Reducing LLM Calls with Vector Search Patterns - Raphael De Lio (Redis)

Large context windows aren't the answer. Learn three vector search patterns to slash your LLM costs and latency.

Reducing LLM Calls with Vector Search Patterns - Raphael De Lio (Redis)
#1about 3 minutes

The hidden costs of large LLM context windows

Large context windows in models like GPT-5 seem to eliminate the need for RAG, but the high token cost makes this approach expensive and unscalable for every request.

#2about 3 minutes

A brief introduction to vectors and vector search

Text is converted into numerical vector embeddings that capture its semantic meaning, allowing computers to efficiently calculate the similarity between different phrases or documents.

#3about 9 minutes

How to classify text using a vector database

Instead of using a costly LLM for every classification task, you can use a vector database to match new text against pre-embedded reference examples for a specific label.

#4about 5 minutes

Using semantic routing for efficient tool calling

By matching user prompts against pre-defined reference phrases for each tool, you can directly trigger the correct function without an initial, expensive LLM call.

#5about 5 minutes

Reducing latency and cost with semantic caching

Semantic caching stores LLM responses and serves them for new, semantically similar prompts, which avoids re-computation and significantly reduces both cost and latency.

#6about 7 minutes

Strategies for optimizing vector search accuracy

Improve the accuracy of vector search patterns through techniques like self-improvement, a hybrid approach that falls back to an LLM, and chunking complex prompts into smaller clauses.

#7about 3 minutes

Addressing advanced challenges in semantic caching

Mitigate common caching pitfalls, like misinterpreting negative prompts, by using specialized embedding models and combining semantic routing with caching to avoid caching certain types of queries.

Related jobs
Jobs that call for the skills explored in this talk.

Matching moments

Reducing latency and cost with semantic caching
05:33 MIN

Reducing latency and cost with semantic caching

WeAreDevelopers LIVE - Vector Similarity Search Patterns for Efficiency and more

Solving LLM limitations with RAG and vector databases
01:48 MIN

Solving LLM limitations with RAG and vector databases

Accelerating GenAI Development: Harnessing Astra DB Vector Store and Langflow for LLM-Powered Apps

Using semantic classification to categorize text
08:44 MIN

Using semantic classification to categorize text

WeAreDevelopers LIVE - Vector Similarity Search Patterns for Efficiency and more

Advanced patterns for building sophisticated AI applications
04:30 MIN

Advanced patterns for building sophisticated AI applications

Java Meets AI: Empowering Spring Developers to Build Intelligent Apps

Implementing semantic routing for tool calling and guardrails
05:09 MIN

Implementing semantic routing for tool calling and guardrails

WeAreDevelopers LIVE - Vector Similarity Search Patterns for Efficiency and more

Exploring the architecture of a RAG system
03:05 MIN

Exploring the architecture of a RAG system

Building Real-Time AI/ML Agents with Distributed Data using Apache Cassandra and Astra DB

Comparing LLM, vector search, and graph RAG approaches
03:45 MIN

Comparing LLM, vector search, and graph RAG approaches

Give Your LLMs a Left Brain

Using caching to serve pre-generated AI responses
03:21 MIN

Using caching to serve pre-generated AI responses

Performant Architecture for a Fast Gen AI User Experience

Featured Partners

Related Videos

See all videos
WeAreDevelopers LIVE - Vector Similarity Search Patterns for Efficiency and more1:05:44

WeAreDevelopers LIVE - Vector Similarity Search Patterns for Efficiency and more

Chris Heilmann, Daniel Cranney, Raphael De Lio & Developer Advocate at Redis

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge42:26

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge

Meta Atamel & Guillaume Laforge

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation21:17

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation

Carl Lapierre

Accelerating GenAI Development: Harnessing Astra DB Vector Store and Langflow for LLM-Powered Apps28:57

Accelerating GenAI Development: Harnessing Astra DB Vector Store and Langflow for LLM-Powered Apps

Dieter Flick & Michel de Ru

Martin O'Hanlon - Make LLMs make sense with GraphRAG24:42

Martin O'Hanlon - Make LLMs make sense with GraphRAG

Martin O'Hanlon

Semantic AI: Why Embeddings Might Matter More Than LLMs26:05

Semantic AI: Why Embeddings Might Matter More Than LLMs

Christian Weyer

Graphs and RAGs Everywhere... But What Are They? - Andreas Kollegger - Neo4j46:51

Graphs and RAGs Everywhere... But What Are They? - Andreas Kollegger - Neo4j

Three years of putting LLMs into Software - Lessons learned26:30

Three years of putting LLMs into Software - Lessons learned

Simon A.T. Jiménez

Related Articles

View all articles
AB
Andrew Brookins, Raphael De Lio
Introducing Redis Agent Memory Server
One of the biggest challenges AI engineers face today is memory management. Large language models are stateless. Every request must carry all the information the model needs to respond well. This is the art of context engineering. Building agents is ...
Introducing Redis Agent Memory Server
DC
Daniel Cranney
Dev Digest 210: AI Agents Are Go! Is MCP Dead? LLMs Crack Anonymity
Inside last week’s Dev Digest 210 . 🪦 Is MCP already dead? 🐍 Secure snake on the CLI 🏗️ The architecture behind open source LLMs ⚖️ AI companies and governments at odds 🦫 Is Go the best language for AI agents? 🕵️ “Security research” bot hacks Micros...
Dev Digest 210: AI Agents Are Go! Is MCP Dead? LLMs Crack Anonymity

From learning to earning

Jobs that call for the skills explored in this talk.