> ## Documentation Index
> Fetch the complete documentation index at: https://docs.seekr.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Create and manage vector stores

> In the SeekrFlow app, create semantic indexes from your documents to power retrieval and agents.

A vector store is a semantic index built from your documents. Language models retrieve relevant information from it, which powers agents and assistants.

SeekrFlow converts each chunk of your documents into a vector embedding. That makes your content searchable by meaning instead of keywords.

> [!NOTE]
>
> This page covers the app. To work with vector stores in code, see [Create and populate a vector database](https://docs.seekr.com/flow/sdk/data-engine/create-and-populate-a-vector-database.md) and [Manage vector databases](https://docs.seekr.com/flow/sdk/data-engine/manage-vector-databases.md) in the SDK guide.

## Create a vector store

**Step 1**

Navigate to **Data Engine > Storage**, then select the **Vector Stores** tab.

**Step 2**

Click **Create Vector Store**.

**Step 3**

Enter the vector store details:

* **Name** – Required. Up to 100 characters.
* **Description** – Optional. Up to 500 characters.
* **Embedding Model** – Select a model. SeekrFlow selects the first model by default. For each model's dimensions, input limits, and language support, see [Embedding models](https://docs.seekr.com/flow/components/models/embedding-models.md).

![The Create Vector Store dialog with the Name and Description fields filled in.](https://mintcdn.com/seekr/Me5IrSz2txrFLsTQ/images/docs/seekrflow-create-vector-store-light.png?fit=max\&auto=format\&n=Me5IrSz2txrFLsTQ\&q=85\&s=c0f50f06f3a80a3003462e8ddd0137a0)

> [!NOTE]
>
> You can't change a store's embedding model in the app after you create it. To use a different model, create a new store and add your files to it.

A **Warning** badge marks a model with non-US origins, which can introduce supply chain risk. Hover over the badge for details.

![The Embedding Model options in the Create Vector Store dialog. Each card shows a country of origin, and some cards show a Warning badge.](https://mintcdn.com/seekr/Me5IrSz2txrFLsTQ/images/docs/seekrflow-vector-store-embedding-models-light.png?fit=max\&auto=format\&n=Me5IrSz2txrFLsTQ\&q=85\&s=a331a6bc765a5fe805881700a0fea4ab)

**Step 4**

Click **Create Vector Store**.

SeekrFlow creates the store and opens its details view.

## Add files to a vector store

Before you add files, check them against the formats and structure in [Prepare files for upload](https://docs.seekr.com/flow/app/prepare-files-for-upload.md).

**Step 1**

In the vector store details view, click **Add Files**.

**Step 2**

Choose where the files come from:

* **Select Files** – Select files you already uploaded to [storage](https://docs.seekr.com/flow/app/upload-and-manage-files.md).
* **Upload Files** – Drag and drop files, or click **Browse**. You can upload up to 20 files at a time, each up to 150 MB. Accepted formats: PDF, Word, PowerPoint, Markdown, and text.

**Step 3**

Optional: Expand **Advanced Embedding Options** and adjust how SeekrFlow segments your content before embedding. Drag a slider or enter a value.

* **Chunk Size (Tokens)** – The maximum token count per chunk. The default is 800.
* **Chunk Overlap (Tokens)** – The number of tokens shared by adjacent chunks. Overlap reduces information loss at chunk boundaries. The default is 400.

![The Add Data to Your Vector Store dialog with a file selected and Advanced Embedding Options expanded to show Chunk Size and Chunk Overlap.](https://mintcdn.com/seekr/Me5IrSz2txrFLsTQ/images/docs/seekrflow-vector-store-add-files-light.png?fit=max\&auto=format\&n=Me5IrSz2txrFLsTQ\&q=85\&s=7f7547d67fe88aadc2153d918c998433)

**Step 4**

Click **Add Files**.

## Track file processing

After you click **Add Files**, SeekrFlow processes each file automatically. It converts compatible files to Markdown when needed, splits the content into chunks based on your settings, converts each chunk to a vector, and stores the vectors in the semantic index.

> [!NOTE]
>
> **Ingestion mode**
>
> Files you add in the app always use speed-optimized ingestion. To use accuracy-optimized ingestion, see [Choose an ingestion method](https://docs.seekr.com/flow/sdk/data-engine/create-and-populate-a-vector-database.md#choose-an-ingestion-method) in the SDK guide.

The **Attached Files** area lists each file with its name, status, and size. When SeekrFlow converts a file, the list shows the converted Markdown file in place of the original. Hover over a file to download it.

![The Attached Files table of a vector store with one file in Processing status and one file in Ready status.](https://mintcdn.com/seekr/Me5IrSz2txrFLsTQ/images/docs/seekrflow-vector-store-files-light.png?fit=max\&auto=format\&n=Me5IrSz2txrFLsTQ\&q=85\&s=83acb4a1021c29ab65c998c7fb81f0bd)

| Status | Description |
| - | - |
| Queued | The file is waiting to be processed |
| Processing | The file is being converted and embedded |
| Ready | The file is indexed and ready for retrieval |

## View vector store details

Click a vector store to open its details view. It shows the store's ID, embedding model, size, file count, creation and modification dates, description, and attached files.

![The Vector Store Details view of a new store, with its ID, model, size, file count, dates, description, and an empty Attached Files area.](https://mintcdn.com/seekr/Me5IrSz2txrFLsTQ/images/docs/seekrflow-vector-store-details-light.png?fit=max\&auto=format\&n=Me5IrSz2txrFLsTQ\&q=85\&s=4c7c4ec0462df61b18c46089cdd7172e)

## Edit, add to, or delete a vector store

Open the store's details view, then choose an action:

* **Edit the description** – Click the edit icon next to it.
* **Add files** – Click **Add Files**.
* **Download a file** – Hover over the file and click the download icon.
* **Remove a file** – Hover over the file and click the remove icon. SeekrFlow removes the file from the store right away.
* **Delete the vector store** – Click the delete icon, then click **Delete Vector Store**. Deleting a store disables any tools connected to it. The files remain in storage.

## Next steps

* [Create an agent](https://docs.seekr.com/flow/app/create-an-agent.md) – Attach a vector store to an agent for retrieval-augmented memory


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.