MeiliSearch VS engine

We needed to introduce a new service for search. As we settled on using meilisearch, we needed a way to sync updates on our models with the records in meilisearch. We could've continued to use callbacks but we needed something better.

Meilisearch

In this case, a good strategy is to use vector search only when the keyword/prefix search returns none or just a small number of results. A good candidate for this is MeiliSearch. It uses custom ranking rules to provide results as fast as the user can type.

With the VertexAI endpoint set up and tested, our next step is to work with LibreChat. LibreChat is an open-source ChatGPT clone that can integrate with various AI models, including the PaLM 2 models via the VertexAI API. It's built using React, MongoDB, and Meilisearch technologies.

Meilisearch seems like it is the best open source option.

https://www.meilisearch.com/

Starting with v1.3, you can use Meilisearch as a vector store. Meilisearch allows you to store vector embeddings alongside your documents conveniently. You will need to create the vector embeddings using your third-party tool of choice (Hugging Face, OpenAI). As we published the first v1.3 release candidate, you can try out vector search today.

I work at Meilisearch, an open-source search engine built in Rust. 🦀

https://www.meilisearch.com/ https://github.com/meilisearch

Qovery: Qovery simplifies the deployment process for Kubernetes by letting you declare your project's structure and dependencies, making it an excellent choice for startups looking to focus on development without worrying about infrastructure.

Enter Qovery - an Internal Developer Platform that can be installed on any Kubernetes cluster to bring a delightful and simplified developer experience. But don't take my word for granted. In this quick step-by-step article, I will show you how to deploy one of my GitHub apps and a Postgres database on my Kubernetes cluster running on GCP. And what's really really cool is that I don't even need to understand how Kubernetes work!

Qovery is a comprehensive PaaS tool that offers a range of features to simplify the deployment and management of applications. With Qovery, you can easily deploy your applications in various cloud environments, eliminating the complexities of infrastructure setup. Its intuitive and developer-friendly interface, Git integration, and automatic scaling capabilities make it a powerful choice for building a custom PaaS. Qovery's seamless integration with popular frameworks and databases further enhances its appeal.

Qovery https://www.qovery.com

I have one of my customers who want to use Qovery to deploy their apps on AWS China. Technically speaking, Qovery runs on Kubernetes and on all the usual AWS regions. But AWS China (Beijing) is a bit different (cf here)

Combining GitLab (CI) with Qovery (CD) sounds what you need.

I am eager to get your feedback on Qovery - an open-source CD platform that helps thousands of developers and DevOps to build and scale on AWS.

Qovery - an open-source platform that makes AWS easier and there is a Terraform provider available