SQLite Vector Search 2026: sqlite-vec and the Lightest RAG Stack Ever

Do you really need a server for vector search? sqlite-vec adds embeddings to the world's most portable database.

## SQLite Vector Search 2026: sqlite-vec and the Lightest RAG Stack Ever SQLite is the most deployed database on Earth - every phone, browser, and desktop app ships with it. sqlite-vec (7,900 GitHub stars) adds vector search as a loadable extension, making it possible to run a full RAG pipeline inside a single file. No server, no Docker, no cloud. ## Why SQLite for Vectors - **Zero infrastructure** - one file, no daemon - **Perfect for desktop/mobile apps** - embed RAG in your app - **Battery-friendly** - no network calls for local semantic search - **Good to ~1M vectors** - plenty for personal or small-team use ## Step 1: Install ```bash pip install sqlite-vec # or load as a SQLite extension in any language ``` ## Step 2: Create and Insert ```python import sqlite3, sqlite_vec conn = sqlite3.connect("search.db") conn.enable_load_extension(True) sqlite_vec.load(conn) conn.execute("CREATE VIRTUAL TABLE vec_docs USING vec0(embedding float[768])") # Insert with an embedding from any model conn.execute( "INSERT INTO vec_docs(rowid, embedding) VALUES (?, ?)", (1, embedding_list) ) ``` ## Step 3: Search ```python rows = conn.execute( "SELECT rowid, distance FROM vec_docs WHERE embedding MATCH ? ORDER BY distance LIMIT 5", (query_embedding,) ).fetchall() ``` ## Step 4: Full RAG in One File The complete stack: documents in a normal table, embeddings in the vec0 virtual table, and the LLM served locally by Ollama. Total: one .db file + one Python script. ## When to Use It vs a Real Vector DB | Scenario | Use | |----------|-----| | Desktop app, mobile app, CLI tool | sqlite-vec | | Single-user local search | sqlite-vec | | Multi-user web app, high concurrency | Qdrant, Chroma, PGVector | | 10M+ vectors | Milvus, Qdrant, Weaviate | ## FAQ **sqlite-vec vs sqlite-vss?** sqlite-vss is the older, unmaintained project; sqlite-vec is its modern successor with better performance and maintenance. **Does it work on mobile?** Yes - loads in iOS and Android apps; it is written in C with no server component. **How many vectors can it handle?** Community benchmarks show smooth operation to ~1M vectors; beyond that, a server-based vector DB is a better fit.