SuperAPI AI Directory
Partner中文AI newsFavorites
Skillsgoogle-workspace-memory

google-workspace-memory

Office & productivity

View repository

Updated 11-04 18:23

About this skill

Google Workspace memory

Runs the Google Workspace memory cookbook in examples/cookbooks/google_workspace_memory/. It remembers the user's primary calendar, newest inbox emails and one Drive folder in the cognee dataset google_workspace_memory, then answers one question across them. Setup, the scripts and what each one does are in the cookbook's README.md.

Run every command from the repo root.

Steps

Without credentials.json in the cookbook folder, the commands below run on a sample workspace (the [setup] line says so) and answer about a fictional ceramics business; only LLM_API_KEY is needed. Tell the user the answer is about sample data. Add --sample to use the sample even when their account is set up. The sample lives in its own dataset, google_workspace_memory_sample, and never mixes with the user's data.

  1. Run uv run python examples/cookbooks/google_workspace_memory/google_workspace_memory.py --check.
    • Exit 0: go to step 2.
    • Exit 2: each [setup] MISSING: line names one fix. Don't create credentials yourself. Tell the user exactly which line to fix, using the README's "What it needs" table, and stop. If only GOOGLE_DRIVE_FOLDER_ID is missing, ask whether to run with --no-drive instead.
  2. Run uv run python examples/cookbooks/google_workspace_memory/google_workspace_memory.py. Add --ask "..." with the user's question if they asked one, and --no-calendar, --no-gmail or --no-drive for any app they don't want used. The first run opens the browser once per app for consent; tell the user to approve each one.
  3. The answer is everything after the line [ask] Answer:. Give it to the user, and say which sources went in (the [ingest_calendar], [ingest_gmail] and [ingest_drive] lines).

If the user runs cognee as a server with their Google account connected there, add --api to both commands: the server syncs and answers, and --check reports each app that is not connected yet (the README's "Through a cognee server" section says how to connect it).

If a run stops after --check passed, the last [<step>] line (or the traceback) says why. Tell the user what failed; rerun only that step's script from scripts/ once it is fixed.

For a follow-up question on the same data, run uv run python examples/cookbooks/google_workspace_memory/scripts/ask.py --ask "...", with --sample if the first run was on the sample; it doesn't ingest again.

Rules

  • Google access is read-only: nothing is created, changed or sent.
  • Don't print the contents of credentials.json, the *_token.json files or .env.
  • A sample run forgets the sample's dataset google_workspace_memory_sample before it ingests (the [clear] line). On the user's own data (google_workspace_memory), pass --clear only when they asked to start over: it forgets everything the dataset holds.
  • Ingesting reads the user's real calendar, mailbox and Drive files, and every run uses LLM credits. The first run cognifies the whole primary calendar, which can take ten minutes or more, so tell the user before you start it and run it only when they asked for it.

Clean up

uv run cognee-cli forget --dataset google_workspace_memory
uv run cognee-cli forget --dataset google_workspace_memory_sample