Utilizing CLIP for Custom Embedding on Ecommerce Sites
TLDR Alain sought to understand how to use CLIP for custom embedding in ecommerce, involving both images and product names. Jason advised using both for optimal embedding.
Oct 20, 2023 (1 month ago)
Alain
01:16 AM(Use case initially will be “similar products” & “you might also like” on ecommerce sites)
Jason
02:58 PMwould I pass the image and text (product name in this case) into CLIPYou want to do this, since CLIP embeds both the text and image
Typesense
Indexed 3011 threads (79% resolved)
Similar Threads
Reverse Image Search in TypeSense with CLIP Model
Ceno asked about reverse image search in TypeSense. Jason suggested using vector search with CLIP model for generating image embeddings.
Utilizing Vector Search and Word Embeddings for Comprehensive Search in Typesense
Bill sought clarification on using vector search with multiple word embeddings in Typesense and using them instead of OpenAI's embedding. Kishore Nallan and Jason informed him that their development version 0.25 supports open source embedding models. They also resolved Bill's concerns regarding search performance, language support, and limitations in the search parameters.
Combining Embedding Feature with Highlights and Large Documents
Walter had questions about Typesense's upcoming embedding feature, including highlights, embedding models, handling large documents, and its impact on cloud pricing. Jason provided answers and invited Walter to test an alpha build.