File Processing

Pattern

Chunk strategy compare

Compare small, large, and paragraph-window chunking on one document with cosine similarity — no vector database.

IntermediateSep 2026View the full pattern on desktop
Chunk strategy compare preview

Problems solved

  • See how chunk size and packing change retrieval on the same document
  • Rank three chunking strategies with AI SDK Core cosineSimilarity
  • Teach chunking as a retrieval hyperparameter without a vector database

Use cases

  • Choosing a chunking strategy for RAG
  • Workshops on embeddings without a vector database
  • Comparing retrieval quality across chunk windows

AI SDK APIs

embedcosineSimilarity

Tags

raglocal-ragchunkingembeddingssimilarity-searchjsonai-sdk

Requirements

Node.js
24+
Memory
256MB
Other
  • Vercel AI Gateway API key

Environment variables

External services

vercel-ai-gatewayupstash

Ready to use?

View the full interactive pattern with live preview and copy the source code.

View the pattern on desktop

Related patterns

Local RAG Chat preview

Local RAG Chat

Load a sample Local RAG index, rank chunks in the browser, and stream a cited answer without a vector database.

raglocal-rag+6
View pattern →
Local RAG Ingest preview

Local RAG Ingest

Chunk local text, create embeddings, and export a portable RAG index without a vector database.

ragretrieval-augmented-generation+5
View pattern →
Local Image Search preview

Local Image Search

Search a portable image index in the browser with caption embeddings — no vector database.

ragembeddings+5
View pattern →
AI Profile Enrichment Form preview

AI Profile Enrichment Form

Analyze user profiles with AI and provide personalized suggestions. Enriches data, suggests improvements, and offers career insights.

aiform+5
View pattern →