Lightnews — Scholar-powered news

Ricardo Ferreira @riferrei.com · 4d

📆 When: Oct 13, 2025
📍 Where: Raleigh, NC
🧑🏻‍💻 Register: 2025.allthingsopen.org/register

Register • All Things Open 2025

We’re thrilled you’re registering for All Things Open! We look forward to bringing our community together this fall, October 12-14, in Raleigh, NC USA. Register Now Registration will take place on Eve...

2025.allthingsopen.org

Ricardo Ferreira @riferrei.com · 4d

How many of you have been in a meeting where someone said, "We should use a vector database for this!" and everyone nodded, but you wondered... should we really?

If this is you, then join me on October 13th at the @allthingsopen.bsky.social conference.

1 1 1

Ricardo Ferreira @riferrei.com · 10d

💡 Tech stack:

✅ #java
✅ @langchain4j.dev
✅ #Terraform
✅ @awscloud.bsky.social

2 3

Ricardo Ferreira @riferrei.com · 10d

If you're interested in understanding how I implemented this demo, here is the GitHub repository:

github.com/redis-develo...

GitHub - redis-developer/my-jarvis-alexa-skill: My Jarvis is an Alexa skill that can remember and recall memories from users, providing more contextual answers. It utilizes the Redis Agent Memory Serv...

My Jarvis is an Alexa skill that can remember and recall memories from users, providing more contextual answers. It utilizes the Redis Agent Memory Server as a memory layer to provide instant-like ...

github.com

1 1

Ricardo Ferreira @riferrei.com · 10d

Would you like to see an AI agent implemented as an
@amazonalexa.bsky.social? Check this out:

An Alexa Skill that recalls all memories

YouTube video by Redis

www.youtube.com

1 1

Ricardo Ferreira @riferrei.com · 16d

Developers will understand.

1

Reposted by Ricardo Ferreira

All Things Open @allthingsopen.bsky.social · 26d

We're excited to have Ricardo Ferreira (@riferrei.com), Developer Relations Lead for Redis, presenting "To Vector, or not to Vector, that is the Question" at #AllThingsOpen! 2025.allthingsopen.org/sessions/to-...

1 3

Ricardo Ferreira @riferrei.com · Aug 28

Hey there, Redis is hiring developer advocates 🥑 in London and San Francisco. If that person is you... well... even better!

Reach out if you're interested!

Ricardo Ferreira @riferrei.com · Aug 22

If you're a software engineer seriously looking for ways to improve your coding experience, check out these two extensions.

Ricardo Ferreira @riferrei.com · Aug 21

magine you get to your hotel lobby and see this. Would you believe that person is only having a meeting with their teammates? 😅

#DevRel #DevRelRoadWarrior

1

Ricardo Ferreira @riferrei.com · Aug 19

a bald man is standing in a room with his hands outstretched .

ALT: a bald man is standing in a room with his hands outstretched .

media.tenor.com

Ricardo Ferreira @riferrei.com · Aug 19

📍 The Midway San Francisco, September 4th, 2025

🔗 Registration: events.redis.io/redis-releas...

Redis Released San Francisco

Join us at Redis Released to catch our newest capabilities in Redis for AI, Redis Cloud, and open source. We’re releasing the best (read: fastest) version of Redis yet—with an AI infrastructure that helps you build & scale better agents, chatbots, and more. See how our latest releases are shaping the new AI stack —and why now is the time to start building with it.

events.redis.io

1 1

Ricardo Ferreira @riferrei.com · Aug 19

Come to the Redis Released event in San Francisco. My friends David Patlut and Sallie Gamboa from the education team at Redis created a great workshop that will be offered to attendees for free. You know what else is free? The registration:

1

Ricardo Ferreira @riferrei.com · Aug 19

💡 Do you want to learn how to develop these things with Redis?

1

Ricardo Ferreira @riferrei.com · Aug 19

Another interesting usage of Redis with LLMs is as the memory layer of your agents, so that they can "remember" details from your users within the same thread (a.k.a short-term memory) and between threads (a.k.a long-term memory).

1

Ricardo Ferreira @riferrei.com · Aug 19

One way is using semantic caching with Redis. By storing answered LLM calls in memory and using vector embeddings to find semantically similar queries, you can serve cached answers to users really fast, even if their prompt is not precisely the same as the original question.

1

Ricardo Ferreira @riferrei.com · Aug 19

LLMs' fanciness and increasing intelligence don't change the reality—ultimately, they're just API calls. As such, they suffer from the same problems as API calls, such as throttling, timeouts, and exponential delays. 🔌 ⚡️

➡️ But you can use clever ways to make LLM calls faster.

1

Ricardo Ferreira @riferrei.com · Aug 18

📍 The Midway San Francisco, September 4th

🔗 Registration: events.redis.io/redis-releas...

Redis Released San Francisco

Join us at Redis Released to catch our newest capabilities in Redis for AI, Redis Cloud, and open source. We’re releasing the best (read: fastest) version of Redis yet—with an AI infrastructure that helps you build & scale better agents, chatbots, and more. See how our latest releases are shaping the new AI stack —and why now is the time to start building with it.

events.redis.io

Ricardo Ferreira @riferrei.com · Aug 18

🎤 Great lineup of speakers, including legends of the AI space

⚡️ Get to know what is coming on Redis, the most loved database

1

Ricardo Ferreira @riferrei.com · Aug 18

➡️ Here is why you should come to Redis Released:

🎉 It's a free event. And key, there is a happy hour at the end.

🧠 Free hands-on workshops on building AI agents with memory.

💻 Bring your laptop + your questions to engineers at Redis.

More below the video 🧶 👇🏻 😉

2 1

Ricardo Ferreira @riferrei.com · Aug 15

It is with a heavy heart that I print k1's value 😢

2

Ricardo Ferreira @riferrei.com · Aug 15

"It's almost impossible to create good videos while you're on the road."

➡️ Me: "Hold my beer."

#DevRelLife #DevRelOnTheRoad #Video #VideoSetup

Ricardo Ferreira @riferrei.com · Aug 9

You may have seen the multiple variants of the Jet2 Holiday Meme at this point, right? Well, me too. I've watched so much that I've decided to do something useful with it.

See below how to implement RAG with Redis using this meme 😅

#Redis #RAG #Jet2HolidayMeme #VectorDatabases

Ricardo Ferreira @riferrei.com · Aug 4

This weekend, I wrote a blog post explaining how to design a data system that handles entities with multiple attributes and complex relationships with #Redis #VectorSets. The result? Simpler design, simpler code, simpler maintenance.

➡️ Check it out:

dev.to/redis/design...

Designing Vector Embeddings: A Finding Nemo Journey Through Redis Vector Sets

Introduction Every software engineer has faced this challenge: how do you model complex,...

dev.to

Reposted by Ricardo Ferreira

Guy Royse @guy.dev · Jul 31

Everybody's putting AI in their apps. They're stringing APIs together and sending the results down to the browser. But those APIs are expensive, the round trips are long, and there's a lot of data being exposed.

Maybe there's a better way?

www.youtube.com/watch?v=nBaG...

Run AI in the browser - faster, cheaper, and private

YouTube video by Redis

www.youtube.com

1 2