AI
AI on RESTHeart Cloud
What the AI group of a service gives you: embedding and reranking models with your own keys, vectors computed as you write, semantic search over your collections, and agents that use your data over MCP.
A service on RESTHeart Cloud can compute a vector for every document it stores, search by meaning, reorder the results with a reranking model, and let an AI agent use all of it over MCP. The models are the ones you choose, called with your own keys; the vectors stay in MongoDB, next to the data they describe. Nothing leaves your service except the calls to your provider.
The AI group of the sidebar has four entries.
| Page | What it is for |
|---|---|
The embedding model and, if you want, the reranking model the service uses, with the keys of your provider. Everything else in this group runs on what you set here. |
|
Let an agent such as Claude use your collections, aggregations, change streams and GraphQL apps, within the permissions you defined. |
|
Files |
Coming: files uploaded to a bucket, split into chunks with their vectors, ready for a semantic search. |
bySophia.ai |
A product of its own, built end to end on RESTHeart Cloud: your documents answering questions in conversation, with the sources cited. Sold and billed apart; the page in the console says what it is, bysophia.ai is where it starts. |
From a key to a semantic search
A key set under Models makes the service able to embed text. A collection told to embed one of its fields gets a vector for every document written from then on. A vector index on that field makes the vectors searchable. An aggregation with $vectorSearch and $vectorize turns a question into a vector and returns the closest documents, and a rerank block hands the best of them to the reranking model. Published on MCP, that aggregation is a search an agent can run.
Models walks you through it on catalog, the collection of the ecommerce starter, so what MCP publishes, what the search finds and what the shop sells are the same products. Each step is a click, and the same calls are shown by hand in curl, HTTPie, JavaScript and Python.
What it costs
The provider bills the calls to your account: one embedding per document written and per question asked, one reranking per search that asks for it. RESTHeart Cloud adds nothing on top. Vector indexes and searches run on your service’s MongoDB, within your plan.
Where it applies
The AI features run on Free and Shared services. A Dedicated service brings its own MongoDB Atlas, and vector search there is Atlas’s own: ask us and we set it up with you.