How does a 1,000-page scanned PDF become something an AI can search in seconds? A beginner's walk through CogniVault's ingestion pipeline: extraction, OCR, chunking, embeddings, …
New to RAG, vector databases, or local AI? This four-part beginner series walks through the CogniVault backend from the ground up. Part 1: the big picture, the full tech stack, and …
Standard vector search fails on exact keywords. Here is how CogniVault uses Hybrid Search and an agent loop to actually find what you are looking for.
Tests that need Ollama running, or Postgres up, or a real PDF on disk, will be skipped in CI and rotted in a week. Here's how I made CogniVault's test suite run in any environment …
A fully local, privacy-first AI Study Companion — Gemma 4 + FAISS + BM25 + Strands Agents, running entirely on your machine.
format="json" gets you 90% of the way there. The other 10% is trailing commas, shape surprises, and items that almost-but-don't-quite match the schema. Here's the defensive pattern …
Re-embedding a 200-page PDF every time you tweak one paragraph is a tax nobody wants to pay. Here's how CogniVault uses DBOS workflows and content hashing to ingest only what …
Dense vectors are smart but forgetful. Keyword search is dumb but loyal. Here's how I combined FAISS, BM25, and Reciprocal Rank Fusion in CogniVault — and why pure semantic search …