turbopuffer(@turbopuffer):contextual embedding improves relevance by encoding the context of a full document into each chunk's embedding we worked with @perplexity_ai to iteratively evaluate their model checkpoints against our private benchmark, resulting in a state-of-the-art contextual embedding model

2026.11.03 16:09

contextual embedding improves relevance by encoding the context of a full document into each chunk's embedding we worked with @perplexity_ai to iteratively evaluate their model checkpoints against our private benchmark, resulting in a state-of-the-art contextual embedding model

Perplexity Developers@perplexitydevs

2026.11.02 21:50

Introducing pplx-embed-v2-context: open-weight vision-language embedding models in 9B and 0.6B. Both return one int8 vector per document, or one per chunk that sees the whole document. Read the paper, written with @turbopuffer:

118

Forward to community