Recently langchain4j-memory-store-redis was added to the langchain4j Quarkusio extension. Basically it uses Redis instead of the RAM to keep the chat context during a conversation. But you might think : What could be the use case ? Here is one : Imagine a serverless chatbot pod (so scaling back to 0) but that needs to keep the context ! Also in case it's needed it can scale up and keep track of multiple sessions/contexts You can see in this short screencast that even after that the pod scaled back to 0, it was able to remember my name at the second request. Some cool stuff about this demo (blog will follow) : - I'm using of course Quarkus/langchain4j compiled natively with GraalVM - I'm using the openshift sandbox because it's free and it has the operators I need - It's using my favourite project around the k8s ecosystem : Knative - For the Redis part, I'm using the blazing fast DragonflyDB running on Aiven
Sébastien Blanc’s Post
More Relevant Posts
-
What if your chatbot could scale to 0 but still keep the context of the previous conversations? Check out the video from Sébastien Blanc using Aiven for Dragonfly
Recently langchain4j-memory-store-redis was added to the langchain4j Quarkusio extension. Basically it uses Redis instead of the RAM to keep the chat context during a conversation. But you might think : What could be the use case ? Here is one : Imagine a serverless chatbot pod (so scaling back to 0) but that needs to keep the context ! Also in case it's needed it can scale up and keep track of multiple sessions/contexts You can see in this short screencast that even after that the pod scaled back to 0, it was able to remember my name at the second request. Some cool stuff about this demo (blog will follow) : - I'm using of course Quarkus/langchain4j compiled natively with GraalVM - I'm using the openshift sandbox because it's free and it has the operators I need - It's using my favourite project around the k8s ecosystem : Knative - For the Redis part, I'm using the blazing fast DragonflyDB running on Aiven
To view or add a comment, sign in
-
Stop testing GenAI. Start deploying it with Redis! A new software stack for deploying GenAI. 90% of apps get stuck before they even launch. Our report with MIT Technology Review Insights exposes the blockers and shows you how to move fast. https://lnkd.in/e2Cr8J-i
To view or add a comment, sign in
-
Introducing Aurora Streams: A Rust Library for Efficient Pub/Sub Communication! 🚀 Looking for a reliable and scalable pub/sub messaging solution for your Rust applications? Look no further than Aurora Streams! This new Rust library simplifies real-time communication using Tokio's message passing channels. With Aurora Streams, you can streamline your pub/sub interactions with an intuitive API, keep your applications responsive with non-blocking operations, ensure robust message delivery even in the face of network blips with duplicate message handling, and easily create and organize multiple communication channels. Plus, connect distributed services via Redis for cross-service messaging with optional remote routing (requires event-routing feature). Get started quickly with this code: [dependencies] aurora-streams = "0.1.0" Please use the code with caution. Explore and contribute on GitHub: https://lnkd.in/gm6miz2p Let me know what you think, and I'd love to get your feedback on the library! #rust #pubsub #tokio #redis #opensource
To view or add a comment, sign in
-
I’ve just published a new article that I think will resonate with anyone working in DevOps or interested in authentication systems, called "SSO & RBAC Authentication System Inspired by Norse Cosmology," where I break down how I leveraged API, Keycloak, and Redis to build a secure, scalable SSO system with RBAC. #devops #keycloak #Auth #NodeJs #DockerCompose
SSO-RBAC Authentication System Inspired by Norse Cosmology (Api + Keycloak + Redis)
link.medium.com
To view or add a comment, sign in
-
I have to say, I’m seriously impressed! How you’ve integrated Norse mythology into a technical project like this is creative and effective. It makes the complex topics of authentication and RBAC engaging and accessible. Your implementation of Keycloak and the seamless handling of multi-tenant authentication are top-notch. Huge congratulations on all the hard work and this fantastic write-up! Also, I love how you've leveraged Bearer tokens in your system. It’s a more efficient choice over JWT for scenarios like this because Bearer tokens can be managed centrally through Keycloak, allowing for better control over revocation and session handling. With JWTs, the lack of built-in revocation often leads to security challenges once tokens are issued, so this approach adds an extra layer of security and flexibility. Well done!
Senior DevOps Engineer at 3Pillar Global | AWS, GitHub, Terraform Associate Certified, Cloud Native, Kubernetes
I’ve just published a new article that I think will resonate with anyone working in DevOps or interested in authentication systems, called "SSO & RBAC Authentication System Inspired by Norse Cosmology," where I break down how I leveraged API, Keycloak, and Redis to build a secure, scalable SSO system with RBAC. #devops #keycloak #Auth #NodeJs #DockerCompose
SSO-RBAC Authentication System Inspired by Norse Cosmology (Api + Keycloak + Redis)
link.medium.com
To view or add a comment, sign in
-
Sync Tables in All Three Formats(Hudi|Delta|Iceberg) with XTable and AWS Lambda: Automate, Schedule, or Trigger On-Demand Blog with steps https://lnkd.in/eiVPzAR6 Gh Repo https://lnkd.in/eVa7dXtc Apache XTable (Incubating)
To view or add a comment, sign in
-
With all of the industry buzz around GraphQL and Federation, I thought it was only appropriate to share what sparked this idea. If you're new to GraphQL or Federation, this is a fantastic read. If you're a seasoned vet, it's always good to have a refresher. It's amazing how this still holds true now just as well as the day it was published. #GraphQL #API #Federation
Principled GraphQL
principledgraphql.com
To view or add a comment, sign in
-
🚀 Get rid of the Redis-cli headaches! Connect seamlessly to your Redis instance, even without a shell in your image, using mirrord https://lnkd.in/d62bC8ic #mirrord #k8s
Local Development With Mirrord
linuxblog.xyz
To view or add a comment, sign in
-
Check out my blog post https://wix.to/sQ6n2hq #newblogpost quick and fun demo to learn how to use identity federation using Google and AWS cognito
Serverless app with identity federation
ptera21c.wixsite.com
To view or add a comment, sign in
-
🚀 **Optimize your Go code with atomic.LoadInt32!** Efficient synchronization is key, especially when `i > t`. In such cases, reset `i = 0`, update `n.procstatus`, and let `runtime.Gosched()` do its magic for smoother scheduling. Keep it simple, scalable, and powerful with Go! 💻 Power up your development with Go! Simple, fast, and built for scalability. 👉 Social Accounts @ Redis Solution → [Redissolution.com](http://redissolution.com) 📧 info@Redissolution.com #GoLang #AtomicOperations #GoDevelopment #Concurrency #RedisSolution #CodingWithGo #SoftwareDevelopment #Scalability
To view or add a comment, sign in
Technology Specialist | Solutions Architect | Technical Leader
7moAn infinispan memory store would be great!