> Explore Qdrant's agent skills catalog at https://skills.qdrant.tech/
> Search the documentation at https://skills.qdrant.tech/search?query=your+query+here
> Use this file to discover all available pages: https://qdrant.tech/llms.txt

# Tutorials & Examples

Find an implementation by goal and stack. Open the example for its prerequisites and procedure, or use its available code.

## 5-Minute RAG with DeepSeek

Build a five-minute RAG pipeline pairing Qdrant vector search with the DeepSeek LLM to enrich prompts with retrieved context.

Goal: RAG & Agents. Stack: Python, DeepSeek.

[Open Example](https://qdrant.tech/documentation/tutorials-build-essentials/rag-deepseek/index.md) | [View Notebook](https://github.com/qdrant/examples/blob/master/rag-with-qdrant-deepseek/deepseek-qdrant.ipynb)

## Agentic RAG with CrewAI

Combine Qdrant vector search with CrewAI agents and Streamlit to extract insights from meeting transcripts and recordings.

Goal: RAG & Agents. Stack: Python, CrewAI, Streamlit.

[Open Example](https://qdrant.tech/documentation/tutorials-build-essentials/agentic-rag-crewai-zoom/index.md)

## Agentic RAG with LangGraph

Build an agentic RAG system with LangGraph and Qdrant that orchestrates multi-step retrieval, web search, and tool selection.

Goal: RAG & Agents. Stack: Python, LangGraph.

[Open Example](https://qdrant.tech/documentation/tutorials-build-essentials/agentic-rag-langgraph/index.md)

## Async API

Build high-throughput, concurrent applications on Qdrant with the async Python client and ASGI-style web frameworks.

Goal: Operations. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-develop/async-api/index.md)

## Blog-Reading Chatbot with GPT-4o

Build a blog-reading RAG chatbot with Qdrant Hybrid Cloud on Scaleway, LangChain, and OpenAI for grounded answers over your own content.

Goal: RAG & Agents. Stack: LangChain, OpenAI, Scaleway.

[Open Example](https://qdrant.tech/documentation/examples/rag-chatbot-scaleway/index.md) | [View Notebook](https://github.com/qdrant/examples/blob/langchain-lcel-rag/langchain-lcel-rag/Langchain-LCEL-RAG-Demo.ipynb)

## Blue-Green Cluster Deployment

Deploy changes to Qdrant with zero production risk using a blue-green cluster strategy: build and test on a new cluster, then switch traffic over.

Goal: Operations. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-operations/blue-green-deployment/index.md)

## Branch-Aware Search

Scope search to a version-controlled branch in Qdrant so a query returns that branch's live view, inherited from its ancestors.

Goal: Data & Filtering. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-search-engineering/branch-aware-search/index.md)

## Build a Hybrid Search API

Build a hybrid search service with Qdrant and FastEmbed by combining dense and sparse embeddings behind a FastAPI endpoint.

Goal: Search Quality. Stack: Python, FastEmbed, FastAPI.

[Open Example](https://qdrant.tech/documentation/tutorials-develop/hybrid-search-fastembed/index.md) | [View Code](https://github.com/qdrant/qdrant_demo/)

## Build a Semantic Search API

Build a neural semantic search service on Qdrant using sentence-transformer embeddings and a FastAPI search endpoint.

Goal: Get Started. Stack: Python, FastAPI.

[Open Example](https://qdrant.tech/documentation/tutorials-develop/neural-search/index.md) | [Open Notebook](https://colab.research.google.com/drive/1kPktoudAP8Tu8n8l-iVMOQhVmHkWV_L9?usp=sharing)

## Building a Chain-of-Thought Medical Chatbot with Qdrant and DSPy

Build a trustworthy medical chatbot with Qdrant and DSPy, combining RAG, dense vectors, and ColBERT multivector retrieval for grounded answers.

Goal: RAG & Agents. Stack: Python, DSPy.

