Vector database showroom. Part 2: Chroma — The E-Scooter That Starts in 90 Second

A developer's hands-on review of Chroma, the open-source Apache 2.0 embedding database, details its embedded-by-default design, three-line setup with a bundled local ONNX embedding model, and SQLite-plus-Parquet persistence. The writeup warns that the HNSW index lives in RAM (roughly 6 GB for 1M 1536-dim vectors plus comparable graph overhead), there is no distributed mode, and durability is prototype-grade, making it suited to RAG prototyping and CI evals but not production workloads with paying users.

🛴 Chroma — The E-Scooter That Starts in 90 Seconds pip install chromadb — and you're already riding. No server, no ports, no API keys. Under the hood: an open-source embedding database Apache 2.0, Python-first, Rust core since v0.4 . Embedded mode is the default: use PersistentClient to write your data to SQLite + Parquet right on disk while the basic Client is ephemeral and loses data on restart — a classic first-day surprise . Need to share it with the team? One command turns the scooter into an HTTP server or a container. Where it shines: - Three lines to your first search, embeddings included : a local ONNX model runs by default — no OpenAI key, no ongoing network calls the model downloads once, ~80 MB, on first run , no bills - The default of every RAG tutorial : first-class LangChain and LlamaIndex integrations - Metadata filters where and document-content filters where document - Cosine instead of the default L2 — a single parameter - Your data is actually yours : collection.get dumps everything. Lock-in is measured in hours, not months Where it stalls: - Single node by design — there is no distributed mode. Single-digit millions of vectors: comfortable. Tens of millions: an expedition with duct tape - The HNSW index lives in RAM : 1M × 1536-dim vectors ≈ 6 GB of raw data — plus roughly the same again for the graph itself same math as pgvector - Prototype-grade durability : SQLite + Parquet segments on disk. A hard kill of the process can cost you the latest writes - No BM25 hybrid, no quantization, no RBAC — invisible in a prototype, painfully visible in production What breaks if you skip the manual: - The scooter that drove itself to production . The classic arc: the prototype grows, "it's basically done, let's ship it" — and at 5M vectors you're looking for a cluster that doesn't exist. Migrating to a "real" database is a day's work; replanning the architecture mid-incident is the day you don't have - No alarm system : token auth at best, TLS is DIY through a reverse proxy. "It's only reachable from the office network" — famous last words - The storage format has changed between major versions before: read the changelog before upgrading Cost of ownership : free under Apache 2.0. Chroma Cloud exists, but the scooter's honest habitat is "zero infrastructure at all." Mechanics & parts : job postings for a "Chroma engineer" don't exist — because they're not needed. Any Python developer can fix a scooter with a screwdriver. The community is one of the largest among vector databases. ✅ Take it if : you're prototyping RAG, learning embeddings, running evals in CI, or building a personal tool that will never see the internet ❌ Pass if : this database is about to hold production with paying users — rent a car, not a scooter Test drive — 90 seconds: That's the whole vehicle. If it feels too easy — that's the point. Just remember: a scooter's job is to one day step aside for a real car.