• PROVISION
  • VALIDATE
  • AUDIT
  • HUMAN

How to create and test vector indexes with your AI

Connect your agent to Redis to automate index setup. Once connected, your AI handles the provisioning and validation of your vector search structures.

Ask AI about this page

Short answer

How can I create and test vector indexes using my AI?

Your agent uses specific tools to provision RediSearch indexes and check their settings against your embedding dimensions. You'll get a verified index ready for vector similarity searches.

The outcomes of this task.

Where your data lands.

Your agent moves from initial setup to a fully validated search index.

PROVISION

New index created

The AI sets up a new RediSearch index with the specific vector parameters you require. You get a fresh entry in your database.

VALIDATE

Configuration check

The agent compares the index settings against your embedding model's dimensions. This ensures your vector math actually works.

AUDIT

Index inspection

Your agent pulls the current metadata for any existing index. You can verify exactly how the vector space is structured.

HUMAN

Manual adjustment

The AI flags dimension mismatches or configuration errors. You decide whether to drop the index or tweak the parameters.

The workflow

What your AI does when the request arrives.

The agent acts as a bridge between your high-level intent and the Redis database commands.

  1. Setup the index

    The agent defines the vector dimensions and distance metrics needed for your specific embedding model.

    create_vector_index

  2. Verify the structure

    The agent pulls the technical details of the newly created index to confirm it matches your requirements.

    get_index_info

  3. Check existing indexes

    The agent looks through your current Redis environment to prevent naming collisions or duplicate setups.

    list_indexes

  4. Report mismatches

    The agent compares the index metadata against your model's output to find errors.

    get_index_info

Try it

Copy these to start.

Use these prompts to kick off the indexing process.

Starting points

Replace the bracketed text with your specific model dimensions or index names.

Redis Vector Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_zP1SqypHeKOFu0yRPw2yTUOrfnlmdOQBZrAWkuF4/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Redis Vector capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "redis-vector-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_zP1SqypHeKOFu0yRPw2yTUOrfnlmdOQBZrAWkuF4/mcp"
    }
  }
}
Copy into chat04

  • Create a new vector index named 'user_embeddings' with 1536 dimensions.

  • List all my current indexes and tell me which ones use cosine similarity.

  • Check the configuration of the 'product_search' index and verify it matches a 768-dimension model.

  • Show me the details for the index named 'doc_vectors' so I can check the distance metric.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Redis Vector once, then ask.

Just link your account once. Your credentials stay encrypted, and you can immediately start managing indexes through your agent.

Connect Redis Vector to your AI

FAQ

How this task behaves.

  • 01

    Can the AI delete my existing indexes?

    No. The agent only has tools to create, list, and inspect indexes. It cannot delete or drop them.

  • 02

    Will the AI fix a dimension mismatch automatically?

    No. The AI will identify the mismatch by checking the index info, but you must decide how to fix it.

  • 03

    Does the AI handle the actual data ingestion?

    No. This agent focuses on the index structure and configuration, not the insertion of individual vectors.

  • 04

    Can I see all my indexes at once?

    Yes. The agent can pull a full list of all existing indexes in your Redis instance.

  • 05

    How does the AI know if the index is correct?

    It uses the index metadata to compare the configured dimensions and distance metrics against your model's specs.

  • More questions about Redis Vector? The Connector page answers them. See everything the Redis Vector Connector can do

Connect Redis Vector to Claude, Cursor, ChatGPT & more