chroma-local

Instructions

Determine these before writing code. Prefer discovering them from the repo and the user request. Ask only when the choice materially changes the implementation.

1. Runtime shape

   • Are they connecting to a running local server, embedding Chroma into tests, or setting up local development from scratch?
   • Decide whether they need chroma run, a Docker or service command, HttpClient or ChromaClient, or Python EphemeralClient.

2. Persistence

   • Persistent local data: choose an intentional data path.
   • Disposable test data: use defaults or a temp directory.

3. Embedding model

   • Reuse the app's existing embedding provider when possible.
   • Otherwise default to @chroma-core/default-embed in TypeScript or the standard local default in Python.
   • If the user explicitly wants OpenAI embeddings in TypeScript, install and use @chroma-core/openai.

4. Indexed data shape

   • Determine what is being indexed, how it should be chunked, and what metadata is needed for filtering and updates.