How to use Qdrant (qdrant/qdrant): 3 use cases

3 use cases

Run a local vector database for your RAG app

Start Qdrant in Docker, connect from Python and store your embeddings with payloads.

View prompt

Start qdrant/qdrant locally with Docker, create a collection for my <documents>, embed them with <model>, and upsert them with payloads for source and date. Then run a search for <query> filtered by <condition> and show me the results.

Combine keyword and semantic search in one query

Use hybrid search with dense and sparse vectors so results match both meaning and exact terms.
- REPO qdrant/qdrant
- Claude Code
- Codex
- Cursor
- Software and DevOps
- Intermediate
View prompt
```
Using qdrant/qdrant, set up a collection with dense and sparse vectors for <dataset>, run hybrid queries merged with Reciprocal Rank Fusion, and compare the top 5 results against dense-only search for <queries>.
```
Cut vector search memory with quantization

Turn on built-in quantization and on-disk storage so a big collection fits on a smaller machine.
- REPO qdrant/qdrant
- Claude Code
- Codex
- Cursor
- Software and DevOps
- Advanced
View prompt
```
For my qdrant/qdrant collection <name>, enable quantization and on-disk storage, then measure memory use and top 10 recall on <sample queries> before and after. Recommend settings that keep recall above <target>.
```

Quick start with Qdrant

Check you have what it needs: Docker for the local server, or a free tier cluster on Qdrant Cloud; A client library, for example the Python client; Embeddings from a model of your choice.
Open qdrant/qdrant on GitHub and read the README and license.
Run docker run -p 6333:6333 qdrant/qdrant to start the server
Install the Python client and connect with QdrantClient(url="http://localhost:6333")
Store your embeddings as points with a JSON payload such as source, date or tags
Use the Web UI to explore collections and test queries

These steps come from our top use case, Run a local vector database for your RAG app, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for qdrant/qdrant

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Best AI repos for Software and DevOps

About this repo

Who it is forDevelopers building semantic search, recommendations or RAG who need a fast vector store they can run themselves.
Why it is hot35k stars, talked about in 2 AI sources we track
LanguageRust
Sourcegithub.com/qdrant/qdrant · Back to Hot repos

Requirements

Docker for the local server, or a free tier cluster on Qdrant Cloud
A client library, for example the Python client
Embeddings from a model of your choice

Add this badge to your README

Maintain Qdrant? Show readers where to find these use cases.

Markdown

[![Use cases on Deduped](https://dedupedai.com/badge/qdrant/qdrant.svg)](https://dedupedai.com/use-cases/qdrant-qdrant/?utm_source=github&utm_medium=badge&utm_campaign=qdrant-qdrant)

HTML

<a href="https://dedupedai.com/use-cases/qdrant-qdrant/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=qdrant-qdrant"><img src="https://dedupedai.com/badge/qdrant/qdrant.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Qdrant

What is Qdrant?

Qdrant is a vector similarity search engine and vector database written in Rust. It stores points, which are vectors with a JSON payload, and offers dense, sparse and multivector search, rich payload filtering, hybrid search with fusion, quantization that cuts RAM use by up to 97%, distributed deployment, a Web UI, REST and gRPC APIs, official clients in several languages and Qdrant Edge for small devices. It is an open-source project on GitHub: https://github.com/qdrant/qdrant.

How do I use Qdrant?

Run docker run -p 6333:6333 qdrant/qdrant to start the server; then install the Python client and connect with QdrantClient(url="http://localhost:6333"); Store your embeddings as points with a JSON payload such as source, date or tags. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Qdrant for?

Developers building semantic search, recommendations or RAG who need a fast vector store they can run themselves.

What can I do with Qdrant?

3 use cases so far, for example: Run a local vector database for your RAG app; Combine keyword and semantic search in one query; Cut vector search memory with quantization. Each has steps and a copy-paste agent prompt.

What do I need to run Qdrant?

Docker for the local server, or a free tier cluster on Qdrant Cloud; A client library, for example the Python client; Embeddings from a model of your choice.

What are alternatives to Qdrant?

Other hot AI repos in Software and DevOps: ECC, Thinkrail, Superpowers, Deep Infer, Instructor.

Is Qdrant safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.