Hybrid search

Agent 12
HTTP/2gRPCUsers600 req/sAPI server2 vCPU · 2 GBVector DB1 vCPU · 16 GB
HTTP/2gRPCUsers600 req/sAPI server2 vCPU · 2 GBVector DB1 vCPU · 16 GB

Turn every goal green.

Traffic
600 req/s · reads only
Limit
API server answers about 6,700 req/s
Bill
  • API server8 USD/mo
  • Vector DB64 USD/mo
72 of 120 USD/mo

Goals

Not tested yet

99 of 100 requests finish faster than this.The share of requests that fail or get no answer.What the servers and services cost each month.

A support assistant gets 600 questions/s and puts the top 5 passages from 2 million help passages in its prompt. 30 percent of questions quote an exact error code. The right passage reaches only 66 percent of prompts. Raise answer quality to 0.92 with p99 under 60 ms.

An index against a full scanTap to add or remove the index

Index · 4 pages read per query · disk writes per insert: 2

Parts you can add: Vector DB. At most 4 parts. Budget: 120 USD/mo.

Tap a part to add it, or drag it onto a trace.Click a part to add it, or drag it onto a trace.