_URL="https://cloud.langfuse.com"
navin agent -m "Hello!"

PowerShell:

$env:LANGFUSE_SECRET_KEY = "sk-lf-..."
$env:LANGFUSE_PUBLIC_KEY = "pk-lf-..."
$env:LANGFUSE_BASE_URL = "https://cloud.langfuse.com"
navin agent -m "Hello!"

Production notes

  • Langfuse is configured with environment variables, not config.json.
  • Start services from an environment that exports the same variables.
  • Add tracing after the provider works; it should not be the first setup step.
  • Native providers that do not use the OpenAI-compatible client path may not produce Langfuse OpenAI-wrapper traces.

Security notes

  • Treat Langfuse projects as observability stores for sensitive prompts and outputs.
  • Use separate projects for personal, staging, and production traffic.
  • Keep Langfuse keys out of committed service files.

Troubleshooting

  • If no traces appear, confirm the service process sees the environment variables.
  • Confirm the provider path is OpenAI-compatible.
  • Run one local navin agent -m "Hello!" call before debugging service logs.

Related navin docs

Source: content/docs/guides/configure-langfuse-observability.md