Documentation
¶
Overview ¶
Package generate provides answer generation steps for RAG pipelines.
This package contains reusable steps for generating answers:
- Generate: LLM-based answer generation from retrieved chunks
Example usage:
p := pipeline.New[*core.RetrievalContext]()
p.AddSteps(
generate.Generate(generator, logger, metrics),
)
Package generate provides answer generation steps for RAG pipelines.
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func Generate ¶
func Generate( generator core.Generator, logger logging.Logger, metrics core.Metrics, ) pipeline.Step[*core.RetrievalContext]
Generate creates a new generation step with logger and metrics.
func RAGEvaluation ¶
func RAGEvaluation(evaluator core.RAGEvaluator, logger logging.Logger, metrics core.Metrics) pipeline.Step[*core.RetrievalContext]
RAGEvaluation creates a RAG evaluation step with logger and metrics.
Parameters:
- evaluator: RAG evaluator implementation
- logger: structured logger (auto-defaults to NoopLogger if nil)
- metrics: metrics collector (optional, can be nil)
Example:
p.AddStep(generate.RAGEvaluation(evaluator, logger, metrics))
Types ¶
This section is empty.
Source Files
Click to show internal directories.
Click to hide internal directories.