clip-retrieval VS Typesense

The tool clip-retreival lets you filter those 400 million images to whatever subsets you're interested in --- for example, 10,000 images of (mostly) handwriting.

Hehe, well you know, PR welcome, the front end is 500 lines https://github.com/rom1504/clip-retrieval/blob/main/front/sr...

Other people have done a few alternate front ends already

This one is meant to be functional, but could sure be made prettier

This might work: https://github.com/rom1504/clip-retrieval .

HaveIBeenTrained uses clip retrieval to search the Laion-5B and Laion-400M image datasets. These are currently the largest public text-to-image datsets, and they are used to train models like Stable Diffusion, Imagen, among many others.

Done https://github.com/rom1504/clip-retrieval/commit/53e3383f58b...

Using clip for searching is better than direct text indexing for a variety of reasons but here for example because it matches better what stable diffusion sees

Based on OpenAI's CLIP and the clip-retrieval library (https://github.com/rom1504/clip-retrieval), I've built an end-to-end demo for a semantic and similarity image search engine. It's incredibly powerful for finding similar images amongst large image datasets, or just submitting text/natural language queries and finding the most relevant images in your dataset. Really useful tool for introspection into large datasets before annotation or ML work begins. This could potentially be used to filter or downsize your datasets by several orders of magnitude and make annotation and ML work easier and less costly.

Checkout the demo here:

http://ec2-52-39-251-116.us-west-2.compute.amazonaws.com/

And you can checkout our website or email me for updates and email list, etc.:

https://machineperception.co

Assuming you have an NVIDIA GPU, you can build a semantic search engine by indexing CLIP embeds (image or text).

https://github.com/rom1504/clip-retrieval

There are actually plenty of non-ES products that are way easier to integrate and tune (and get better results with less effort).

- Typesense (https://github.com/typesense/typesense)

- Algolia

- Google Programmable Search Engine (https://programmablesearchengine.google.com/about/)

Typesense - Open Source Alternative to Algolia

If you like your penny take a look at Typesense https://typesense.org/ - nothing to complain here. Especially nothing complain about pricing.

I work on Typesense [1] (historically considered an open source alternative to Algolia).

We then launched vector search in Jan 2023, and just last week we launched the ability to generate embeddings from within Typesense.

You'd just need to send JSON data, and Typesense can generate embeddings for your data using OpenAI, PaLM API, or built-in models like S-BERT, E-5, etc (running on a GPU if you prefer) [2]

You can then do a hybrid (keyword + semantic) search by just sending the search keywords to Typesense, and Typesense will automatically generate embeddings for you internally and return a ranked list of keyword results weaved with semantic results (using Rank Fusion).

You can also combine filtering, faceting, typo tolerance, etc - the things Typesense already had.

[1] https://github.com/typesense/typesense

[2] https://typesense.org/docs/0.25.0/api/vector-search.html

For something small with a minimal footprint, I'd recommend Typesense. https://github.com/typesense/typesense

I haven’t used Publish, but I’d assume you could use something like https://typesense.org/ to index and search the vault.

A cheaper option would be to use https://typesense.org. You can use DynamoDb streams to automatically load records. It has worked well for me.

Try tigris | typesense for faster search

I’m also checking out Typesense as a possibility for replacing Elastic: https://typesense.org/