jmopines/site/content/software/chromadb.md
Jean-Michel Tremblay b2727be8ce Initial commit: Hugo site with Terminal theme
Scripts: setup.sh, build.sh, serve.sh (Docker-based)
Content: about, config, software, posts sections
Custom: CSS overrides, HTML sitemap layout, extended_head partial
Theme: hugo-theme-terminal via Hugo modules (go.mod)
2026-04-03 16:30:38 -04:00

653 B

title date draft tags
Vector Search with ChromaDB 2026-04-02 false
chromadb
python
llm
tools

ChromaDB is an embedding database for building search and retrieval systems.

How I use it

I chunk documentation (VyOS, Hugo) into paragraphs, embed them with nomic-embed-text via Ollama, and store the vectors in ChromaDB for semantic search.

Stack

Documents → Chunker → Ollama embeddings → ChromaDB → Query API

Key concepts

  • Collection: a named group of embeddings (like a table).
  • Document: the raw text stored alongside the vector.
  • Metadata: key-value pairs for filtering results.