Text Embeddings for Search
The cluster focuses on discussions about using text embedding models (e.g., OpenAI, VoyageAI, sentence-transformers) for semantic search, vector databases, and retrieval-augmented generation (RAG) with LLMs.
Activity Over Time
Top Contributors
Keywords
Sample Comments
Did u try VoyageAI’s new embedding models for this?
1000 upvotes for you. My brain can't compute why someone hasn't made this, along with embeddings-based search that doesn't suck.
It’t that precisely embeddings API from OpenAI? It has all context so very useful for search
Thank you! I'm looking into sentence-transformers also to create embeddings from documents.
Every method so far basically uses embeddings and vector searches. what i mean is how the LLM processes/uses that information doesn't need to be this handholdy.
It's much better to use something like bge-large-en - https://github.com/arguflow/openembeddings
Does this work with vector embeddings?
that sounds like a really great example of..... searching through vector embedding. I don't think the LLM part was technically necessary.
how would this be different from vector embeddings / semantic search?
No gpt3. Embeddings alone can be used for semantic search.