verica-observability 0.1.2

Two-line LLM tracing for Verica: init(token) and your OpenAI/Anthropic calls land as evaluable traces.

verica-observability

Two-line LLM tracing for Verica: your OpenAI/Anthropic calls land as evaluable traces.

Install

pip install verica-observability

Use

import verica

verica.init(token=os.environ["VERICA_TOKEN"])

# Import AFTER init so the client is patched.
from openai import OpenAI

Gemini calls via the google-genai SDK are auto-traced once verica.init() runs (no extra setup).

Serverless

Call verica.flush() (or verica.shutdown()) before the runtime freezes so the span batch is exported.

Options

Option / env var	Default	Notes
token / VERICA_TOKEN	(required)	ingest-scoped API token
capture_content / VERICA_CAPTURE_CONTENT	true	send prompt/response content
conversation_id	(none)	stamps gen_ai.conversation.id
service_name / OTEL_SERVICE_NAME	app	resource service.name
debug / VERICA_DEBUG	false	log export errors

Fail-open by design: if Verica is unreachable or the token is invalid, spans are dropped and your app is never affected. Export errors are silent unless debug is on.