Pp Weaviate Collections

<!-- GENERATED FILE — DO NOT EDIT.
     This file is a verbatim mirror of library/developer-tools/weaviate-collections/SKILL.md,
     regenerated post-merge by tools/generate-skills/. Hand-edits here are
     silently overwritten on the next regen. Edit the library/ source instead.
     See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->

Weaviate Collections — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the weaviate-collections-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:

   npx -y @mvanhorn/printing-press-library install weaviate-collections --cli-only

2. Verify: weaviate-collections-pp-cli --version
3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:

go install github.com/mvanhorn/printing-press-library/library/developer-tools/weaviate-collections/cmd/weaviate-collections-pp-cli@latest

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

Manage every aspect of Weaviate collections — vectorizers, replication, sharding, multi-tenancy, and property indexes — from the command line. Unlike the official weaviate-cli or community tools, this CLI keeps a local history of your collection configs so you can diff, lint, and roll back with confidence.

When to Use This CLI

Use this CLI to create, inspect, and tune Weaviate Cloud collections — vectorizer/replication/sharding/multi-tenancy config, property indexes, and shard management — and to track how collection configs change over time.

Anti-triggers

Do not use this CLI for:

• Do not use this CLI for inserting, querying, or searching data objects — it only manages collection (schema) config, not object data.
• Do not use this CLI for self-hosted Weaviate cluster administration (nodes, backups, RBAC) — it targets the schema surface only.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Local state that compounds

• schema snapshot — Save a point-in-time copy of every collection's config to the local store, then browse history over time.

  Use before any risky schema change so you have a rollback reference.

  weaviate-collections-pp-cli schema snapshot --label pre-migration

• schema diff — Diff a collection's live config against a saved snapshot or another collection.

  Catch unintended config drift between environments or over time.

  weaviate-collections-pp-cli schema diff Article --against pre-migration

Reachability mitigation

• collections lint — Flag risky collection configs: no vectorizer set, replication factor of 1, unindexed high-cardinality properties.

  Catch production-readiness gaps before they bite in an incident.

  weaviate-collections-pp-cli collections lint Article

Agent-native plumbing

• tenants audit — See tenant counts and activity status across every collection in one view.

  Spot inactive or overloaded tenants across a multi-tenant deployment at a glance.

  weaviate-collections-pp-cli tenants audit --json

• schema export — Export every collection's config as one portable JSON bundle for backup or promotion to another environment.

  Promote a schema from staging to production, or restore after an incident, without full data backup.

  weaviate-collections-pp-cli schema export --output schema-bundle.json

Command Reference

indexes — Manage indexes

• weaviate-collections-pp-cli indexes <className> — Returns per-property index state including active reindex progress. This powers the UI to show live migration status.

properties — Manage properties

• weaviate-collections-pp-cli properties <className> — Adds a new property definition to an existing collection (className) definition.

schema — Manage schema

• weaviate-collections-pp-cli schema dump — Retrieves the definitions of all collections (classes) currently in the database schema.
• weaviate-collections-pp-cli schema objects-create — Defines and creates a new collection (class). If [AutoSchema](https://docs.weaviate.
• weaviate-collections-pp-cli schema objects-delete — Removes a collection definition from the schema.
• weaviate-collections-pp-cli schema objects-get — Retrieve the definition of a specific collection (className), including its properties, configuration
• weaviate-collections-pp-cli schema objects-update — Updates the configuration settings of an existing collection (className) based on the provided definition.

shards — Manage shards

• weaviate-collections-pp-cli shards get — Retrieves the status of all shards associated with the specified collection (className).
• weaviate-collections-pp-cli shards update — Updates the status of a specific shard within a collection (e.g., sets it to READY or READONLY).

tenants — Manage tenants

• weaviate-collections-pp-cli tenants create — Creates one or more new tenants for a specified collection (className).
• weaviate-collections-pp-cli tenants delete — Deletes one or more specified tenants from a collection (className).
• weaviate-collections-pp-cli tenants exists — Checks for the existence of a specific tenant within the given collection (className).
• weaviate-collections-pp-cli tenants get — Retrieves a list of all tenants currently associated with the specified collection.
• weaviate-collections-pp-cli tenants get-one — Retrieves details about a specific tenant within the given collection (className)
• weaviate-collections-pp-cli tenants update — Updates the activity status (e.g., ACTIVE, INACTIVE, etc.

vectors — Manage vectors

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

weaviate-collections-pp-cli which "<capability in your own words>"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query.

