File Processing
Pattern
Local RAG Chat
Load a sample Local RAG index, rank chunks in the browser, and stream a cited answer without a vector database.
IntermediateAug 2026View the full pattern on desktop
Problems solved
- Import a portable embedding index and chat over it in the browser
- Rank local vectors with AI SDK Core cosineSimilarity
- Stream cited answers from bounded selected text without a vector database
Use cases
- Query a portable documentation index without a database
- Local RAG demos and workshops
- Cited chat over an exported embedding JSON file
AI SDK APIs
embedcosineSimilaritystreamTextsafeValidateUIMessagesconvertToModelMessagescreateUIMessageStreamtoUIMessageStreamcreateUIMessageStreamResponsegateway
Tags
raglocal-ragchat-with-documentssimilarity-searchcitationsembeddingsjsonai-sdk
Requirements
- Node.js
- 24+
- Memory
- 256MB
- Other
- Vercel AI Gateway API key
- A completed local-rag-ingest JSON export
Environment variables
AI_GATEWAY_API_KEYGet key
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
