---
title: "Julien L (@wiscale) | Hashnode"
description: "Building VelesDB & developer tools | Blogging about databases, dev products, and tech. Read the latest articles by Julien L on Hashnode."
url: "https://hashnode.com/@wiscale"
---

@wiscale

# Julien L

@wiscale · Paris, France · Joined March 2026

Building VelesDB & developer tools | Blogging about databases, dev products, and tech.

### [VelesDB now has a Haystack connector - build a RAG pipeline with zero infrastructure](https://velesdb.hashnode.dev/velesdb-now-has-a-haystack-connector-build-a-rag-pipeline-with-zero-infrastructure?utm_source=hashnode&utm_medium=feed)

VelesDB ships a first-party Haystack 2.x DocumentStore. Build a full RAG pipeline with pip install, no Docker, no API keys.

6 min read · [velesdb.hashnode.dev](https://velesdb.hashnode.dev/velesdb-now-has-a-haystack-connector-build-a-rag-pipeline-with-zero-infrastructure?utm_source=hashnode&utm_medium=feed)

[May 1](https://hashnode.com/posts/velesdb-now-has-a-haystack-connector-build-a-rag-pipeline-with-zero-infrastructure/69f52a7cdfd04749ea453d9d)

### [Find duplicate photos on your machine in 0.3ms - no cloud, no GPU](https://velesdb.hashnode.dev/find-duplicate-photos-on-your-machine-in-0-3ms-no-cloud-no-gpu?utm_source=hashnode&utm_medium=feed)

You have 10,000 photos on your laptop. Some are duplicates. Some are resized. Some are cropped versions of the same scene. Your brain instantly knows they're related. Your computer? It thinks they're

9 min read · [velesdb.hashnode.dev](https://velesdb.hashnode.dev/find-duplicate-photos-on-your-machine-in-0-3ms-no-cloud-no-gpu?utm_source=hashnode&utm_medium=feed)

[Apr 6](https://hashnode.com/posts/find-duplicate-photos-on-your-machine-in-0-3ms-no-cloud-no-gpu/69d3068840c9cabf4470bb99)

### [Run your AI assistant fully offline: a local-first architecture](https://velesdb.hashnode.dev/run-your-ai-assistant-fully-offline-a-local-first-architecture?utm_source=hashnode&utm_medium=feed)

What if your AI assistant worked on an airplane? In a hospital? On a classified network? Most AI stacks fall apart without internet. They depend on OpenAI for inference, Pinecone for vectors, and half a dozen cloud APIs for everything in between. Kil...

7 min read · [velesdb.hashnode.dev](https://velesdb.hashnode.dev/run-your-ai-assistant-fully-offline-a-local-first-architecture?utm_source=hashnode&utm_medium=feed)

[Apr 2](https://hashnode.com/posts/run-your-ai-assistant-fully-offline-a-local-first-architecture/69ceaf236c3d1325ca76a28e)

### [Build an MCP server that gives any LLM long-term memory](https://velesdb.hashnode.dev/build-an-mcp-server-that-gives-any-llm-long-term-memory?utm_source=hashnode&utm_medium=feed)

Your LLM forgets everything after each session. MCP lets you fix that with 3 tools and zero infrastructure. No database cluster. No Redis. No "memory service" running in the background. Just a Python script and a 3MB embedded engine that persists to ...

5 min read · [velesdb.hashnode.dev](https://velesdb.hashnode.dev/build-an-mcp-server-that-gives-any-llm-long-term-memory?utm_source=hashnode&utm_medium=feed)

[Apr 2](https://hashnode.com/posts/build-an-mcp-server-that-gives-any-llm-long-term-memory/69ceaf233d92d26a18f87421)

### [One query is never enough: why top RAG systems search three times](https://velesdb.hashnode.dev/one-query-is-never-enough-why-top-rag-systems-search-three-times?utm_source=hashnode&utm_medium=feed)

LangChain has MultiQueryRetriever. LlamaIndex has SubQuestionQueryEngine. Every serious RAG framework decomposes user questions into multiple search queries before hitting the vector database. Why? Because a single embedding compresses your entire qu...

10 min read · [velesdb.hashnode.dev](https://velesdb.hashnode.dev/one-query-is-never-enough-why-top-rag-systems-search-three-times?utm_source=hashnode&utm_medium=feed)

[Apr 2](https://hashnode.com/posts/one-query-is-never-enough-why-top-rag-systems-search-three-times/69ceaf2320ffea80ace78308)
