---
title: "VAST Vector Search cheat sheet"
slug: "dev-vector-search-reference-cheat-sheet"
description: "Explore VAST Vector Search in Cluster 5.5: create vector-indexed tables, search efficiently, and connect with the Query Engine for optimal results."
updated: 2026-10-30T18:19:01Z
published: 2026-10-30T18:19:01Z
canonical: "docs.vastdata.com/dev-vector-search-reference-cheat-sheet"
---

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

# VAST Vector Search cheat sheet

*Applies to VAST Cluster 5.5. Examples use the VAST DataBase Python SDK 2.1.0.*

A one-page summary of VAST Vector Search in VAST Cluster 5.5: create a vector-indexed table, search it, and connect. Each item links to the page with the details.

## Create a table with a vector index

```
CREATE TABLE "bucket/schema".t (
  id BIGINT,
  embedding VECTOR(FLOAT, 1024)
)
VECTOR CLUSTER BY embedding (
  metric = 'l2sq',                      -- l2sq | cosine | ip
  cluster_quantization = 'scalar_8bit', -- default if omitted
  search_quantization = 'scalar_8bit'   -- default if omitted
);
```

There's no `CREATE VECTOR INDEX`: the index is created with the table, and can't be added, changed or dropped later. See [SQL reference](/develop/docs/dev-vector-search-reference-sql#create-table-with-a-vector-index).

## Search

```
SELECT id,
  array_distance(embedding::FLOAT[1024], ARRAY[...]::FLOAT[1024]) AS dist
FROM "bucket/schema".t
ORDER BY dist LIMIT 10;
```

| Metric | Order by |
| --- | --- |
| `l2sq` | `array_distance` |
| `cosine` | `array_cosine_distance` |
| `ip` | `array_negative_inner_product` |

To use the index: one distance expression in `ORDER BY`, ascending, with `LIMIT k`. No `OFFSET`, and no similarity sorted descending. `EXPLAIN` shows `VAST_VEC_INDEX_SCAN` when the index is used. See [query design](/develop/docs/dev-vector-search-guides-query-design).

## Quantization pairs

| Cluster / search | Allowed? |
| --- | --- |
| omitted / omitted | Yes: `scalar_8bit` / `scalar_8bit` |
| `none` / `none` | Yes |
| `none` / `scalar_8bit` | Yes |
| `scalar_8bit` / `scalar_8bit` | Yes |
| `scalar_8bit` / `none` | No |

See [quantization](/develop/docs/dev-vector-search-guides-quantization).

## Connect

- Endpoint: a VAST Query Engine endpoint, on a virtual IP pool with the Query Engine role, with the cluster's S3 port (for example `http://<qe-vip>:9090`). See [setup](/develop/docs/dev-vector-search-operations-setup#which-endpoint-does-what).
- Permissions: `s3:QueryEngine*` and the `s3:Tabular*` actions on the bucket. The Python SDK also needs `s3:ListBucket`.
- ADBC options: `vast.db.endpoint`, `vast.db.access_key`, `vast.db.secret_key`. Connect with `autocommit=True`, or commit, or your DDL is lost. See [ADBC](/develop/docs/dev-vector-search-integrations-adbc).
- Search tuning: `vast.db.setting.vector_search_min_prob`, `vector_search_max_prob` and `vector_search_pruning_distance_ratio` (four comma-separated values each), set on the connection with `set_options`. See [search session settings](/develop/docs/dev-vector-search-reference-configuration).

**Admin task: send to your platform team.** The Query Engine VIP pool and the permissions. See [setup](/develop/docs/dev-vector-search-operations-setup) and [security](/develop/docs/dev-vector-search-operations-security).

## Python SDK

```
from vastdb import VectorIndexSpec

table = schema.create_table("t", columns,
                            vector_index=VectorIndexSpec(column="embedding", distance_metric="l2sq"))
reader = table.vector_search(vec=q, columns=["id"], limit=10)
```

The result has a `vast_pysdk_vector_dist` column. Don't use `vector_search()` on an `ip` table: it returns the least similar rows first ([Python SDK](/develop/docs/dev-vector-search-integrations-python-sdk#inner-product-indexes-search-with-sql)). Signatures: [SDK reference](/develop/docs/dev-database-reference-sdk#vector-index).

## Operations

- Clustering progress: the REST API grades it `A+`, `A`, `B` or `C` (`clustering_progress_label`). `C` doesn't mean the index is unused. See [performance](/develop/docs/dev-vector-search-operations-performance#check-the-index-first).
- Replication: not supported for vector-indexed tables. See [limits](/develop/docs/dev-vector-search-reference-limits#table-rules).
- Trino and Spark don't use the vector index: search through the VAST Query Engine. See [limits](/develop/docs/dev-vector-search-reference-limits#search-rules).

## See also

- [SQL reference](/develop/docs/dev-vector-search-reference-sql)
- [Limits](/develop/docs/dev-vector-search-reference-limits)
- [Release notes](/develop/docs/dev-vector-search-release-notes)