How-To Guides

How-to guides are task-oriented recipes that help you accomplish specific goals. Each guide focuses on solving a particular problem and can be completed independently.

🤖 LLM Extensions

• Cache LLM Responses: semantic caching to reduce costs and latency

• Use LangCache as the LLM cache: managed cache service with LangCache

• Manage LLM Message History: persistent chat history with relevancy retrieval

• Route Queries with SemanticRouter: classify intents and route queries

🔍 Querying

• Query and Filter Data: combine tag, numeric, geo, and text filters

• Use Advanced Query Types: hybrid, multi-vector, range, and text queries

• Write SQL Queries for Redis: translate SQL to Redis query syntax

🧮 Embeddings

• Create Embeddings with Vectorizers: OpenAI, Cohere, HuggingFace, and more

• Cache Embeddings: reduce costs by caching embedding vectors

⚡ Optimization

• Rerank Search Results: improve relevance with cross-encoders and rerankers

• Optimize Indexes with SVS-VAMANA: graph-based vector search with compression

💾 Storage

• Choose a Storage Type: Hash vs JSON formats and nested data

• Migrate an Index: use the migrator helper, wizard, plan, apply, and validate workflow

• Migrate an Index: Quantization, Resume, Backup, Wizard: hands-on notebook for vector quantization with crash-safe resume, rollback, and wizard flow

💻 CLI Operations

• Manage Indices with the CLI: create, inspect, and delete indices from your terminal

• Run RedisVL MCP: expose an existing Redis index to MCP clients

Quick Reference

I want to…	Guide
Cache LLM responses	Cache LLM Responses
Use LangCache (managed) for LLM caching	Use LangCache as the LLM cache
Store chat history	Manage LLM Message History
Route queries by intent	Route Queries with SemanticRouter
Filter results by multiple criteria	Query and Filter Data
Use hybrid or multi-vector queries	Use Advanced Query Types
Translate SQL to Redis	Write SQL Queries for Redis
Choose an embedding model	Create Embeddings with Vectorizers
Speed up embedding generation	Cache Embeddings
Improve search accuracy	Rerank Search Results
Optimize index performance	Optimize Indexes with SVS-VAMANA
Decide on storage format	Choose a Storage Type
Manage indices from terminal	Manage Indices with the CLI
Expose an index through MCP	Run RedisVL MCP
Plan and run a supported index migration	Migrate an Index
Quantize vectors with resume, rollback, and the wizard	Migrate an Index: Quantization, Resume, Backup, Wizard