VelesDB now has a Haystack connector - build a RAG pipeline with zero infrastructure
VelesDB ships a first-party Haystack 2.x DocumentStore. Build a full RAG pipeline with pip install, no Docker, no API keys.
May 1, 20266 min read4
Command Palette
Search for a command to run...
Latest articles
Find duplicate photos on your machine in 0.3ms - no cloud, no GPU
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
Apr 6, 20269 min read2Run 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 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...
Apr 2, 20267 min read3Build 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 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 ...
Apr 2, 20265 min read3One query is never enough: why top RAG systems search three times
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...
Apr 2, 202610 min read1What if SQL could search by meaning? Meet VelesQL
You know SQL. You have been writing SELECT, WHERE, and JOIN for years. But the moment you need to search by meaning, traverse a knowledge graph, or rank results by relevance, SQL cannot help you. You reach for a proprietary API, a different client, a...
Apr 2, 202616 min read1Stop 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 distance metric should I use?", the answer is always "cosine, probably." But here is the thing: your vector database supports other metrics. And those metr...
Mar 30, 20268 min read3Build 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 install. The problem Retrieval-Augmented Generation (RAG) is the standard way to ground LLM answers in your own data. But the typical setup looks like thi...
Mar 29, 20264 min read2I 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 6333:6333 qdrant/qdrant That's 500MB+ of Docker image, a running server process, a REST API to talk to, and a container to babysit in production. For what? St...
Mar 27, 20265 min read2