Essential Examples on Qdrant - Vector Search Engine

Agentic RAG with CrewAI

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Qdrant Agentic RAG System with CrewAI

Time: 45 min	Level: Beginner	Output: GitHub

By combining the power of Qdrant for vector search and CrewAI for orchestrating modular agents, you can build systems that don’t just answer questions but analyze, interpret, and act.

Traditional RAG systems focus on fetching data and generating responses, but they lack the ability to reason deeply or handle multi-step processes.

In this tutorial, we’ll walk you through building an Agentic RAG system step by step. By the end, you’ll have a working framework for storing data in a Qdrant Vector Database and extracting insights using CrewAI agents in conjunction with Vector Search over your data.

S3 Ingestion with LangChain

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

S3 Ingestion with LangChain and Qdrant

Time: 30 min	Level: Beginner

Data ingestion into a vector store is essential for building effective search and retrieval algorithms, especially since nearly 80% of data is unstructured, lacking any predefined format.

In this tutorial, we’ll create a streamlined data ingestion pipeline, pulling data directly from AWS S3 and feeding it into Qdrant. We’ll dive into vector embeddings, transforming unstructured data into a format that allows you to search documents semantically. Prepare to discover new ways to uncover insights hidden within unstructured data!

Agentic RAG with LangGraph

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Agentic RAG with LangGraph and Qdrant

Time: 45 min	Level: Intermediate

Traditional Retrieval-Augmented Generation (RAG) systems follow a straightforward path: query → retrieve → generate. Sure, this works well for many scenarios. But let’s face it—this linear approach often struggles when you’re dealing with complex queries that demand multiple steps or pulling together diverse types of information.

Agentic RAG takes things up a notch by introducing AI agents that can orchestrate multiple retrieval steps and smartly decide how to gather and use the information you need. Think of it this way: in an Agentic RAG workflow, RAG becomes just one powerful tool in a much bigger and more versatile toolkit.

Discord RAG Bot

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Qdrant Agentic RAG Discord Bot with CAMEL-AI and OpenAI

Time: 45 min	Level: Intermediate

Unlike traditional RAG techniques, which passively retrieve context and generate responses, agentic RAG involves active decision-making and multi-step reasoning by the chatbot. Instead of just fetching data, the chatbot makes decisions, dynamically interacts with various data sources, and adapts based on context, giving it a much more dynamic and intelligent approach.

Multimodal and Multilingual RAG

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Multimodal and Multilingual RAG with LlamaIndex and Qdrant

Time: 15 min	Level: Beginner	Output: GitHub

Overview

We often understand and share information more effectively when combining different types of data. For example, the taste of comfort food can trigger childhood memories. We might describe a song with just “pam pam clap” sounds. Instead of writing paragraphs. Sometimes, we may use emojis and stickers to express how we feel or to share complex ideas.

5-Minute RAG with DeepSeek

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

RAG in 5 Minutes with DeepSeek and Qdrant

Time: 5 min	Level: Beginner	Output: GitHub

This tutorial demonstrates how to build a Retrieval-Augmented Generation (RAG) pipeline using Qdrant as a vector storage solution and DeepSeek for semantic query enrichment. RAG pipelines enhance Large Language Model (LLM) responses by providing contextually relevant data.

Overview

In this tutorial, we will:

Take sample text and turn it into vectors with FastEmbed.
Send the vectors to a Qdrant collection.
Connect Qdrant and DeepSeek into a minimal RAG pipeline.
Ask DeepSeek different questions and test answer accuracy.
Enrich DeepSeek prompts with content retrieved from Qdrant.
Evaluate answer accuracy before and after.

Architecture:

n8n Workflow Automation

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Automate Qdrant Workflows with n8n

Time: 45 min	Level: Intermediate

This tutorial shows how to combine Qdrant with n8n low-code automation platform to cover use cases beyond basic Retrieval-Augmented Generation (RAG). You’ll learn how to use vector search for recommendations and unstructured big data analysis.

Setting Up Qdrant in n8n

To start using Qdrant with n8n, you need to provide your Qdrant instance credentials in the credentials tab. Select QdrantApi from the list.

Video Anomaly Detection Part 1: Architecture, Twelve Labs, and NVIDIA VSS

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Video Anomaly Detection: Architecture, Twelve Labs, and NVIDIA VSS

Time: 90 min	Level: Advanced	Output: GitHub

This is Part 1 of a 3-part series on building real-time video anomaly detection from edge to cloud. We’ll go from architecture and integrations to a production-grade detection pipeline.

Series:

Part 1 | Architecture, Twelve Labs, and NVIDIA VSS (here)
Part 2 | Edge-to-Cloud Pipeline
Part 3 | Scoring, Governance, and Deployment

In this tutorial, you will learn how to build a real-time video anomaly detection system that monitors live surveillance cameras across multiple sites, automatically detecting unusual events without training on specific anomaly types. You’ll see how Qdrant Edge integrates with Twelve Labs and NVIDIA Metropolis VSS to create a production-grade edge-to-cloud detection pipeline deployed on Vultr Cloud GPUs.

Video Anomaly Detection Part 2: Edge-to-Cloud Pipeline

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Video Anomaly Detection: Edge-to-Cloud Pipeline

Time: 90 min	Level: Advanced	Output: GitHub

This is Part 2 of a 3-part series on building real-time video anomaly detection from edge to cloud.

Series:

Part 1 | Architecture, Twelve Labs, and NVIDIA VSS
Part 2 | Edge-to-Cloud Pipeline (here)
Part 3 | Scoring, Governance, and Deployment

In Part 1, we set up the project, covered why kNN anomaly detection in Qdrant outperforms classifiers, integrated Twelve Labs for video embeddings and Q&A, and connected NVIDIA VSS. Now we build the edge.

Video Anomaly Detection Part 3: Scoring, Governance, and Deployment

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Video Anomaly Detection: Scoring, Governance, and Deployment

Time: 90 min	Level: Advanced	Output: GitHub

This is Part 3 of a 3-part series on building real-time video anomaly detection from edge to cloud.

Series:

Part 1 | Architecture, Twelve Labs, and NVIDIA VSS
Part 2 | Edge-to-Cloud Pipeline
Part 3 | Scoring, Governance, and Deployment (here)

In Part 1, we set up the architecture, Twelve Labs integration, and NVIDIA VSS connection. In Part 2, we built Qdrant Edge’s two-shard architecture and the escalation pipeline. Now we turn raw scores into incidents, protect the baseline, and deploy.