[Open Example](https://qdrant.tech/documentation/examples/qdrant-dspy-medicalbot/index.md) | [View Notebook](https://github.com/qdrant/examples/blob/master/DSPy-medical-bot/medical_bot_DSPy_Qdrant.ipynb)

## Chat With Product PDF Manuals Using Hybrid Search

Build a PDF-manual chatbot with Qdrant Hybrid Cloud, LlamaIndex, and Jina embeddings, using hybrid search to answer product-support questions.

Goal: RAG & Agents. Stack: Python, LlamaIndex, Jina.

[Open Example](https://qdrant.tech/documentation/examples/hybrid-search-llamaindex-jinaai/index.md) | [Open Notebook](https://githubtocolab.com/infoslack/qdrant-example/blob/main/HC-demo/HC-DO-LlamaIndex-Jina-v2.ipynb)

## Collaborative Filtering

Build an effective movie recommendation system using collaborative filtering and Qdrant's similarity search.

Goal: Recommendations. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-search-engineering/collaborative-filtering/index.md) | [Open Notebook](https://githubtocolab.com/qdrant/examples/blob/master/collaborative-filtering/collaborative-filtering.ipynb)

## Compressed Multivector Search

Combine the turbo4 datatype with multivector late interaction to cut on-disk vector size at a bounded recall cost.

Goal: Search Quality. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-search-engineering/turbo4-multivector-search/index.md) | [Open Notebook](https://githubtocolab.com/qdrant/examples/blob/master/multivector-turbo4/Multivector_Turbo4.ipynb)

## Data Migration

Migrate vector data into Qdrant from Pinecone, Weaviate, Chroma, or other Qdrant clusters using the Qdrant Migration Tool.

Goal: Operations. Stack: Migration Tool.

[Open Example](https://qdrant.tech/documentation/tutorials-operations/migration/index.md)

## Deterministic Collection Slicing

Split a Qdrant collection into disjoint, deterministic subsets with the slice filter for parallel scroll and reproducible sampling.

Goal: Data & Filtering. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-search-engineering/slicing-filter/index.md)

## Discord RAG Bot

Build an agentic RAG Discord bot powered by Qdrant vector search, CAMEL-AI agents, and OpenAI embeddings for context-aware answers.

Goal: RAG & Agents. Stack: Python, CAMEL-AI.

[Open Example](https://qdrant.tech/documentation/tutorials-build-essentials/agentic-rag-camelai-discord/index.md) | [Open Notebook](https://colab.research.google.com/drive/1Ymqzm6ySoyVOekY7fteQBCFCXYiYyHxw#scrollTo=QQZXwzqmNfaS)

## GPU-Accelerated HNSW Indexing

Speed up HNSW index builds with GPU acceleration on Qdrant Cloud, and measure the effect on indexing time, query latency, and cost.

Goal: Operations. Stack: Python, Qdrant Cloud.

[Open Example](https://qdrant.tech/documentation/tutorials-operations/gpu-accelerated-hnsw-indexing/index.md) | [Open Notebook](https://githubtocolab.com/qdrant/examples/blob/master/gpu-accelerated-hnsw-indexing/Gpu_Accelerated_HNSW_Indexing.ipynb)

## GraphRAG with Qdrant and Neo4j

Integrating Qdrant and Neo4j for Graph Retrieval-Augmented Generation (GraphRAG) with structured and unstructured data.

Goal: RAG & Agents. Stack: Python, Neo4j.

[Open Example](https://qdrant.tech/documentation/examples/graphrag-qdrant-neo4j/index.md) | [View Code](https://github.com/qdrant/examples/blob/master/graphrag_neo4j/graphrag.py)

## Hugging Face Dataset Ingestion

Load Hugging Face datasets directly into Qdrant collections, including precomputed embeddings, with batched uploads and streaming.

Goal: Data & Filtering. Stack: Python, Hugging Face.

[Open Example](https://qdrant.tech/documentation/tutorials-basics/huggingface-datasets/index.md)

## Hybrid Search

Step-by-step tutorial: build hybrid search in Qdrant combining dense semantic and sparse keyword retrieval with reciprocal rank fusion.

Goal: Search Quality. Stack: Python, Cloud Inference.

