Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: qdrant
ROE Versus TechRAG: GraphRAG on Docker and Qdrant or on SQLite and LanceDB
Two takes on one GraphRAG thesis: Qdrant, MongoDB and a 120B model against LanceDB, SQLite and qwen2.5 7B, with retrieval logic compared and lessons drawn.
7 min readDesigning Portable Multi-Tenant Semantic Search on Kubernetes and Qdrant
How a semantic search platform uses Kubernetes for portability and tenant-aware routing to keep its vector database replaceable and its workloads isolated.
6 min readA Local RAG Pipeline with Qdrant, fastembed and Gemini in Python
A small RAG pipeline in Python: chunk local docs, embed them offline with fastembed, keep vectors in Qdrant, and answer questions with Gemini from the CLI.
6 min readSemantic Agent Memory in LangGraph with Qdrant and Cross-Thread Recall
Give a LangGraph agent long-term memory with Qdrant: embed user facts, recall them across thread IDs, and add payload filters for multi-tenant isolation.
10 min readAgentic RAG with Agno Teams: Query Rewriting, a Critique Loop and Qdrant
Agentic RAG with an Agno team: a coordinator rewrites queries, a critic loops retrieval, and answers come only from approved context in Qdrant hybrid search.
22 min readA Fully Local GraphRAG Pipeline With LangExtract, Neo4j, Qdrant and Ollama
Build GraphRAG on local models: extract entities with LangExtract, store them in Neo4j, index them in Qdrant, then expand subgraphs for graph-grounded answers.
39 min readCutting RAG Token Spend 67% With Qdrant Multivectors and Sentence Isolation
A legal-discovery RAG pipeline that reranks with ColBERT inside Qdrant, isolates the matching sentence, and trades some latency for a verified 67.1% token cut.
8 min readBuilding a Cited Q&A System Over Central Bank PDFs With RAG
A hands-on RAG build over quarterly central bank reports: ingestion, recency-aware retrieval, cited answers, and the practical bugs found along the way.
8 min readTracing a Voice RAG Agent with LiveKit, Qdrant and MLflow
Build a speech-to-speech mortgage assistant using LiveKit, LlamaIndex and Qdrant, with OpenTelemetry traces in MLflow showing each retrieval and LLM step.
46 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.