python - Create native picture embeddings and then make a similarity search with text - Stack Overflow

Is it generally possible to create image embeddings directly (without additional text) and store them in a database? The aim is to make the content of the images findable later via a text input in the front end using a similarity search. Is this feasible?

In best case I dont want to use any OCR and natively embed the images.

Is it generally possible to create image embeddings directly (without additional text) and store them in a database? The aim is to make the content of the images findable later via a text input in the front end using a similarity search. Is this feasible?

In best case I dont want to use any OCR and natively embed the images.

• python
• openai-api
• large-language-model
• word-embedding

Share Improve this question Follow asked Jan 2 at 12:50 FelixFelix 20111 silver badge1111 bronze badges

Add a comment  | 

1 Answer 1

Sorted by: Reset to default 0

Have you looked into multimodal embedding models?

A commercial option would be Amazons Titan Multimodal Embeddings G1 model. Another one is Coheres Embed which is multimodal too.

There are also Open Source options on Huggingface - see e.g. here.