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

# 🎁 Database

> Create a database for your LLM App

Instead of managing your data, a vector database, an embedding model, a search
algorithm, a PostgreSQL database, and your LLM all in different places...

What if you could do it in one spot, with your teammates?

Like to work in code? Check out our APIs.

<Frame caption="Hybrid database for your regular data and your embeddings">
  <img src="https://mintcdn.com/baseplate/lG0F4fZdc5qZCcZP/images/database.png?fit=max&auto=format&n=lG0F4fZdc5qZCcZP&q=85&s=f78c2f2c501e3ab387a975472604141a" width="4024" height="2218" data-path="images/database.png" />
</Frame>

## Create Columns

<Frame caption="Add data, metadata, and embedding columns">
  <img src="https://mintcdn.com/baseplate/lG0F4fZdc5qZCcZP/images/create-columns.png?fit=max&auto=format&n=lG0F4fZdc5qZCcZP&q=85&s=89c681cecaf54b706d0f08a3109f7e3f" width="1292" height="626" data-path="images/create-columns.png" />
</Frame>

A Baseplate database is as flexible as a spreadsheet. You can create any number
of columns, and edit them directly from the UI.

1. Embedding Columns <br /> The content in these columns will be embedded using
   the embedding model you select
2. Data Columns <br /> Typically images, urls, code snippets, or links that you'd
   like to be returned with your search result
3. Metadata Columns <br /> Really useful for large datasets to make sure you're
   getting relevant vectors. Segment your data based on customer, datasource,
   version, date, or whatever your prefer!
4. Image Columns <br /> Drag and Drop or import images for use as image references.

## Adding Documents

1. Add a whole document <br /> You can use Baseplate's built in parsing
   capabilities to break documents into chunks for embedding. Specify a chunk
   size and which column to add the chunks to, and we'll do the rest
2. Add context chunk-by-chunk <br /> For more nuanced indices, upload rows to
   Baseplate via API once you've chunked them

<Frame>
  <img src="https://mintcdn.com/baseplate/lG0F4fZdc5qZCcZP/images/adding-documents.png?fit=max&auto=format&n=lG0F4fZdc5qZCcZP&q=85&s=9bdea608768fb8389e50d1a803c635d0" alt="" width="1486" height="1524" data-path="images/adding-documents.png" />
</Frame>

## Updating Vectors

Edit your vectors from the interface or through the API. We'll automatically
handle the embedding, updating of your text representation, and upsert of the
new vector.

<Frame>
  <img src="https://mintcdn.com/baseplate/lG0F4fZdc5qZCcZP/images/updating-vectors.png?fit=max&auto=format&n=lG0F4fZdc5qZCcZP&q=85&s=6352ffe22fc32fa7d7adacb440f05a0c" alt="" width="3454" height="1790" data-path="images/updating-vectors.png" />
</Frame>

## Manage Documents

<Frame caption="Manage your Database">
  <img src="https://mintcdn.com/baseplate/lG0F4fZdc5qZCcZP/images/manage-documents.png?fit=max&auto=format&n=lG0F4fZdc5qZCcZP&q=85&s=b220aa4353b38e80c0f9a550b059d5d7" width="3680" height="2256" data-path="images/manage-documents.png" />
</Frame>

You can view, edit, replace, and delete your documents at once, instead of going
row-by-row. See our API for a guide on replacing old data.

## Auto Embedding

<Frame caption="Automatically caption and embed images.">
  <img src="https://mintcdn.com/baseplate/lG0F4fZdc5qZCcZP/images/auto-embed.png?fit=max&auto=format&n=lG0F4fZdc5qZCcZP&q=85&s=877f89dfa56c66afd62d67d554382362" width="212" height="127" data-path="images/auto-embed.png" />
</Frame>

Enable auto embedding on an image column to automatically generate a caption for the uploaded image. This is useful for when you want to search for images based on their content.
The caption is added to the row's text embedding.
