> ## Documentation Index
> Fetch the complete documentation index at: https://ragopt.aboneda.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Core Architecture

> Understanding RAGOpt's architecture and optimization workflow

<img src="https://mintcdn.com/grpo/-04D4Zy0ca7um31C/images/RAGOpt.svg?fit=max&auto=format&n=-04D4Zy0ca7um31C&q=85&s=643ae8e989c8cb930407407c07cf288a" alt="RAGOpt Workflow Architecture" width={500} className="rounded-lg mx-auto" data-path="images/RAGOpt.svg" />

## Overview

RAGOpt has three core components working together to optimize your RAG pipeline:

**RAG Pipeline**: Handles data loading, parsing, chunking, indexing, and retrieval. Supports multiple providers for embeddings, LLMs, and vector stores.

**Metric Evaluator**: Measures pipeline performance across quality, speed, cost, and safety dimensions. Acts as the objective function for optimization.

**Bayesian Optimizer**: The brain of RAGOpt. Intelligently searches the configuration space by:

* Loading your search space definition (which parameters to tune)
* Sampling configurations using Sobol sequences or other strategies
* Encoding parameters as PyTorch tensors for numerical optimization
* Using acquisition functions to select promising configurations
* Iteratively converging on optimal settings

## How It Works

### 1. Setup & Storage

Generate evaluation questions from your data, then store them in dual systems:

* **Vector Store**: Semantic similarity search
* **Lexical Store**: Keyword-based retrieval

### 2. Define Your Pipeline

Configure your RAG system via YAML. Use the default LangChain implementation or build custom agentic pipelines.

<Card title="RAG Configuration" icon="gear" href="/rag/overview">
  Learn how to configure your RAG pipeline
</Card>

### 3. Bayesian Optimization

**Why Bayesian Optimization?**\
RAG evaluation is expensive. Unlike grid or random search, Bayesian Optimization builds a probabilistic model to intelligently select which configurations to test next, finding optimal settings with far fewer evaluations.

**Powered by BoTorch**: PyTorch-based optimization with flexible sampling strategies (Sobol, random).

<Card title="Optimization Process" icon="chart-line" href="/optimization/overview">
  Deep dive into the optimization workflow
</Card>

### 4. Comprehensive Metrics

Each iteration evaluates your pipeline across multiple dimensions:

* **Quality**: Context precision/recall, relevancy, faithfulness, correctness (from RAGEval paper & RAGAS)
* **Performance**: Latency and cost per query
* **Safety**: Toxicity and bias detection
* **Ranking**: MRR and NDCG

**Custom metrics**: Add your own evaluation criteria.

<Card title="Metrics System" icon="chart-bar" href="/metrics/overview">
  Explore metrics and create custom evaluations
</Card>

### 5. Get Your Optimized Config

The output is a **YAML file** with the best hyperparameters for your data and use case. Weight metrics based on your priorities—emphasize latency for real-time apps or safety for production.

**Next Steps:**

* [Custom RAG Configuration →](rag/overview)
* [Custom Optimization Workflow →](optimization/overview)
* [Evaluation and Metrics →](metrics/overview)