Skip to main content
RAGOpt provides an end-to-end framework for optimizing RAG (Retrieval-Augmented Generation) pipelines using Multi-Objective Bayesian Optimization. The framework automatically tunes hyperparameters to find Pareto-optimal configurations that balance multiple objectives like cost, latency, and quality metrics.

​
Framework Architecture

RAGOpt Framework The optimization workflow consists of five key components working together:
  1. Dataset Generation - Create synthetic question-answer pairs from your documents
  2. Search Space - Define the hyperparameter space to explore
  3. BO Input Encoder - Encode the RAG hyperparameter from and to pytorch tensors
  4. Sampler - Sampling choices from search space using SOBOL sampler by default
  5. RAG Manager - Orchestrate component loading and configuration sampling
  6. Evaluation - Measure performance across multiple metrics
  7. Optimization - Find optimal configurations using Bayesian Optimization

​
Quick Start

Here’s a minimal example to get started: 
from rag_opt.dataset import TrainDataset
from rag_opt.optimizer import Optimizer

# Load your dataset
dataset = TrainDataset.from_json("./rag_dataset.json")

# Initialize optimizer with configuration
optimizer = Optimizer(
    train_dataset=dataset,
    config_path="./rag_config.yaml"
)

# Run optimization
best_configs = optimizer.optimize(n_trials=3)