#community-help

Discussing Built-in Image Embedding Plans and Solutions

TLDR Gustavo asked about built-in image embedding. Jason stated it is not planned due to binary data issues, but asked for a GitHub issue for the feature.

3mo

Join the chat

Jun 28, 2023 (3 months ago)

Photo of md5-f930fdb99fd46477205fa1201164ea50

Gustavo

07:08 PM

Are there plans for built-in image embeddings? If so, any ETA?

Photo of md5-8813087cccc512313602b6d9f9ece19f

Jason

09:07 PM

We don’t have plans for built-in image embeddings at the moment, because then we’d have to start accepting binary data in the ingestion APIs which we don’t do today…

Gustavo

10:01 PM

https://marqo.ai/ just reads the URL and then fetches it server-side, maybe you could do that

Jason

10:05 PM

Could you open a GitHub issue with this feature request?

Typesense

Lightning-fast, open source search engine for everyone | Knowledge Base powered by Struct.AI

Indexed 2764 threads (79% resolved)

Join Our Community Manage subscription

Similar Threads

Discussing Indexing and Embedding Performance in Typesense

Dima had queries about indexing with embedding in Typesense. Kishore Nallan and Jason provided solutions, including reducing documents sent in an API call and running embeddings on a GPU. They facilitated Dima with the latest RC.

2mo

Integrating OpenAI Embeddings with DocSearch Scraper

Marcos was looking for how to use OpenAI embeddings with DocSearch. Jason guided with an update to the scraper config, and suggested the GTE built-in model for generic use.

Issues with Cluster Upgrade and Embedding Field

Gustavo had issues upgrading their cluster and their embedding field wasn't being filled. Jason helped to solve the upgrade issue and advised re-indexing the documents to solve the embedding field issue. Both problems were successfully resolved.

1mo