---
title: "Vector Database"
description: "Vector Database runs a managed Qdrant database on TIR, so you can store embeddings and search them by similarity for RAG, recommendations and more."
content_type: "overview"
product: "vector-database"
platform: "TIR"
url: "/tir/vector-database/"
---

# Vector Database

Vector Database runs a managed Qdrant database on TIR. It stores the vectors your machine learning
models produce and finds the ones most similar to a query. Use it for similarity search,
recommendations, RAG pipelines and natural language applications. Each database is a cluster of nodes
with a dashboard, monitoring, snapshots, a REST API and a gRPC API. TIR runs Qdrant
for you.

## Where to find it

In TIR, open your project. In the side menu, under **Storage**, select **Vector
Database**. The page, **Manage Vector Database**, lists the databases in the project.

## What you can do

- [Create a vector database](/tir/vector-database/how-to/create-a-vector-database/) with a default
  collection, a plan, and 3 to 10 nodes.
- [Connect to a vector database](/tir/vector-database/how-to/connect-to-a-vector-database/): find the
  endpoint and API keys, open the Qdrant dashboard, and copy sample commands.
- [Scale up a vector database](/tir/vector-database/how-to/scale-up-a-vector-database/) by adding
  nodes, then [use the new nodes](/tir/vector-database/how-to/use-new-nodes/).
- [Resize the disk](/tir/vector-database/how-to/resize-the-disk/) of every node.
- [Monitor a vector database](/tir/vector-database/how-to/monitor-a-vector-database/) with hardware
  and service graphs.
- [Stop or start a vector database](/tir/vector-database/how-to/stop-or-start-a-vector-database/).
- [Take](/tir/vector-database/how-to/take-a-snapshot/),
  [restore](/tir/vector-database/how-to/restore-a-snapshot/) and
  [delete](/tir/vector-database/how-to/delete-a-snapshot/) a snapshot of the whole database, or
  [back up one collection with Qdrant snapshots](/tir/vector-database/how-to/back-up-a-collection-with-qdrant-snapshots/).
- [Delete a vector database](/tir/vector-database/how-to/delete-a-vector-database/) when you are finished with it.
- Use the database as the vector store for
  [LangChain](/tir/vector-database/how-to/use-qdrant-with-langchain/) or
  [LlamaIndex](/tir/vector-database/how-to/use-qdrant-with-llamaindex/).

Through the [TIR API](/api/tir/) you can also list, create, show, update and delete databases, resize their disks, and list, take, restore and delete snapshots.

## Concepts

- [Vector database concepts](/tir/vector-database/concepts/vector-database-concepts/): points,
  collections, shards and replicas, and how many vectors a plan holds.
- [Vector Database billing](/tir/vector-database/concepts/vector-database-billing/): what is charged
  for compute, disk and snapshots.

## Where to start

Start with [Get started with Vector Database](/tir/vector-database/get-started/). For help with a
message or a step, [Troubleshooting Vector Database](/tir/vector-database/troubleshooting/vector-database/)
has the fixes, and the [Vector Database FAQ](/tir/vector-database/faq/) has short answers. To
feed a database from your own documents, see
[Build a RAG pipeline with the GenAI API](/tir/genai-api/how-to/build-a-rag-pipeline/).