TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Rank Fusion for improved code context in RAG

3 pointsby wsxiaoys11 months ago

1 comment

wsxiaoys11 months ago
Fun fact: We&#x27;ve implemented binary embedding search [1] without the need for a specialized vector database. Instead, dimensional tokens like &#x27;embedding_0_0&#x27;, &#x27;embedding_1_0&#x27; are created and being built into the tantivy index [2].<p>We&#x27;re satisfied with the quality and performance this approach yields, while still keep Tabby embed everything into a single binary.<p>[1] My binary vector search is better than your FP32 vectors: <a href="https:&#x2F;&#x2F;blog.pgvecto.rs&#x2F;my-binary-vector-search-is-better-than-your-fp32-vectors" rel="nofollow">https:&#x2F;&#x2F;blog.pgvecto.rs&#x2F;my-binary-vector-search-is-better-th...</a><p>[2] Tantivy: <a href="https:&#x2F;&#x2F;github.com&#x2F;quickwit-oss&#x2F;tantivy">https:&#x2F;&#x2F;github.com&#x2F;quickwit-oss&#x2F;tantivy</a>