[Open Example](https://qdrant.tech/documentation/tutorials-basics/cloud-inference-hybrid-search/index.md)

## Hybrid Search with Reranking

Combine dense, sparse, and late-interaction embeddings in Qdrant to build hybrid search with reranking for high-precision results.

Goal: Search Quality. Stack: Python, FastEmbed.

[Open Example](https://qdrant.tech/documentation/tutorials-basics/reranking-hybrid-search/index.md)

## Implement Cohere RAG connector

Implement a custom Cohere RAG connector backed by Qdrant to expose your collections to Cohere LLMs with inline citations.

Goal: RAG & Agents. Stack: Python, Cohere.

[Open Example](https://qdrant.tech/documentation/examples/cohere-rag-connector/index.md)

## Incremental Embedding Updates

Sync embeddings with raw text data that changes over time.

Goal: Data & Filtering. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-operations/incremental-embedding-updates/index.md) | [Open Notebook](https://githubtocolab.com/qdrant/examples/blob/master/temporal-data-drift/sync_raw_data_to_embeddings.ipynb)

## Indexing Payloads of Random Shape

Index open-ended payloads whose keys are data in Qdrant, using a nested filter over a fixed key-value array instead of one index per key.

Goal: Data & Filtering. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-search-engineering/index-dynamic-payloads/index.md)

## Large-Scale Search

Index and search hundreds of millions of vectors in Qdrant cost-efficiently with minimal hardware and tuned configuration.

Goal: Operations. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-operations/large-scale-search/index.md) | [View Code](https://github.com/qdrant/laion-400m-benchmark)

## Measuring ANN Recall

Compare approximate search with exact results, inspect ANN recall in the Web UI, and add a repeatable Python check.

Goal: Search Quality. Stack: Python, Web UI.

[Open Example](https://qdrant.tech/documentation/tutorials-search-engineering/ann-recall/index.md)

## Migrate to a New Embedding Model

Migrate a Qdrant collection to a new embedding model with zero downtime using a blue-green dual-collection strategy.

Goal: Operations. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-operations/embedding-model-migration/index.md)

## Movie Recommendation System

Build a movie recommendation system on OVHcloud with Qdrant Hybrid Cloud and sparse vectors using collaborative filtering over user preferences.

Goal: Recommendations. Stack: Python, OVHcloud.

[Open Example](https://qdrant.tech/documentation/examples/recommendation-system-ovhcloud/index.md) | [View Notebook](https://github.com/infoslack/qdrant-example/blob/main/HC-demo/HC-OVH.ipynb)

## Multi-Representation Search

Combine title, summary, and chunk vectors in one retrieval pipeline, then compare the effect of each representation.

Goal: Search Quality. Stack: Python, FastEmbed.

[Open Example](https://qdrant.tech/documentation/tutorials-search-engineering/multi-representation-search/index.md) | [Open Notebook](https://githubtocolab.com/qdrant/examples/blob/master/multi-representation-search/multi-representation-search.ipynb)

## Multimodal Search

Build a multimodal, multilingual vector earch application with Cohere Embed 4.0 and Qdrant Cloud Inference that searches across image and text modalities.

Goal: Multimodal Search. Stack: Python, Cohere, Cloud Inference.

[Open Example](https://qdrant.tech/documentation/tutorials-basics/multimodal-search/index.md) | [Open Notebook](https://githubtocolab.com/qdrant/examples/blob/master/multimodal-search/Multimodal_Search_with_Cohere_and_Cloud_Inference.ipynb)

## Multitenancy with LlamaIndex

Set up multitenancy in LlamaIndex with Qdrant using payload-based partitioning to keep each user's data fully isolated in one collection.

Goal: Data & Filtering. Stack: Python, LlamaIndex.

[Open Example](https://qdrant.tech/documentation/examples/llama-index-multitenancy/index.md)

## Multivector Document Retrieval

Optimizing PDF retrieval at scale with Qdrant and Vision Large Language Models (VLLMs) such as ColPali and ColQwen.

Goal: Multimodal Search. Stack: Python, ColPali.

