llm4s-docs/org.llm4s/org.llm4s.rag/org.llm4s.rag.evaluation/RAGASLangfuseObserver

RAGASLangfuseObserver

org.llm4s.rag.evaluation.RAGASLangfuseObserver

See theRAGASLangfuseObserver companion object

class RAGASLangfuseObserver(langfuseUrl: String, publicKey: Secret, secretKey: Secret, environment: String, release: String, version: String, batchSender: LangfuseBatchSender)

Observer that logs RAGAS evaluation results to Langfuse.

Integrates with the Langfuse tracing infrastructure in llm4s-observability, which llm4s-rag depends on for it, to log:

Individual metric scores
Composite RAGAS scores
Evaluation details and metadata

Value parameters

environment: Environment name (e.g., "production", "development")
langfuseUrl: The Langfuse API URL
publicKey: Langfuse public key
release: Release version
secretKey: Langfuse secret key
version: API version

Attributes

Example

{
val observer = LangfuseConfigLoader.default().map(RAGASLangfuseObserver.from)
val result = evaluator.evaluate(sample)
for {
 obs        <- observer
 evalResult <- result
} obs.logEvaluation(evalResult)

}

Companion

object

Graph

Supertypes

class Object

trait Matchable

class Any

Members list

Value members

Concrete methods

Log a single evaluation result to Langfuse.

Creates a trace with the evaluation details and scores for each metric.

Value parameters

result: The evaluation result to log
traceId: Optional trace ID to link to an existing trace

Attributes

Log a batch evaluation summary to Langfuse.

Value parameters

summary: The evaluation summary to log

Attributes

In this article

Generated with