spark-ai VS jina

We've just released our product's latest version, making it easier for teams to build data pipelines for LLM-based applications. As part of the release, we're also open-sourcing the toolbox for Spark (https://github.com/prophecy-io/spark-ai) that contains useful connectors, transformations, and agents for building Gen-AI applications.

Hey HN, I'm Maciej, one of the co-founders of Prophecy (https://prophecy.io) - low code for Data Transformations and Generative-AI.

We've just released the latest version of our product, which makes it easier for teams to build data pipelines for LLM-based applications. As part of the release, we're also open-sourcing the toolbox for Spark (https://github.com/prophecy-io/spark-ai) that contains useful connectors, transformations, and agents for building Gen-AI applications.

Hopefully, this allows some of you to build your apps easier and make them more robust and scalable from day one. Quick getting started example available here: https://github.com/prophecy-samples/gen-ai-chatbot-template (all code is open-source too).

While our product is already mature, the toolbox shared above is still in a pretty early stage but will be completely OSS. Any thoughts on the concept and ideas for what's important to the community would be super appreciated!

Jina mainly because of their use of neural networks and AI.

Jina - It’s an open-source project where you can build search engines. Well maybe not no code but it claims that you only need a few lines of code for creating projects. The project supports semantic, text, image, audio, and video search. What I’m also interested in is with their neural search and generative AI. I’m also interested in the amount of github repo that they have. I have this on my radar since this is also something I was interested in.

Do you guys have any ideas how we can match images on our database? We’re working on a project that about matching images on our database. We were trying to use SIFT and some other similar methods, but for some reason, nothing doesn’t seem to be working that well. Does anyone have any suggestions for the most effective way to do this? Maybe some open-source solutions like HuggingFace or Jina AI? We just want to make sure our image matching is correct and that part’s been a bit of a struggle on our part.

The tech lets you find 3D models without sifting through tons of text - An information retrieval framework does the heavy lifting and compares models to each other, no descriptions or keywords needed.

Jina AI -They offer a neural search solution that can help build smarter, more efficient search engines. They also have a list of cool github repos that you can check out. Similar to Vertex AI, they have image classification tools, NLPs, fine tuners etc.

Well, it's not exactly a new feature, but we've been working on early support for DocArray v2 in Jina.

Jina let’s you serve all of your models through the same Gateway while deploying them as individual microservices. You can also tie your models together in a pipeline if needed. Also some nice ML focussed features such as dynamic batching.