Page 3 of 8~104 min topic

Hybrid search for RAG

Learn the controls and knobs

Each hybrid search control is a hypothesis about a metric under a workload—not a synonym for quality on the technical support search assistant.

~13 min this pageControls

1Learn the idea

Read

Control map

Primary knobs for hybrid search: lexical weight, vector weight, RRF k, candidate pools, reranker depth, filters.

Write a sheet for the technical support search assistant with columns: control, current value, predicted benefit, predicted cost, rollback trigger. Fill it using this topic’s real tension: Hybrid raises recall and latency/complexity. Heavy lexical weight helps IDs and hurts paraphrase. Rerankers improve order and cost milliseconds.

Change one hybrid search family at a time. If you move two knobs and the technical support search assistant improves, you learned a cocktail, not a cause—and you cannot roll back surgically.

Read

Product exposure

End users of the technical support search assistant should see only safe dials related to hybrid search. Infrastructure limits, private prompts, and policy thresholds stay server-owned. A user-facing control that bypasses those limits is a vulnerability dressed as UX for hybrid search.

Read

Make it operational

Publish the hybrid search control sheet next to the technical support search assistant runbook. On-call should see which knob moved in the last deploy without reading chat archaeology. Unknown hybrid search knobs are unowned knobs.

Also pin one numeric memory from this hybrid search chapter: On 50 tickets, pure vector recall@5=0.72, pure BM25=0.64, RRF hybrid=0.86—report denominators. That number is not decoration; it is a template for how claims about hybrid search on the technical support search assistant should look in design docs. Scoped specifically to hybrid search / technical support search assistant / controls-and-knobs.

Read

Common mix-ups

People confuse hybrid search with neighboring buzzwords when debugging the technical support search assistant. Before changing prompts, ask whether the broken stage was evidence gathering, the hybrid search judgment itself, validation, or the product action. Fixing the wrong stage creates folklore (“we tried hybrid search and it failed”) that blocks the next team on the technical support search assistant. Scoped specifically to hybrid search / technical support search assistant / controls-and-knobs.

Read

Rehearsal (hybrid-search-rag/controls-and-knobs)

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to hybrid search rag rather than generic AI advice.

Read

Rehearsal (hybrid-search-rag/controls-and-knobs)

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to hybrid search rag rather than generic AI advice.

Read

Rehearsal (hybrid-search-rag/controls-and-knobs)

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to hybrid search rag rather than generic AI advice.

Go deeper

Before you start

Why this matters

From [lexical weight, vector weight, RRF k, candidate pools, reranker depth, filters], pick one control for hybrid search on the technical support search assistant. Predict which metric rises and which cost rises if you increase it.

In the wild

See how this idea shows up as a product and a company — then come back to the lesson. Skills transfer across vendors.

Check your understanding

Page assessment

Answer from memory. Completion is saved from this evidence, not from opening the next page.

1. What is one idea from this page you would apply, and what evidence would you check?

All responses are required.