Recipes

Snapshot before a risky change

weaviate-collections-pp-cli schema snapshot --label pre-change && weaviate-collections-pp-cli schema objects-update Article --replication-config-factor 3

Save a rollback reference, then apply the change.

Diff a select subset of a large collection config

weaviate-collections-pp-cli schema objects-get Article --agent --select class,vectorizer,replicationConfig

Pull only the fields that matter instead of the full nested config blob.

Auth Setup

Run weaviate-collections-pp-cli auth setup for the URL and steps to obtain a token (add --launch to open the URL). Then store it:

echo "$WEAVIATE_API_KEY" | weaviate-collections-pp-cli auth set-token

Or set WEAVIATE_API_KEY as an environment variable directly (no auth set-token needed).

You also need WEAVIATE_COLLECTIONS_BASE_URL set to your own Weaviate Cloud cluster URL (e.g. https://your-cluster-id.weaviate.cloud/v1, found in the Weaviate Cloud console). Every cluster has a unique hostname, so there is no usable default.

Run weaviate-collections-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.

• Pipeable — JSON on stdout, errors on stderr

• Filterable — --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:

  weaviate-collections-pp-cli indexes mock-value --agent --select id,name,status

• Previewable — --dry-run shows the request without sending

• Offline-friendly — sync/search commands can use the local SQLite store when available

• Non-interactive — never prompts, every input is a flag

• Explicit retries — use --idempotent only when an already-existing create should count as success, and use --ignore-missing only when a missing delete target should count as success

Response envelope

Commands that read from the local store or the API wrap output in a provenance envelope:

{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}

Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout.

Paths and state

Agents should treat the CLI's path resolver as part of the runtime contract:

• Use --home <dir> for one invocation, or set WEAVIATE_COLLECTIONS_HOME=<dir> to relocate all four path kinds under one root.

• Use per-kind env vars only when a specific kind must diverge: WEAVIATE_COLLECTIONS_CONFIG_DIR, WEAVIATE_COLLECTIONS_DATA_DIR, WEAVIATE_COLLECTIONS_STATE_DIR, WEAVIATE_COLLECTIONS_CACHE_DIR.

• Resolution order is per-kind env var, --home, WEAVIATE_COLLECTIONS_HOME, XDG (XDG_CONFIG_HOME, XDG_DATA_HOME, XDG_STATE_HOME, XDG_CACHE_HOME), then platform defaults.

• config contains settings like config.toml and profiles. data contains credentials.toml, data.db, cookies, and auth sidecars. state contains persisted queries, jobs, and teach.log. cache contains regenerable HTTP/cache files.

• Stored secrets live in credentials.toml under the data dir. Existing legacy config.toml secrets are read for compatibility and leave config.toml on the first auth write.

• Run weaviate-collections-pp-cli doctor --fail-on warn to surface path and credential-location warnings. agent-context exposes a schema v4 paths block for agents that need the resolved dirs.

• For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags:

  {
    "mcpServers": {
      "weaviate-collections": {
        "command": "weaviate-collections-pp-mcp",
        "env": {
          "WEAVIATE_COLLECTIONS_HOME": "/srv/weaviate-collections"
        }
      }
    }
  }

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use WEAVIATE_COLLECTIONS_HOME or per-kind vars as durable fleet levers, and use --home only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing WEAVIATE_COLLECTIONS_HOME, or doctor will not find credentials left under the former root.

Automatic learning

This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a flag_alias candidate, and a teach on a query family without a playbook auto-synthesizes a playbook_candidate from the session's journal. Your job is judgment only: recall first, act on surfaced candidates, teach the final answer, playbook amend when you observe a correction. You never record failures by hand.

