/quickstart

description: Interactive onboarding guide — set up Weaviate Cloud, configure credentials, load data, and learn every command
argument-hint:
allowed-tools: Bash, AskUserQuestion, Skill

Weaviate Plugin Quickstart

Welcome the user and walk them through the full setup of the Weaviate plugin, step by step. Be friendly, patient, and thorough — assume the user has never used Weaviate before.

Welcome & Orientation

Greet the user and give a brief overview of what this plugin can do:

• **Search & Query**: Ask questions and get AI-generated answers with citations, or run hybrid/semantic/keyword searches across your data.
• **Collection Management**: Create, list, explore, and inspect collections (like tables in a database, but for vector data).
• **Data Operations**: Import your own data from local CSV/JSON/JSONL files, fetch and filter objects, or load ready-made sample datasets to experiment with.
• **Build Full-Stack Apps**: Use cookbooks to build chatbots, data explorers, RAG pipelines, and AI agents — all powered by Weaviate.

Then ask the user where they are in their journey:

Use AskUserQuestion with these options:

• **"Brand new to Weaviate"** — I don't have an account or cluster yet.
• **"I have a cluster but it's empty"** — I have a Weaviate Cloud account but no data in it yet.
• **"I have a cluster with data"** — I'm ready to start querying.

Route them accordingly:

• Brand new → Continue to Step 2
• Cluster but empty → Skip to Step 3
• Cluster with data → Skip to Step 5

Sign Up for Weaviate Cloud

Guide the user through creating a Weaviate Cloud account:

1. Direct them to **[Weaviate Cloud Console](https://console.weaviate.cloud/signin?utm_source=github&utm_campaign=agent_skills)** to register. 2. Tell them to click either **"Sign in with Google"** or **"Sign in with GitHub"** to sign up. 3. Once registered and logged into the dashboard, guide them to **create a free Sandbox cluster**:

• Click **"+ Create cluster"**
• Choose **Sandbox**
• Enter a cluster name and select a region
• Click **"Create cluster"** and wait for it to be ready (usually a few minute)

4. Once the cluster is ready, they need two environment variables:

• **WEAVIATE_URL**: Copy the "REST Endpoint" URL shown under the "Endpoints" section in the cluster dashboard (ends with `.weaviate.cloud`)
• **WEAVIATE_API_KEY**: Go to **"API Keys"** section and click "+ New key", once the Create API Key popup appears, add an API key name and select "admin" in the "Role(s)" dropdown. Click on "Create Key" and copy it as you will not be able to see it again.

Setting Environment Variables

**Security rule**: Never ask the user to paste or type their API keys into this chat session.

Present the user with the exact steps below. Format them clearly as a numbered checklist they can follow after leaving this session:

---

**Step 1.** Type `/exit` in this chat to quit Claude Code.

**Step 2.** In your terminal, run these two commands (replace the placeholder values with the REST Endpoint URL and API key you copied from the Weaviate Cloud dashboard):

export WEAVIATE_URL="https://your-cluster-name.weaviate.cloud"
export WEAVIATE_API_KEY="your-api-key-here"

These are session-scoped — they only last until you close this terminal window, which is fine for sandbox clusters.

**Step 3.** Relaunch Claude Code from the **same terminal** by running `claude`. It will automatically inherit the environment variables you just set.

**Step 4.** Run the quickstart again:

/weaviate:quickstart

When it asks where you are in your journey, select **"I have a cluster but it's empty"** — this will skip the signup steps and take you straight to loading data.

---

After presenting these steps, **stop here**. Do not continue to Step 3 or beyond — the user needs to exit and come back first.

**If the user chose "I have a cluster but it's empty" or "I have a cluster with data" at the start** (meaning they already have credentials configured), verify the variables are available with a non-leaking check — do not echo actual values:

[ -z "$WEAVIATE_URL" ] && echo "WEAVIATE_URL is NOT set" || echo "WEAVIATE_URL is set"
[ -z "$WEAVIATE_API_KEY" ] && echo "WEAVIATE_API_KEY is NOT set" || echo "WEAVIATE_API_KEY is set"

If either is missing, show the user the same 4-step checklist above and stop.

Verify Prerequisites

Check that the required tools are installed:

python3 --version

uv --version

If `uv` is not installed, offer to install it:

curl -LsSf https://astral.sh/uv/install.sh | sh

Or suggest alternatives: `pip install uv` or `brew install uv`.

Load Data

Ask the user how they want to get data into their cluster:

Use AskUserQuestion with these options:

• **"Load sample data"** — I want to try example datasets to explore the plugin.
• **"Import my own data"** — I have a CSV, JSON, or JSONL file I want to import.
• **"Create an empty collection"** — I just want to set up a schema and add data later.
• **"Skip for now"** — I'll add data later, just show me the commands.

If "Load sample data":

Ask which domain interests them using AskUserQuestion:

• **"Academic"** — AI/ML research papers from Arxiv → creates `AI_Arxiv` collection
• **"Finance"** — Synthetic Indian Income Tax Returns → creates `Income_Tax_Returns` collection
• **"E-commerce"** — Product catalog with pricing and categories → creates `Product_Catalog` collection
• **"Medical"** — Hair disease information → creates `Hair_Medical` collection
• **"Customer Support"** — IT helpdesk support tickets → creates `IT_Support_Tickets` collection

Then run the example data script for their chosen domain:

uv run ${CLAUDE_PLUGIN_ROOT}/skills/weaviate/scripts/example_data.py --domain "CHOSEN_DOMAIN"

Valid `--domain` values: `academic` (default), `finance`, `ecommerce`, `medical`, `customer_support`.

After it completes, confirm the collection was created:

uv run