Is this not just a wrapper around a vector database?

The vector search is the part that is genuinely easy, and if that were all you needed you should build it. What is not easy is entity resolution that holds under concurrent writers, provenance bookkeeping that retracts a fact only when its last supporter drops it, an ontology apply that is reversible, and orchestration that does not lose documents. Those took us the time; the vector call took an afternoon.

We already have a working prototype. What changes at production scale?

The prototype works because nothing is concurrent and nothing has failed yet. What arrives with scale is: two workers extracting two documents that mention the same entity and creating two nodes; a single slow provider call taking a whole document down with it; and the day someone asks you to change an entity type and you realise it means re-extracting everything. Those are the three we would budget for.

What does it cost to run this yourself?

The model spend is the smaller part: graph extraction is paid once per document, and each search adds a model call to write its answer. The real cost is the datastores you now operate (a vector index and usually a graph database, both needing sizing, backups and a rebuild path) and the engineer who owns the pipeline.

What is the lock-in if we adopt you and later change our minds?

You keep pushing documents you already have, so the input side is yours. On the way out you would need to re-extract into whatever you build next, because we do not export a graph dump today — that is a real cost and we would rather name it. What you would not lose is content: everything we hold, you sent us.

Comparison

Should your team own this?

A real question with two real answers. Every team that wants grounded answers over its own content ends up building the same seven things — here is an honest inventory of them, and of what you give up by not owning them.

Read the long version Start free

The inventory

What you would own.

Not the naive version of each — the version that survives a second source system and a bad week.

Splitting documents up
Boundaries that do not cut a claim in half — and the discovery, later, that changing your mind about them means reprocessing everything you have ever stored.
Turning text into vectors
A model choice you are stuck with, because moving off it means recomputing every vector in the corpus and paying for all of it again.
A vector store to hold them
Sizing, capacity planning, and a rebuild path for the day it loses a collection — which is the day you find out whether you could rebuild it at all.
Reading facts out of prose
A language model, run over every document, reliably enough that a bad afternoon at the provider does not leave gaps you cannot see. This is where the quality of everything downstream is decided.
Knowing when two things are the same thing
The account in a billing row and the account in a ticket have to become one thing, while several documents are being processed at once. Get it wrong and the graph quietly fills with near-duplicates that no query joins.
A vocabulary that can change
Your content will outgrow whatever categories you started with. Changing them after the fact, without losing what was already stored under the old ones, is a versioning problem most teams meet only once it is expensive.
Writing the answer
Prose that says only what the sources say, citations that resolve to real documents, and a refusal that arrives instead of a plausible invention. The failure here is silent and lands in front of your customer.

Plus the part that is not a system at all and takes the longest: keeping a document that fails halfway through processing from disappearing without an error. That one raises no alarm of its own, and by the time anyone notices the answers getting worse, it has been wrong for months.

The honest trade

What you give up by not building it.

Buying is not free either. These are the four things you would be handing over.

What building gives you

What we do instead

Model choice. Your own extraction and embedding models, your own provider, your own region.

We select the models and pay for them. You cannot swap them, and that is a real constraint rather than a setting.

Deployment control. Your VPC, your keys, your compliance posture.

One managed deployment, one region. No bring-your-own-cloud and no customer-managed keys today.

A prompt you can tune per use case.

A synthesis prompt we tune, with grounding and refusal enforced. You can inspect every input to it, but not rewrite it.

No dependency on anyone else's roadmap.

A REST integration with no code-level coupling — but our roadmap is still ours.

Deciding

Which side you are on.

When to build and when to buy
If this is true of you	Build	Use GRaaS
Retrieval quality is your product's core differentiator	Included	Not included
Retrieval is a feature inside a product about something else	Not included	Included
You must run in your own cloud or a specific region	Included	Not included
You need a specific model or provider	Included	Not included
You have an engineer who can own a pipeline indefinitely	Included	Not included
You want the first cited answer this week	Not included	Included
You want a governable vocabulary without building versioning	Not included	Included
Your content spans two or more source systems	Not included	Included

Build

Retrieval quality is your product's core differentiator: Included
Retrieval is a feature inside a product about something else: Not included
You must run in your own cloud or a specific region: Included
You need a specific model or provider: Included
You have an engineer who can own a pipeline indefinitely: Included
You want the first cited answer this week: Not included
You want a governable vocabulary without building versioning: Not included
Your content spans two or more source systems: Not included

Use GRaaS

Retrieval quality is your product's core differentiator: Not included
Retrieval is a feature inside a product about something else: Included
You must run in your own cloud or a specific region: Not included
You need a specific model or provider: Not included
You have an engineer who can own a pipeline indefinitely: Not included
You want the first cited answer this week: Included
You want a governable vocabulary without building versioning: Included
Your content spans two or more source systems: Included

FAQ

Frequently asked

Try the shortcut before you commit to the long way.

The free tier costs nothing and takes one POST. If it does not do what you need, you have lost an afternoon rather than a quarter.

no card required
first workspace is free
one POST to ingest

Talk to us Start free

Should your team own this?

What you would own.

Splitting documents up

Turning text into vectors

A vector store to hold them

Reading facts out of prose

Knowing when two things are the same thing

A vocabulary that can change

Writing the answer