Hi! I am new to Typesense, and I was exploring the semantic search. My site is a fashion aggregator platform, where I collect fashion clothes from different websites. I had very good results with keyword search and filtering, but not with semantic search...I cannot get accurate results, if I search for instance 'White dress for a wedding party' I got black dresses, even having the color as part of the embedding. Here is part of my code, I am using auto-embedded feature, and I have tried with different models including OpenAI but with no luck: { name: "embedding", type: "float[]", embed: { from: [ "name", "description", "color", "product_categories", "brand", ], ... (I have also tried with a single field like 'description'...and with no good results either). My site is in Spanish...so name, description, etc are in Spanish. Thanks in advance.

The quality of the results are almost entirely dependent on the embedding model. The models are trained on large amounts of query/document data. It is possible that the training does not include enough example from the ecommerce domain. You have to try a few different models to check which returns better results.

Thank you! I will switch to some other model. Appreciate the response.