The `vector` extension in AlloyDB for PostgreSQL provides `pgvector` functions and
operators that let you use your database as a vector store. You can add
`vector` columns to your tables and store generated embeddings as vector values
for semantic search and generative AI workloads.

## Required database extension

Use the `vector` extension, version `0.5.0.google-1` or later, which includes
`pgvector` functions and operators, to store generated embeddings as `vector` values. This
is a version of `pgvector` that Google has extended with optimizations specific
to AlloyDB.

```sql
CREATE EXTENSION IF NOT EXISTS vector;
```

## Store generated embeddings

Ensure that you have already created a table in your AlloyDB database.

> [!NOTE]
> **Note:** If your application uses the LangChain framework and your dataset has `O(100k)` embeddings, we recommend that you use the `AlloyDBVectorStore` vector class included in the AlloyDB LangChain library to store your embeddings. For more information, see [Build LLM-powered applications using
> LangChain](https://docs.cloud.google.com/alloydb/docs/ai/langchain#vector-store-procedure-guide).

To store vector embeddings, do the following:

1. Create a `vector` column in your table to store your embeddings:

   ```sql
   ALTER TABLE TABLE ADD COLUMN EMBEDDING_COLUMN vector(DIMENSIONS);
   ```

   Replace the following:
   - `TABLE`: the table name.

   - `EMBEDDING_COLUMN`: the name of the new embedding column.

   - `DIMENSIONS`: the number of dimensions that the model
     supports.

     For example, if you are using one of the `text-embedding` English models---for example, `text-embedding-005` with Agent Platform, specify `768`.
2. Copy the vectors to the vector column. The following example assumes your embeddings are available in a CSV file:

   ```sql
   COPY TABLE (EMBEDDING_COLUMN) FROM 'PATH_TO_VECTOR_CSV' (FORMAT CSV);
   ```

   <br />

   Replace the following:
   - `TABLE`: the name of the table.

   - `EMBEDDING_COLUMN`: the name of the embedding column.

   - `PATH_TO_VECTOR_CSV`: the full path of where you have stored your `.CSV` file.

After you store the embeddings, you can use the `vector` extension or the `alloydb_scann`
extension to create indexes for faster query performance.

## What's next

- [Create indexes and query vectors](https://docs.cloud.google.com/alloydb/docs/ai/create-scann-index.md.txt)
- [Perform a vector search](https://docs.cloud.google.com/alloydb/docs/ai/perform-vector-search.md.txt)