Semantic Search & RAG Tool

The Result Reranker Tool

Rerank a set of retrieved passages with a cross-encoder so the most relevant rise to the top — sharpening RAG accuracy by putting the best context first for the model.

Explore VDF AI Agents
MeaningSemantic, not keyword, recall
GroundedAnswers cite real sources
AssignableTo any knowledge agent
100%On-premise capable
The Retrieval Problem

Your answer exists — retrieval just can’t find it

Private knowledge is only useful if an agent can retrieve exactly the right piece and ground its answer in it. Keyword search misses, hosted RAG can’t touch sensitive data, and ungrounded models make things up.

01

Keyword search misses

The right content is phrased differently than the query.

02

Ungrounded answers

Without retrieval, models invent instead of cite.

03

Scale hides signal

The best chunk is buried among thousands of near-matches.

04

Hosted RAG is off-limits

Sensitive knowledge can’t go to a third-party index.

How the Tool Works

Result Reranker, without the risk

Capability

What it does

Reorder retrieved results by true relevance.

it reranks a set of retrieved results by their true relevance to the query.

Tool
Result Reranker

Assignable to any agent

RerankCross-encoderRelevancePrecise

How it works

Predictable, inspectable behavior

Designed to be reliable.

it scores each query-passage pair with a cross-encoder rather than a coarse similarity, so the ordering reflects real relevance and the top results are the ones worth using.

Governed
Policy + Audit

Every call logged

ScopedLoggedGovernedOn-prem

Governance

Private, governed, on-premise

Runs inside your perimeter.

Indexing and retrieval run on-premise or in your sovereign cloud, scoped per tenant and audit-logged, so even sensitive knowledge is searchable and citable without any of it leaving your perimeter.

100%
On-Prem

Per-tenant, logged

On-premRBACAudit logSovereign
Inputs

Parameters

The rerank_results tool accepts these inputs when an agent calls it. Required inputs are flagged.

Name Type Required Description
query string Required The query the results should be relevant to.
results array Required The retrieved results to rerank.
top_k integer
default: 5
Optional How many top results to keep after reranking.
In depth

How the Result Reranker tool works in practice

Result Reranker is a semantic search & rag tool you assign to a VDF AI agent. It reranks a set of retrieved results by their true relevance to the query. Its hallmarks — Rerank, Cross-encoder, Relevance — let an agent rely on it as a dependable step in a larger task rather than a brittle one-off script.

Under the hood, it scores each query-passage pair with a cross-encoder rather than a coarse similarity, so the ordering reflects real relevance and the top results are the ones worth using. It expects query and results as required inputs, so calls are explicit and easy to audit. Every call is scoped to the requesting tenant and written to an audit log, so the capability is safe to run inside a regulated, on-premise environment — the same governance model behind every VDF AI tool.

Teams reach for Result Reranker when they need to handle sharper RAG, trim context, and better answers. It rarely works alone — pair it with Hybrid Search, RAG Vector Query, and Chunk Citation to build a complete, governed workflow, then compose those steps into an on-premise VDF AI Network.

Where it pays back

Where Result Reranker pays back

Sharper RAG

Put the most relevant chunks first for the model.

Trim context

Keep only the top few passages, dropping noise.

Better answers

Improve accuracy without re-indexing.

Fusion step

Rerank the merged output of hybrid search.

How VDF AI connects it

Assigned to agents, orchestrated as networks

On VDF AI, an industry’s use cases map to agents, and you assign tools like this one to those agents. Compose multiple agents into a governed, on-premise network.

ROI Snapshot

What changes after you assign it

Faster
To the right knowledge
Cited
Answers traceable to source
Grounded
Less hallucination
100%
Data never leaves your perimeter
FAQ

Questions about the Result Reranker tool

What is the Result Reranker tool?

It reranks a set of retrieved results by their true relevance to the query. Assigned to a VDF AI agent, it runs under role-based policy with full audit logging so the capability is safe to use in production.

Why rerank after retrieval?

Initial retrieval optimizes for recall; reranking with a cross-encoder optimizes the final order for precision.

Does it need re-indexing?

No. Reranking operates on already-retrieved results, so it improves accuracy with no index changes.

What inputs does the Result Reranker tool need?

It requires query and results, and optionally accepts top_k. Each parameter is validated when an agent calls the tool, and the full call is logged for audit.

Which tools pair well with Result Reranker?

Result Reranker is commonly assigned alongside Hybrid Search, RAG Vector Query, and Chunk Citation. On VDF AI you compose several tools and agents into a single governed, on-premise network.

Does it run on-premise?

Yes. Like every VDF AI tool, it can run on-premise or in your sovereign cloud, scoped per user and audit-logged, so your data never leaves your perimeter.

How do agents use it?

You assign the tool to an agent under a role-based policy; the agent calls it as one step in a task, and several agents and tools can be orchestrated together as a governed VDF AI Network.

Put Result Reranker to work

See the Result Reranker tool assigned to an agent and orchestrated in a governed, on-premise network.