MeiliSearch VS RedisLess

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

1) your program uses a db to index but the actual search is querying too much data at a time and you need to chop the server side query into smaller/faster queries. you could build your own efficient search with something like https://github.com/meilisearch/meilisearch

Don't know about a progress bar, but here is an open source search engine: https://www.meilisearch.com/

toml [dependencies] milli_v1 = { git = "https://github.com/meilisearch/meilisearch", package = "milli", tag = "v1.1.1" }

RedisLess is an experiment to provide a fast, lightweight, embedded, and scalable in-memory Key/Value store library compatible with the Redis API. This project aims to check the feasibility of the principle listed above, and in a few days of works we succeed to have:

I hope you liked this article, and it gives you the appetite to try out Rust. If you have no idea how to start learning it, I would recommend reading the official free ebook. Then, trying to reimplement some good old academic (or not) algorithms and data structures in Rust. If you want to put your hands into dirty stuff, I can recommend contributing to my project Qovery Engine and RedisLess as well.

Data is not persisted yet - everything lives in memory and synced to different instances via Raft (not implemented yet). So it will be a volatile K/V store at the moment. In the future, it will be possible to plug another [storage](https://github.com/Qovery/RedisLess/tree/main/redisless/storage/src) to support persistence.

The project is super early, but in [my company](https://www.qovery.com) we already plan to use RedisLess for our backend API written in Kotlin. I am interested in getting your feedback, and if you like the project, give it a star :)