> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vectoraidb.actian.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Core concepts

> How VectorAI DB works, its data model, and how a search query flows through the system.

<Note>
  **New to vector databases?** Vector databases store numerical representations of your data called embeddings, and find results by similarity rather than exact keyword matching. Use one when meaning matters more than exact text: semantic search, RAG pipelines, agent memory.
</Note>

## Architecture

VectorAI DB runs as a single Docker container with no external dependencies. Data is persisted to a volume-mounted directory on the host.

| Port | Protocol | Purpose                         |
| ---- | -------- | ------------------------------- |
| 6573 | HTTP     | REST API                        |
| 6574 | gRPC     | gRPC API (recommended for SDKs) |
| 6575 | HTTP     | Local UI                        |

The Python and JavaScript SDKs communicate over gRPC by default.

## Data model

| Concept                                                                  | What it is                                                                                                                                                       |
| ------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [Collections](/docs/fundamentals/collections/collections)                | Named containers for vectors, similar to tables in a relational database. Each collection has a fixed vector dimension and distance metric set at creation time. |
| [Points](/docs/fundamentals/points/points)                               | The unit of data in a collection. Each point has a unique ID, a vector embedding, and an optional JSON payload.                                                  |
| [Vectors](/docs/fundamentals/vectors/vectors)                            | Fixed-length arrays of floats that represent your data semantically. Generated by embedding models from text, images, or other content.                          |
| [Payload](/docs/fundamentals/payload/payload)                            | JSON metadata attached to a point. Use payloads to store context and to filter search results.                                                                   |
| [Distance metrics](/docs/fundamentals/distance-metrics/distance-metrics) | The function used to measure similarity between vectors. Supported metrics: Cosine, Euclidean, and Dot Product.                                                  |

## How a search works

<Steps>
  <Step title="Generate an embedding">
    Your application converts a query (text, image, or other data) into a vector using an embedding model.
  </Step>

  <Step title="Send a search request">
    The vector is sent to VectorAI DB over gRPC or REST.
  </Step>

  <Step title="HNSW nearest-neighbour search">
    VectorAI DB traverses the HNSW index to find the closest vectors, applying any payload filters inline.
  </Step>

  <Step title="Ranked results returned">
    Results come back with IDs, similarity scores, and optional payloads. No post-processing needed.
  </Step>
</Steps>

You can build on this foundation with:

* [Semantic search](/docs/fundamentals/semantic-search/semantic-search) for meaning-based retrieval
* [Hybrid search](/docs/fundamentals/hybrid-search/hybrid-search) to combine dense and sparse scores
* [Filtering](/docs/fundamentals/filtering/filtering) for must, should, and must-not payload conditions

## Next steps

<CardGroup cols={2}>
  <Card title="Installation" icon="download" href="/home/installation/instructions">
    Install VectorAI DB with Docker.
  </Card>

  <Card title="Quickstart" icon="rocket" href="/home/quickstart/quickstart">
    Create a collection, insert vectors, and run a search.
  </Card>

  <Card title="Fundamentals" icon="book-open" href="/docs/fundamentals/index">
    Collections, points, vectors, search, and filtering.
  </Card>

  <Card title="Academy" icon="graduation-cap" href="/academy/tutorials">
    Hands-on tutorials for semantic search, RAG, and more.
  </Card>
</CardGroup>