Raphael De Lio

Table of Contents TL;DR:What’s Zero-Shot Classification (and Why It Matters)Integrating a Zero-Shot Classification Model with the Deep Java LibraryDependenciesThe Criteria ClassLoading and using the modelUsing different modelsUsing a model that is not available in the Model ZooLoading a local model …

Table of Contents Here’s the flow:Virtual Threads for Massive ParallelismSpring AI Prompt CallProcessing in BatchesHandling Errors GracefullyProcess Results in BulkFull ImplementationStay curious! TL;DR: You’re building an AI-powered app that needs to send lots of prompts to OpenAI. Instead of sending …

Table of Contents Redis as a Vector DatabaseRedis OM SpringDatasetBuilding the Application0. GitHub Repository1. Add the required dependencies2. Define the Movie entity3. Repository Interface4. Search Service5. Movie Service for Data Loading5. Search Controller6. Application Bootstrap7. Sample RequestsWrapping upMore AI ResourcesStay …

Table of Contents IndexHow It Works1. Define a Time Window2. Track Requests3. Remove Expired Intervals4. Rate Limit CheckHow to Implement It with Redis1. Track Requests by Sub-Interval2. Remove Expired Intervals3. Sum Counts for the Active WindowImplementing it with JedisAdd Jedis …

Table of Contents How It Works1. Define a Time Window2. Track Requests3. Remove Expired Entries4. Rate Limit CheckHow to Implement It with Redis and Java1. Log Each Request (If Allowed)2. Remove Expired Entries3. Count Requests in the Time WindowImplementing it …

Table of Contents How It Works1. Define a Token Refill Rate2. Track Token Consumption3. Refill Tokens4. Rate Limit CheckHow to Implement It with Redis and Java1. Retrieve current token count and last refill time2. Refill tokens if necessary and update …

Table of Contents How It Works1. Define a Window Interval2. Track Requests3. Reset Counter:4. Rate Limit Check:How to Implement It with Redis and Java1. Use the INCR command to increment the counter in Redis each time a request is allowed2. …

Table of Contents Why Redis for Rate Limiting?Popular Rate-Limiting PatternsLeaky BucketToken BucketFixed Window CounterSliding Window LogSliding Window CounterChoosing the Right Tool for the JobUnderstand Your Traffic PatternsAssess the Level of Precision NeededConsider Resource ConstraintsAccount User ExperienceStay curious! This article is …