[Open Example](https://qdrant.tech/documentation/tutorials-search-engineering/pdf-retrieval-at-scale/index.md) | [Open Notebook](https://githubtocolab.com/qdrant/examples/blob/master/pdf-retrieval-at-scale/ColPali_ColQwen2_Tutorial.ipynb)

## Multivectors and Late Interaction

Use multivector representations and late interaction reranking in Qdrant to improve precision without exploding RAM or insert times.

Goal: Search Quality. Stack: Python, FastEmbed.

[Open Example](https://qdrant.tech/documentation/tutorials-search-engineering/using-multivector-representations/index.md)

## n8n Workflow Automation

Automate Qdrant workflows in n8n: build no-code pipelines for vector search, recommendations, and unstructured data analysis.

Goal: RAG & Agents. Stack: n8n.

[Open Example](https://qdrant.tech/documentation/tutorials-build-essentials/qdrant-n8n/index.md)

## Prevent Unoptimized Usage

Defer visibility of unindexed points to stop bulk uploads from slowing down search.

Goal: Operations. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-operations/prevent-unoptimized-usage/index.md) | [Open Notebook](https://githubtocolab.com/qdrant/examples/blob/master/prevent_unoptimized_usage/prevent_unoptimized.ipynb)

## Private Chatbot for Interactive Learning

Build a fully private interactive learning chatbot with Qdrant Hybrid Cloud, Haystack, and an open-source LLM running on Red Hat OpenShift.

Goal: RAG & Agents. Stack: Haystack, OpenShift.

[Open Example](https://qdrant.tech/documentation/examples/rag-chatbot-red-hat-openshift-haystack/index.md)

## Private RAG Information Extraction Engine

Run a private information-extraction engine on Vultr with Qdrant Hybrid Cloud, DSPy, and Ollama to structure unstructured documents on-premises.

Goal: RAG & Agents. Stack: DSPy, Ollama, Vultr.

[Open Example](https://qdrant.tech/documentation/examples/rag-chatbot-vultr-dspy-ollama/index.md)

## Question-Answering System for AI Customer Support

Build a private customer-support QA system on AWS using Qdrant Hybrid Cloud, Cohere, and Airbyte to keep ticket data inside your infrastructure.

Goal: RAG & Agents. Stack: Cohere, Airbyte, AWS.

[Open Example](https://qdrant.tech/documentation/examples/rag-customer-support-cohere-airbyte-aws/index.md)

## RAG System for Employee Onboarding

Build an employee onboarding RAG assistant on Oracle Cloud using Qdrant Hybrid Cloud, Cohere, and LangChain for natural-language access to internal docs.

Goal: RAG & Agents. Stack: LangChain, Cohere, Oracle Cloud.

[Open Example](https://qdrant.tech/documentation/examples/natural-language-search-oracle-cloud-infrastructure-cohere-langchain/index.md)

## Region-Specific Contract Management System

Build a region-specific contract management RAG system on STACKIT with Qdrant Hybrid Cloud and Aleph Alpha for GDPR-compliant document search.

Goal: RAG & Agents. Stack: Aleph Alpha, STACKIT.

[Open Example](https://qdrant.tech/documentation/examples/rag-contract-management-stackit-aleph-alpha/index.md)

## Relevance Feedback Retrieval in Qdrant

Add relevance feedback to a Qdrant retriever to nudge search toward more relevant results across the entire vector space.

Goal: Search Quality. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-search-engineering/using-relevance-feedback/index.md) | [Open Notebook](https://githubtocolab.com/qdrant/examples/blob/master/using-relevance-feedback/Customizing_Relevance_Feedback.ipynb)

## S3 Ingestion with LangChain

Stream documents from AWS S3 into Qdrant with LangChain to build a vector ingestion pipeline for unstructured data.

Goal: Data & Filtering. Stack: Python, LangChain, AWS.

[Open Example](https://qdrant.tech/documentation/tutorials-build-essentials/data-ingestion-beginners/index.md)

## Scaling and Monitoring Hybrid Cloud

Scale CPU, memory, and disk for Qdrant Hybrid Cloud clusters and monitor pod resource usage.

