Semantic Search & RAG Tool

The Vector Delete by Repository Tool

Remove all vectors belonging to a repository from the store in one call so retired, private, or stale content stops surfacing in search — clean index hygiene and a real deletion path.

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

Vector Delete by Repository, without the risk

Capability

What it does

Purge a repository’s vectors from the index.

it deletes every vector associated with a given repository from the store.

Tool
Vector Delete by Repository

Assignable to any agent

DeletePurgeScopedAuditable

How it works

Predictable, inspectable behavior

Designed to be reliable.

deletion is scoped and logged, so removing content from retrieval is a single auditable action — important for retiring data and honoring deletion requirements.

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 rag.vector_delete_by_repo tool accepts these inputs when an agent calls it. Required inputs are flagged.

Name Type Required Description
collection string Required Vector collection to delete from.
repo string Required Repository whose vectors should be removed.
In depth

How the Vector Delete by Repository tool works in practice

Vector Delete by Repository is a semantic search & rag tool you assign to a VDF AI agent. It deletes every vector associated with a given repository from the store. Its hallmarks — Delete, Purge, Scoped — let an agent rely on it as a dependable step in a larger task rather than a brittle one-off script.

Under the hood, deletion is scoped and logged, so removing content from retrieval is a single auditable action — important for retiring data and honoring deletion requirements. It expects collection and repo 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 Vector Delete by Repository when they need to handle retire content, index hygiene, and compliance. It rarely works alone — pair it with Vector Upsert, Batch Embed & Upsert, and Audit Trail Query to build a complete, governed workflow, then compose those steps into an on-premise VDF AI Network.

Where it pays back

Where Vector Delete by Repository pays back

Retire content

Stop a decommissioned repo from surfacing in search.

Index hygiene

Remove stale vectors before a full re-index.

Compliance

Delete content to honor data-removal requirements.

Access changes

Purge vectors when a source loses permission.

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 Vector Delete by Repository tool

What is the Vector Delete by Repository tool?

It deletes every vector associated with a given repository from the store. 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.

Is deletion complete?

Yes. All vectors for the repository are removed from the collection, and the action is logged.

Why is this important for compliance?

It gives you a concrete, auditable path to remove content from retrieval when data must be forgotten.

What inputs does the Vector Delete by Repository tool need?

It requires collection and repo. Each parameter is validated when an agent calls the tool, and the full call is logged for audit.

Which tools pair well with Vector Delete by Repository?

Vector Delete by Repository is commonly assigned alongside Vector Upsert, Batch Embed & Upsert, and Audit Trail Query. 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 Vector Delete by Repository to work

See the Vector Delete by Repository tool assigned to an agent and orchestrated in a governed, on-premise network.