| Agentic RAG with Qdrant and CrewAI |
Build a vector-search-powered agentic workflow to extract insights from meeting recordings |
Docker, Qdrant, CrewAI, Claude |
| Qdrant 101 - Getting Started |
Introduction to semantic search and the recommendation API of Qdrant |
NumPy, Faker |
| Qdrant 101 - Image Data |
Use semantic search for accurate skin cancer image comparison with Qdrant and CLIP |
CLIP, PyTorch, datasets |
| Qdrant 101 - Text Data |
Introduction to the intersection of Vector Databases and Natural Language Processing |
transformers, datasets, GPT-2, Sentence Transformers, PyTorch |
| Qdrant 101 - Audio Data |
Introduction to audio embeddings, audio data, and music recommendation systems |
transformers, librosa, openl3, panns_inference, streamlit, datasets, PyTorch |
| Build a Semantic Search Engine in 5 Minutes |
Quick starter tutorial that builds a semantic search engine for science-fiction books |
Qdrant, OpenAI, FastEmbed |
| AI Getting Started Demo |
Sample menu dataset and pre-written script used by the "Start building on Qdrant" agent prompt in the Qdrant docs to demo local semantic search |
Qdrant, FastEmbed |
| Semantic Search for Sci-Fi Books |
Semantic search over a top-100 set of science-fiction books |
Qdrant, FastEmbed |
| Build a Semantic Search API |
Search startup descriptions by meaning with Qdrant Cloud Inference, filter by city, and serve results through FastAPI |
Qdrant Cloud Inference, FastAPI |
| Language Model QA with Qdrant — ColPali and Binary Quantization |
Document retrieval with Vision Language Models and binary quantization |
ColPali, Qdrant, CLIP, PyTorch |
| ColPali and ColQwen2 PDF Retrieval at Scale |
Visual document retrieval over PDFs without OCR using vision-language embeddings |
ColPali, ColQwen2, Qdrant |
| Ecommerce - reverse image search |
Notebook demonstrating how to implement a reverse image search for ecommerce |
CLIP, semantic image search, Sentence-Transformers |
| Ecommerce Search in Golang |
Semantic product search using Qdrant with cloud inference for embeddings |
Go, Qdrant Cloud |
| Multimodal Search with LlamaIndex |
Multimodal image + caption embeddings stored and retrieved in a shared embedding space |
LlamaIndex, Qdrant, multimodal embeddings |
| Multi-Representation Search |
Step-by-step build-up of a retrieval pipeline using a document's multiple representations |
Qdrant, FastEmbed, dense + multi-vector |
| Multivector Representation |
Use Qdrant multi-vector search with dense and late-interaction (ColBERT-style) embeddings for retrieval and reranking |
Qdrant, late-interaction / ColBERT embeddings |
| Binary Quantization with Qdrant |
Demonstrate and evaluate the search performance of Qdrant with binary quantization |
Qdrant Cloud, binary quantization |
| GraphRAG with Neo4j, Qdrant, and OpenAI |
Extract graph relationships from text, store them in Neo4j, and enrich retrieval with Qdrant vector search |
GraphRAG, Neo4j, Qdrant, OpenAI |
| Minimal Dependency RAG with DeepSeek and Qdrant |
Build a lightweight RAG pipeline with the DeepSeek model and Qdrant |
DeepSeek, Qdrant, RAG |
| Semantic Caching for RAG |
Put a semantic cache in front of a RAG pipeline and calibrate its similarity threshold |
Qdrant Cloud Inference, OpenRouter, RAG |
| Question Answering with LangChain and Qdrant, Without Boilerplate |
Retrieval-augmented question answering pipeline with LangChain, FastEmbed, and Qdrant |
LangChain, FastEmbed, Qdrant, Claude/GPT |
| LLM QA with Qdrant — DSPy Medical Bot |
Build a medical Q&A bot using DSPy and Qdrant |
DSPy, Qdrant, medicine |
| Extractive Question Answering with Qdrant |
Build an extractive question-answering system that pulls answers from context |
Qdrant, retriever model, reader model |
| QA which is always updated: Recency and Cohere using Llama Index |
Keep your QA system always using updated information |
Llama Index, OpenAI Embeddings, Cohere Reranker |
| Choosing a Fusion Method: RRF, DBSF, and FormulaQuery |
Compare RRF, DBSF, and FormulaQuery for hybrid (dense + sparse) search |
Qdrant, RRF, DBSF, FormulaQuery |
| Migrate Hybrid Search from Chroma Cloud to Qdrant Cloud |
Migrate a Chroma Cloud hybrid search collection with the Qdrant Migration Tool, replace its embedding functions with Cloud Inference, and translate the RRF query |
Qdrant Cloud Inference, Chroma, Migration Tool |
| Customizing Relevance Feedback |
Customize the Relevance Feedback Query, add it to your pipeline, and evaluate gains |
Qdrant, relevance feedback |
| Collaborative Filtering and MovieLens |
A notebook demonstrating how to build a collaborative filtering system using Qdrant |
Sparse Vectors, Qdrant, MovieLens |
| Collaborative Filtering (via Sparse Vectors) |
Build a collaborative filtering recommender using sparse vector representations |
Sparse Vectors, Qdrant, MovieLens |
| Self-Query on Wine Reviews |
Semantic search and filtering over ~120k wine reviews |
Qdrant, Python |
| Use semantic search to navigate your codebase |
Implement a semantic search application for code search tasks |
Qdrant, Python, sentence-transformers, Jina |
| Time-Based Sharding of Social Media |
Shard social-media post data by time for efficient retrieval |
Qdrant, time-based sharding |
| Incremental Embedding Updates |
Sync embeddings with changing raw text data |
Qdrant Cloud, Python |
| Qdrant Data Preparation Webinar |
Transform raw data into an AI-ready format using Qdrant and FastEmbed |
Qdrant, FastEmbed, RAG |
| Qdrant Essentials Course |
Multi-day course notebooks: semantic recommendation, HNSW performance tuning, hybrid and sparse search, LAION-400M large-scale ingestion, and Universal Query |
Qdrant, HNSW, FastEmbed, ColBERT |
| Qdrant Multi-Vector Search Course |
Multi-module course on late-interaction (ColPali) multi-vector search: basics, MaxSim, how ColPali works, quantization, pooling, and multi-stage retrieval pipelines |
Qdrant, FastEmbed, ColPali, ColBERT, quantization |
| RAG Pipeline Evaluation with Ragas |
Evaluate a RAG pipeline end to end: recall@10 and context precision for retrieval, Ragas faithfulness and answer relevancy for generation |
Qdrant, FastEmbed, Ragas, OpenRouter |
| Chat With Product PDF Manuals Using Hybrid Search |
Parse product manuals and answer questions using dense and sparse retrieval with Qdrant hybrid search |
Qdrant, LlamaIndex, LlamaParse, Jina, FastEmbed, OpenRouter |
| Discord RAG Bot |
Answer Discord questions from indexed Qdrant documentation and inspect the supporting sources |
Qdrant, CAMEL-AI, OpenAI, discord.py |