Vectorize - Reduced end-to-end latency for vector changes

<p>We have greatly improved the throughput of the Vectorize <a href="https://blog.cloudflare.com/building-vectorize-a-distributed-vector-database-on-cloudflare-developer-platform/#the-wal" target="_blank" rel="noopener">write-ahead log (WAL)<span class="external-link"> ↗︎</span></a>. As a result, we have significantly reduced the end-to-end latency for a vector change to become queryable: median latency has dropped from 2 minutes to under 30 seconds, and p99 latency from 5 minutes to under 2 minutes.</p> <img src="https://developers.cloudflare.com/cdn-cgi/image/onerror=redirect,width=2542,height=1184,format=webp/_astro/vectorize-p99-wal-batch-end-to-end-latency-improvement.k8gtzlG7.png" alt="Vectorize p99 WAL batch end-to-end latency improved" loading="lazy" decoding="async" width="2542" height="1184"> <p>This means inserts, upserts, and deletes are reflected in query results faster, improving the freshness of semantic search, recommendation, and retrieval-augmented generation (RAG) workloads. You do not need to change your code or configuration to benefit from this improvement.</p> <p>For more information, refer to the <a href="https://developers.cloudflare.com/vectorize/">Vectorize documentation</a>.</p>