> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.twelvelabs.io/v1.3/agents/guides/create-a-knowledge-store/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.twelvelabs.io/_mcp/server.

# Create a knowledge store

This guide shows you how to create a knowledge store and optionally customize what the platform extracts during indexing.

# Key concepts

* **Knowledge store**: A persistent store of your videos and images plus the understanding the platform derives from them - spatiotemporal context, a typed ontology, and embeddings - that together enable corpus-level reasoning.

# Prerequisites

* To use the platform, you need an API key:

  If you don't have an account, [sign up](https://playground.twelvelabs.io/) for a free account.

  Go to the [API Keys](https://playground.twelvelabs.io/dashboard/api-keys) page.

  If you need to create a new key, select the **Create API Key** button. Enter a name and set the expiration period. The default is 12 months.

  Select the **Copy** icon next to your key to copy it to your clipboard.

* Depending on the programming language you are using, install the TwelveLabs SDK by entering one of the following commands:

  **`Python`**

  ```shell Python
  pip install --upgrade twelvelabs
  ```

  **`Node.js`**

  ```shell Node.js
  yarn add twelvelabs-js@latest # or npm install twelvelabs-js@latest
  ```

# Example

Copy and paste the code below, replacing the placeholders surrounded by `<>` with your values.

**`Python`**

```python Python maxlines=13
from twelvelabs import TwelveLabs

client = TwelveLabs(api_key="<YOUR_API_KEY>")

store = client.knowledge_stores.create(
    name="<YOUR_KNOWLEDGE_STORE_NAME>",
    # ingestion_config=...,  # Optional. Shape what the platform extracts during indexing.
    # metadata={"team": "marketing", "quarter": "2026-Q1"},  # Optional. Up to 10 key-value pairs.
)
print(f"Knowledge store created: {store.id}")
```

**`Node.js`**

```javascript Node.js maxlines=13
import { TwelveLabs } from "twelvelabs-js";

const client = new TwelveLabs({ apiKey: "<YOUR_API_KEY>" });

const store = await client.knowledgeStores.create({
  name: "<YOUR_KNOWLEDGE_STORE_NAME>",
  // ingestionConfig: ...,  // Optional. Shape what the platform extracts during indexing.
  // metadata: { team: "marketing", quarter: "2026-Q1" },  // Optional. Up to 10 key-value pairs.
});
console.log(`Knowledge store created: ${store.id}`);
```

# Code explanation

#### Python

To create a knowledge store, call the [`knowledge_stores.create`](/v1.3/sdk-reference/python/knowledge-stores#create-a-knowledge-store) method.\

**Parameters**:

* `name`: A name for the knowledge store.
* *(Optional)* `ingestion_config`: An object that shapes what the platform extracts from your content during indexing. For the available approaches, see the [Configure ingestion](/v1.3/agents/guides/create-a-knowledge-store/configure-ingestion) page.
* *(Optional)* `metadata`: An object of up to 10 key-value pairs to label and organize your stores. Keys are strings; values can be a string, a number, a boolean, or an array of strings.\


**Return value**: An object of type `KnowledgeStore` with a field named `id` representing the unique identifier of the newly created knowledge store.

#### Node.js

To create a knowledge store, call the [`knowledgeStores.create`](/v1.3/sdk-reference/node-js/knowledge-stores#create-a-knowledge-store) method. You pass all parameters as properties of a single object.\

**Parameters**:

* `name`: A name for the knowledge store.
* *(Optional)* `ingestionConfig`: An object that shapes what the platform extracts from your content during indexing. For the available approaches, see the [Configure ingestion](/v1.3/agents/guides/create-a-knowledge-store/configure-ingestion) page.
* *(Optional)* `metadata`: An object of up to 10 key-value pairs to label and organize your stores. Keys are strings; values can be a string, a number, a boolean, or an array of strings.\


**Return value**: An `HttpResponsePromise` that resolves to an object of type `KnowledgeStore` with a field named `id` representing the unique identifier of the newly created knowledge store.

# Next steps

* [Add assets to a knowledge store](/v1.3/agents/guides/add-assets) - add your uploaded assets to the knowledge store for indexing

# Jupyter notebook

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/twelvelabs-io/twelvelabs-developer-experience/blob/main/quickstarts/jockey/guides/building_knowledge_stores.ipynb)

## Docs

- [Configure ingestion](https://docs.twelvelabs.io/agents/guides/create-a-knowledge-store/configure-ingestion.md)