✕ Clear all filters
13 articles

📰 Dev.to · Julien L

13 articles · Updated every 3 hours · View all reads

All Articles 83,650Blog Posts 106,015Tech Tutorials 20,471Research Papers 17,848News 14,030 ⚡ AI Lessons
Run your AI assistant fully offline: a local-first architecture
Dev.to · Julien L 2mo ago
Run your AI assistant fully offline: a local-first architecture
What if your AI assistant worked on an airplane? In a hospital? On a classified network? Most AI...
Share memory between AI agents without infrastructure
Dev.to · Julien L 2mo ago
Share memory between AI agents without infrastructure
Two AI agents need to collaborate. One researches, the other writes. How do they share what they...
One query is never enough: why top RAG systems search three times
Dev.to · Julien L 2mo ago
One query is never enough: why top RAG systems search three times
LangChain's MultiQueryRetriever and LlamaIndex's SubQuestionEngine exist for a reason. Here's the math behind multi-query fusion - and how to do it in one API c
Stop Using Cosine for Everything: 5 Distance Metrics That Unlock Hidden Powers in Your Vector Database
Dev.to · Julien L 2mo ago
Stop Using Cosine for Everything: 5 Distance Metrics That Unlock Hidden Powers in Your Vector Database
Everyone uses cosine similarity. Tutorials use it. Frameworks default to it. If you ask "which...
Your RAG pipeline is missing two-thirds of the picture
Dev.to · Julien L 2mo ago
Your RAG pipeline is missing two-thirds of the picture
Most RAG pipelines do one thing well: find text chunks that are semantically similar to a query. But...
Build a local RAG pipeline in 30 lines of Python (no Docker, no API keys)
Dev.to · Julien L 2mo ago
Build a local RAG pipeline in 30 lines of Python (no Docker, no API keys)
Most RAG tutorials start with "spin up Docker" and "get your API key." This one starts with pip...
Build an MCP server that gives any LLM long-term memory
Dev.to · Julien L 2mo ago
Build an MCP server that gives any LLM long-term memory
Your LLM forgets everything after each session. MCP lets you fix that with 3 tools and zero...
Give your AI agent a real memory in 50 lines of Python
Dev.to · Julien L 2mo ago
Give your AI agent a real memory in 50 lines of Python
Your AI agent is brilliant for exactly one conversation. Then it forgets everything. It doesn't...
I replaced my 500MB vector database Docker stack with a 3MB embedded engine
Dev.to · Julien L 2mo ago
I replaced my 500MB vector database Docker stack with a 3MB embedded engine
Most vector database tutorials start the same way: docker pull qdrant/qdrant docker run -p...