Goal: Operations. Stack: Kubernetes, Qdrant Hybrid Cloud.

[Open Example](https://qdrant.tech/documentation/tutorials-operations/scaling-and-monitoring-pods/index.md)

## Secure a Self-Hosted Qdrant Instance

Harden a self-hosted Qdrant deployment with TLS, an Admin API key, a Read-Only key, and Granular Access Control.

Goal: Operations. Stack: Docker.

[Open Example](https://qdrant.tech/documentation/tutorials-operations/secure-qdrant/index.md)

## Securing and Exposing a Hybrid Cloud Cluster

Authentication and TLS management for Qdrant Hybrid Cloud clusters

Goal: Operations. Stack: Kubernetes, Qdrant Hybrid Cloud.

[Open Example](https://qdrant.tech/documentation/tutorials-operations/secure-and-expose-hybrid-cloud/index.md)

## Semantic Search 101

Run your first semantic search on Qdrant Cloud: create a cluster, upload a small dataset, and query by meaning instead of keywords.

Goal: Get Started. Stack: Python, Cloud Inference.

[Open Example](https://qdrant.tech/documentation/tutorials-basics/search-beginners/index.md) | [Open Notebook](https://githubtocolab.com/qdrant/examples/blob/master/semantic-search-in-5-minutes/semantic_search_in_5_minutes.ipynb)

## Semantic Search 101

Build a semantic search engine locally with Qdrant in five minutes using sentence-transformer embeddings and the Python SDK.

Goal: Get Started. Stack: Python, Sentence Transformers.

[Open Example](https://qdrant.tech/documentation/tutorials-basics/search-beginners-local/index.md)

## Semantic Search for Code

Build a semantic code search engine on Qdrant using natural-language and code-to-code embeddings for navigating large codebases.

Goal: Search Quality. Stack: Python, FastEmbed.

[Open Example](https://qdrant.tech/documentation/tutorials-develop/code-search/index.md) | [Open Notebook](https://colab.research.google.com/github/qdrant/examples/blob/master/code-search/code-search.ipynb)

## Snapshots

Back up and restore Qdrant collections with snapshots across single-node and distributed multi-node clusters.

Goal: Operations. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-operations/create-snapshot/index.md)

## Static Embeddings

Use static embeddings in Qdrant for fast, low-resource semantic search with minimal quality trade-offs versus transformer models.

Goal: Search Quality. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-search-engineering/static-embeddings/index.md)

## Time-Based Sharding

Implement time-based sharding in Qdrant to route fast-moving data by timestamp and prune old shards without expensive re-indexing.

Goal: Data & Filtering. Stack: Python.

[Open Example](https://qdrant.tech/documentation/tutorials-operations/time-based-sharding/index.md)

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

Architect a real-time video anomaly detection system on Qdrant Edge with Twelve Labs video intelligence and NVIDIA Metropolis VSS.

Goal: Multimodal Search. Stack: Qdrant Edge, Twelve Labs.

[Open Example](https://qdrant.tech/documentation/tutorials-build-essentials/video-anomaly-edge-part-1/index.md) | [View Code](https://github.com/qdrant/video-anomaly-edge)

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

Build the edge-to-cloud pipeline for video anomaly detection using Qdrant Edge shards, snapshot sync, and offline-capable kNN search.

Goal: Multimodal Search. Stack: Qdrant Edge, Twelve Labs.

[Open Example](https://qdrant.tech/documentation/tutorials-build-essentials/video-anomaly-edge-part-2/index.md) | [View Code](https://github.com/qdrant/video-anomaly-edge)

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

Score, govern, and deploy a video anomaly detection system on Qdrant Edge with incident formation and baseline protection.

Goal: Multimodal Search. Stack: Qdrant Edge, Twelve Labs.

[Open Example](https://qdrant.tech/documentation/tutorials-build-essentials/video-anomaly-edge-part-3/index.md) | [View Code](https://github.com/qdrant/video-anomaly-edge)

Choose an example that matches your data, stack, and operating requirements.