chunking-strategy
Optimal chunking strategies for RAG systems and document processing pipelines.
- Five strategy levels from fixed-size to advanced methods (late chunking, contextual retrieval), each suited to different document types and complexity
- Includes recursive character chunking with hierarchical separators, structure-aware chunking for Markdown/code/PDFs, and embedding-based semantic chunking with configurable thresholds
- Provides evaluation framework covering retrieval precision, recall, end-to-end accuracy, processing latency, and resource usage
- Best practices emphasize starting simple (512 tokens, 10-20% overlap), testing with representative documents, and iterating based on document characteristics and retrieval performance
Chunking Strategy for RAG Systems
Overview
Provides chunking strategies for RAG systems, vector databases, and document processing. Recommends chunk sizes, overlap percentages, and boundary detection methods; validates semantic coherence; evaluates retrieval metrics.
When to Use
Use when building or optimizing RAG systems, vector search pipelines, document chunking workflows, or performance-tuning existing systems with poor retrieval quality.
Instructions
Choose Chunking Strategy
Select based on document type and use case:
- Fixed-Size Chunking (Level 1)
- Use for simple documents without clear structure
- Start with 512 tokens and 10-20% overlap
More from giuseppe-trisciuoglio/developer-kit
shadcn-ui
Provides complete shadcn/ui component library patterns including installation, configuration, and implementation of accessible React components. Use when setting up shadcn/ui, installing components, building forms with React Hook Form and Zod, customizing themes with Tailwind CSS, or implementing UI patterns like buttons, dialogs, dropdowns, tables, and complex form layouts.
17.1Ktailwind-css-patterns
Provides comprehensive Tailwind CSS utility-first styling patterns including responsive design, layout utilities, flexbox, grid, spacing, typography, colors, and modern CSS best practices. Use when styling React/Vue/Svelte components, building responsive layouts, implementing design systems, or optimizing CSS workflow.
10.9Kunit-test-bean-validation
Provides patterns for unit testing Jakarta Bean Validation (JSR-380), including @Valid, @NotNull, @Min, @Max, @Email constraints with Hibernate Validator. Generates custom validator tests, constraint violation assertions, validation groups, and parameterized validation tests. Validates data integrity logic without Spring context. Use when writing validation tests, bean validation tests, or testing custom constraint validators.
2.0Kreact-patterns
Provides comprehensive React 19 patterns for Server Components, Server Actions, useOptimistic, useActionState, useTransition, concurrent features, Suspense boundaries, and TypeScript integration. Generates executable code patterns, validates security for public endpoints, and optimizes performance with React Compiler or manual memoization. Proactively use when building React 19 applications with Next.js App Router, implementing optimistic UI, or optimizing concurrent rendering.
1.8Ktypescript-docs
Generates comprehensive TypeScript documentation using JSDoc, TypeDoc, and multi-layered documentation patterns for different audiences. Use when creating API documentation, architectural decision records (ADRs), code examples, and framework-specific patterns for NestJS, Express, React, Angular, and Vue.
1.2Knestjs
Provides comprehensive NestJS framework patterns with Drizzle ORM integration for building scalable server-side applications. Generates REST/GraphQL APIs, implements authentication guards, creates database schemas, and sets up microservices. Use when building NestJS applications, setting up APIs, implementing authentication, working with databases, or integrating Drizzle ORM.
1.2K