> ## 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.

# Overview

> Learn the core fundamentals of Actian VectorAI DB.

This section covers the core fundamentals for working with Actian VectorAI DB.

## Overview

VectorAI DB organizes data in a hierarchical structure. Collections contain points, and each point consists of a vector with optional payload metadata. This structure enables semantic search: you query with a vector, and VectorAI DB finds points with similar vectors in your collection.

| Category | Component | Description |
| - | - | - |
| Data structure | [Collections](https://docs.vectoraidb.actian.com/docs/fundamentals/collections/collections.md) | Named containers that store points, similar to tables in relational databases. Each collection has a fixed vector dimension and distance metric. |
| Data structure | [Points](https://docs.vectoraidb.actian.com/docs/fundamentals/points/points.md) | Individual data units within a collection. Each point has a unique ID and contains a vector with optional metadata. |
| Data structure | [Vectors](https://docs.vectoraidb.actian.com/docs/fundamentals/vectors/vectors.md) | Numerical embeddings that represent your data semantically. Generated by embedding models from text, images, or other content. |
| Data structure | [Payload](https://docs.vectoraidb.actian.com/docs/fundamentals/payload/payload.md) | Optional JSON metadata attached to points. Use payloads for filtering and storing contextual information. |
| Operations | [Search](https://docs.vectoraidb.actian.com/docs/fundamentals/search/search.md) | Vector similarity search using distance metrics to find semantically similar content. |
| Operations | [Hybrid search](https://docs.vectoraidb.actian.com/docs/fundamentals/hybrid-search/hybrid-search.md) | Combine dense and sparse vector search to improve recall and relevance. |
| Operations | [Filtering](https://docs.vectoraidb.actian.com/docs/fundamentals/filtering/filtering.md) | Combine vector similarity with metadata conditions using must, should, and must-not filters. |
| Operations | [Hybrid search](https://docs.vectoraidb.actian.com/docs/fundamentals/hybrid-search/hybrid-search.md) | Combine dense and sparse vector search with fusion strategies such as RRF and DBSF for improved retrieval quality. |
| Configuration | [Indexing](https://docs.vectoraidb.actian.com/docs/fundamentals/indexing/indexing.md) | HNSW algorithm for efficient approximate nearest neighbor search at scale. |
| Configuration | [Distance metrics](https://docs.vectoraidb.actian.com/docs/fundamentals/distance-metrics/distance-metrics.md) | Cosine similarity, Euclidean distance, and dot product for measuring vector similarity. |

## Next steps

* Start with [Collections](https://docs.vectoraidb.actian.com/docs/fundamentals/collections/collections.md) to understand how data is organized.
* Learn about [Points](https://docs.vectoraidb.actian.com/docs/fundamentals/points/points.md) to manage your vector data.
* Explore [Search](https://docs.vectoraidb.actian.com/docs/fundamentals/search/search.md) to query your collections.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.