towhee VS cadence

As another commenter noted, Milvus is overkill and a "bit much" if you're learning/playing.

A good intro to the field with progression towards a full Milvus implementation could be starting with towhee[0] (which is also supported by Milvus).

towhee has an example to do exactly what you want with CLIP[1].

[0] - https://towhee.io/

[1] - https://github.com/towhee-io/examples/tree/main/image/text_i...

The description of this is kind of confusing but I think the easiest way to understand it is that it is a data processing pipeline of sorts. Take unstructured data and apply transformation and computation. A similar project to this is Towhee (https://github.com/towhee-io/towhee). This project tries to simplify unstructured data processing and provides pretrained models and pipelines from their hub.

Milvus also has incredible flexibility when it comes to choosing an indexing strategy, and we also have a library specifically meant to help vectorize a variety of data called Towhee (https://github.com/towhee-io/towhee).

Benchmarking the models with towhee is as simple as:

The project's homepage is https://github.com/towhee-io/towhee, and you can find more about towhee by going through the documents.

I made a tutorial for building an image search engine with python. The code example is as simple as 10 lines of code, using Towhee and Milvus To put images into the search engine:

Traditionally, I've done this through PyTorch by adding a hook, but this requires knowledge of the model itself (i.e. model arch and layer names). I found https://github.com/Hironsan/awesome-embedding-models but it didn't provide many CV-focused open-source projects. There's also https://github.com/towhee-io/towhee which is great but more targeted towards application development.

You can check the result from the tutorial.

Uber | Software Engineers | Hybrid (Denmark) | https://www.uber.com/dk/en/careers/locations/aarhus/

Work with an amazing team responsible for the infrastructure software that makes Uber’s data centers around the world reliable and scalable. If you want to solve the toughest engineering challenges alongside some of the smartest people in the industry, Uber Aarhus is the right place for you.

The team in Aarhus build and operate the stateless and stateful compute platforms used by nearly every other engineer in the company (Up - https://www.uber.com/en-GB/blog/up-portable-microservices-re... and Odin - https://www.uber.com/en-GB/blog/how-uber-optimized-cassandra...) as well as other related infrastructure projects such as Cadence - https://github.com/uber/cadence.

May be this..https://cadenceworkflow.io/

a managed esb orchestration for example is exactly same as step functions and workflow engines like cadence - https://github.com/uber/cadence

Having done a reasonable amount of messaging code in my time, I would say the final form of this sort of thing might look more like Cadence[0] than anything like this.

[0] https://github.com/uber/cadence

Emit events from your primary DB (postgres, etc.) to something like kafka or rabbitmq and then catch that in your search engine. There's also some end-to-end solutions like temporal (temporal.io) or cadence (https://cadenceworkflow.io/)