Qdrant on René Zander | AI Automation Consultant

Qdrant vs Pinecone vs Weaviate: Production Vector DB Comparison 2026

Fri, 03 Apr 2026 13:00:00 +0200

Three vector databases keep showing up on every RAG stack in 2026: Qdrant, Pinecone, and Weaviate. I get asked which one to pick at least once a week, usually by someone who already spent two days reading benchmarks and still has no answer.

The short version, because you have real work to do: Qdrant for most self-hosted production RAG in 2026. Pinecone when the requirement is “managed, don’t touch the servers”. Weaviate when you need the extra primitives like GraphQL or the module ecosystem. I run Qdrant in production for Teedian and recommend it to most consulting clients. The reasons are below, including the edge cases where I pick something else.

RAG Pipeline Tutorial: Build a Production Document Q&A System with Qdrant and Claude

Wed, 01 Apr 2026 09:00:00 +0200

Most RAG tutorials ship a toy. You paste a PDF, it answers one question, and the moment you point it at 500 documents the retrieval goes sideways and Claude hallucinates half the citations. This one is the opposite. I am going to walk through the pipeline I actually run in production, line by line, with the tradeoffs called out where they bit me.

The verdict first. If your corpus is under 200k tokens and rarely changes, skip RAG and stuff it all into Claude’s context window. If your corpus is larger, changes often, or you need hard citations, build this RAG pipeline tutorial end to end with Qdrant, a local embedding model, and Claude Sonnet 4.6. That is the sweet spot for cost and quality in 2026.

Docker Compose AI ML Development Stack: Local LLM, Vector DB, Full YAML

Fri, 20 Mar 2026 10:00:00 +0100

Every AI project I start now begins the same way: docker compose up -d and I have Ollama, Qdrant, Postgres, Redis, and a LiteLLM proxy running in under two minutes. No pyenv conflicts, no homebrew drift, no “works on my machine”. One YAML file, one command, identical stack across my laptop and my dev VPS.

This is a tutorial for a full docker compose AI ML development stack. Copy the YAML, run it, pull a model, and start building. I use this exact layout for prototyping RAG pipelines, testing MCP servers, and running my cron-driven Claude agents before they ship to production.