Connect Codex to Chroma

Similarity search by a query embedding vector.

Full-text / semantic search using query text — Chroma embeds it server-side via an attached function.

Add records to a collection (fails if IDs already exist; use Upsert for insert-or-update).

Upsert records — inserts new IDs and updates existing ones (idempotent sync).

Update existing records by ID (fails if an ID does not exist; use Upsert otherwise).

Get records by ID or filter.

Count the number of records in a collection.

Delete records by ID, metadata filter, or document content filter.

Upload a document file, chunk + embed it, and add the records.

List collections in the tenant/database.

Get a collection's metadata and configuration by name.

Create a collection.

Rename a collection or replace its metadata.

Permanently delete a collection and all its records.

Count the total number of collections in the database.

Get the indexing status of a collection (records indexed vs pending).

Fork (copy) an existing collection into a new one.

Get the number of times a collection has been forked.

Get a collection's metadata by its UUID.

Get a collection by its Cloud Resource Name (CRN).

Attach an embedding or processing function to a collection.

Get details about a function attached to a collection.

Add input data to an attached function (e.g. provide documents to embed).

Detach (remove) a function from a collection.

Get metadata about a tenant.

Create a new tenant.

Update a tenant's configuration.

List all databases in the tenant.

Create a new database in the tenant.

Get metadata about a database.

Delete a database and ALL its collections. DESTRUCTIVE.

Check whether the Chroma server is healthy.

Get the server heartbeat (nanosecond timestamp).

Get the Chroma server version string.

Reset the Chroma server. DESTRUCTIVE — wipes ALL data across all tenants and databases.

Get the identity of the currently authenticated user.