The Embedding Generator Tool
Generate embedding vectors for text or chunks using a governed, on-premise model so your content becomes searchable by meaning — without sending it to a hosted embedding API.
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.
Keyword search misses
The right content is phrased differently than the query.
Ungrounded answers
Without retrieval, models invent instead of cite.
Scale hides signal
The best chunk is buried among thousands of near-matches.
Hosted RAG is off-limits
Sensitive knowledge can’t go to a third-party index.
Embedding Generator, without the risk
Capability
What it does
Turn text into vectors for semantic search.
it generates embedding vectors for one or many pieces of text using a governed model.
Assignable to any agent
How it works
Predictable, inspectable behavior
Designed to be reliable.
embeddings are produced by a model that can run inside your perimeter, so even sensitive content can be vectorized without leaving your environment.
Every call logged
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.
Per-tenant, logged
Parameters
The rag.embed tool accepts these inputs when an agent calls it. Required inputs are flagged.
How the Embedding Generator tool works in practice
Embedding Generator is a semantic search & rag tool you assign to a VDF AI agent. It generates embedding vectors for one or many pieces of text using a governed model. Its hallmarks — Embed, Vectors, On-prem — let an agent rely on it as a dependable step in a larger task rather than a brittle one-off script.
Under the hood, embeddings are produced by a model that can run inside your perimeter, so even sensitive content can be vectorized without leaving your environment. It expects texts as required input, 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 Embedding Generator when they need to handle index building, private embeddings, and query encoding. It rarely works alone — pair it with Vector Upsert, Batch Embed & Upsert, and Repository Chunker to build a complete, governed workflow, then compose those steps into an on-premise VDF AI Network.
Where Embedding Generator pays back
Index building
Vectorize chunks to make content searchable.
Private embeddings
Embed sensitive text without a hosted API.
Query encoding
Embed a query to run similarity search.
Custom RAG
Power bespoke retrieval over your data.
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.
What changes after you assign it
Questions about the Embedding Generator tool
What is the Embedding Generator tool?
It generates embedding vectors for one or many pieces of text using a governed model. 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.
Do embeddings leave my environment?
No. Embedding can run on an on-premise model, so content is vectorized inside your perimeter.
Can it embed in batches?
Yes. Pass multiple texts to embed them efficiently in one call.
What inputs does the Embedding Generator tool need?
It requires texts, and optionally accepts model. Each parameter is validated when an agent calls the tool, and the full call is logged for audit.
Which tools pair well with Embedding Generator?
Embedding Generator is commonly assigned alongside Vector Upsert, Batch Embed & Upsert, and Repository Chunker. 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.
Tools that work well alongside this one
Where this tool delivers value
Put Embedding Generator to work
See the Embedding Generator tool assigned to an agent and orchestrated in a governed, on-premise network.