Hello,
Hello,
I am thinking of using CF Vectorize databases but can't find the docs for max queries/requests per second per namespace/globally. Do you know where I can get this information?
We need to be able to handle at least 10,000 queries/second, and want to make sure that CF can support that.
Thanks!
1 Reply
Hi @Noam. Thanks for reaching out!
The Vectorize platform limits are described in https://developers.cloudflare.com/vectorize/platform/limits/. The global rate limit for Cloudflare APIs is 1200 requests per 5 minutes (https://developers.cloudflare.com/fundamentals/api/reference/limits/) and the Vectorize HTTP APIs fall under that limit.
If you would like a higher throughput of query operations in Vectorize, we recommend the use of Vectorize Bindings in Workers: https://developers.cloudflare.com/vectorize/get-started/intro/#3-bind-your-worker-to-your-index. Vectorize queries received through a worker binding would not be rate limited, and you could potentially receive a throughput higher than 10k queries per second (as long as your requests are spread out geographically).
Please feel free to add more details on this thread or over DM if you'd like to discuss your use case further. We'd also be happy to record any feedback that you have for Vectorize or the Developer Platform as a whole.
Cloudflare Docs
Limits · Vectorize
The following limits apply to accounts, indexes and vectors (as specified):
Cloudflare Docs
Limits · Cloudflare Fundamentals docs
The global rate limit for the Cloudflare API is 1200 requests per five minute period per user, and applies cumulatively regardless of whether the request is made via the dashboard, API key, or API token.
Cloudflare Docs
Introduction to Vectorize · Vectorize
Vectorize is Cloudflare's vector database. Vector databases allow you to use machine learning (ML) models to perform semantic search, recommendation, classification and anomaly detection tasks, as well as provide context to LLMs (Large Language Models).