Step 1: recall before any discovery

Before list/search/drill commands on a new user question, run:

weaviate-collections-pp-cli recall "<user's question>" --agent

The response envelope:

{
  "query": "...",
  "normalized": "<normalized form>",
  "query_entities": ["..."],
  "found": true | false,
  "match_score": 0.0,
  "results": [
    { "resource_id": "...", "resource_type": "...", "venue": "...",
      "confidence": 2, "entity_match": "exact|partial|unknown",
      "source": "taught|preseed|pattern", "warnings": ["..."] }
  ],
  "mismatches": [ /* only when --debug-mismatches */ ],
  "warnings": [ /* top-level */ ],
  "candidates": [
    { "id": 12, "class": "flag_alias | playbook_candidate",
      "summary": "...", "sightings": 3, "last_seen": "...",
      "rationale": "...",
      "next_action": ["<trial command>", "weaviate-collections-pp-cli learnings confirm 12"] }
  ],
  "playbook": {
    "query_family": "...",
    "playbook": {
      "steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
      "entity_slots": ["$ENTITY"],
      "expected_tool_calls": 3
    },
    "slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
    "notes": "<workarounds + gotchas for this query family>"
  },
  "notes": "<duplicate surface for non-playbook callers>"
}

Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and learnings list and learnings candidates are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught.

Step 2: decision tree

Read candidates, playbook, notes, results[0], and warnings in that order:

if Candidates present (warnings include "candidates_present"):
    -> candidates are try-then-confirm, never facts. Follow each candidate's
       two-step next_action verbatim: run the trial command first, then run
       `learnings confirm <id>` only after the trial verified the behavior.
       Reject a wrong candidate with `learnings reject <id>`.
    -> NEVER re-teach something recall surfaced as a candidate; confirm or
       reject that candidate instead of teaching a duplicate.
    -> candidates ride alongside playbooks and resource hits, not instead of
       them; continue with the branches below after acting on them.

if Playbook present:
    -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose)
    -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries
       for the entity slot tokens. If a step's slot is unresolved, fall back to
       discovery for that step only.
    -> the Playbook's expected_tool_calls is a budget; if you find yourself running
       materially more, record the divergence via `weaviate-collections-pp-cli playbook amend`
       at end-of-session.

elif Notes present (no Playbook):
    -> read Notes verbatim before any discovery step; they carry known gotchas
       for this query family even when no structured choreography exists yet.

elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2:
    -> skip discovery; fetch live data for Results[*].ResourceID in parallel

elif Found AND Results[0].EntityMatch == "partial":
    -> candidate hint, NOT a hit; read the resource title to validate before trusting

elif (any row in Mismatches[] when --debug-mismatches was passed):
    -> treat as cold start; the stored learning is for a different entity
       (different canonical resolved from query_entities)

else:  // Found == false, no playbook, no notes
    -> cold start; run discovery normally; teach the answer afterward (Step 4).
       If the family has no playbook yet, that teach auto-synthesizes a
       playbook candidate from this session's journal - you do not need to
       record one by hand.

Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a Results[] hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping mismatches; pass --debug-mismatches only when investigating cold-start surprises.

Candidate judgment details: learnings confirm <id> prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject <id> tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; weaviate-collections-pp-cli learnings candidates lists the full open set.

Graceful degradation: if learnings confirm is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol.

Step 3: always read warnings

• low_confidence: row exists at confidence<2. Treat as a hint, not a skip-discovery hit.
• resource_not_in_store: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate.
• cross_alias_match (per-result): the row was taught under a different alias and matched the live query's canonical via entity_lookups (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id.
• similar_shape_different_entity:<canonical> (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results.
• ambiguous_alias (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource.
• candidates_present (top-level): the envelope carries a candidates section. Handle it via the candidates branch in Step 2 before anything else.
• lookup_refresh_available (top-level): an entity in the query has no lookup row yet, but synced data could provide one. Run weaviate-collections-pp-cli sync to refresh entity lookups.
• Top-level no_learnings_for_query_family: the table had no rows above the Jaccard floor. Pure cold start.