> ## Documentation Index
> Fetch the complete documentation index at: https://docs.turingdb.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Vector Search
> Search through high-dimensional embeddings and connect the results to your graph data
TuringDB has a built-in vector index that lets you run k-nearest-neighbor searches over embedding vectors. You bring your own embeddings, from any model or provider, and TuringDB handles the indexing, storage, and fast retrieval.
Each vector is associated with a numerical ID. That ID can be a node property, an edge property, or a foreign key referencing data in an external system. This keeps the index lightweight and flexible: the vector store doesn't need to know what your data looks like.
Vector indexes live at the TuringDB root level, independent of graphs and versioning. A single vector index can serve searches across multiple graphs and commits.
## Create a vector index
A vector index is defined by a name, a dimension, and a distance metric.
**Syntax:**
```
CREATE VECTOR INDEX WITH DIMENSION METRIC
```
| Parameter | Description |
| ---------- | ------------------------------------------------------------------------------ |
| `` | Identifier for the vector index |
| `` | Dimension of the embedding vectors (positive integer) |
| `` | Distance metric: `EUCLID` (Euclidean distance) or `COSINE` (cosine similarity) |
```jsx theme={null}
CREATE VECTOR INDEX doc_embeddings WITH DIMENSION 768 METRIC COSINE
```
```python theme={null}
client.query("CREATE VECTOR INDEX doc_embeddings WITH DIMENSION 768 METRIC COSINE")
```
## Load embeddings
Once the index exists, load your pre-computed embeddings from a file. Each row in the file maps a numerical ID to a vector.
The file path is relative to your TuringDB data directory (`~/.turing/data` by default).
The TuringDB data directory defaults to `~/.turing/data`. You can change it at startup with the `-turing-dir` flag.
**Syntax:**
```
LOAD VECTOR FROM "" IN
```
| Parameter | Description |
| -------------- | -------------------------------------------------------------------- |
| `` | Path to the embeddings file, relative to the TuringDB data directory |
| `` | Name of the target vector index |
```jsx theme={null}
LOAD VECTOR FROM "document_vectors.csv" IN doc_embeddings
```
```python theme={null}
client.query('LOAD VECTOR FROM "document_vectors.csv" IN doc_embeddings')
```
## Search
`VECTOR SEARCH` finds the k nearest neighbors of a query vector and yields their IDs. It is a read statement, so you can chain it with `MATCH` to pull back the actual graph data.
**Syntax:**
```
VECTOR SEARCH IN FOR () YIELD
```
| Parameter | Description |
| -------------- | -------------------------------------------------------- |
| `` | Name of the vector index to search |
| `` | Number of nearest neighbors to return (positive integer) |
| `` | Query vector as a list literal of float values |
| `` | Variable name to hold the result IDs |
### Standalone search
```jsx theme={null}
VECTOR SEARCH IN doc_embeddings FOR 5 (0.12, 0.45, 0.78, 0.33) YIELD ids
RETURN ids
```
```python theme={null}
df = client.query("""
VECTOR SEARCH IN doc_embeddings FOR 5 (0.12, 0.45, 0.78, 0.33) YIELD ids
RETURN ids
""")
print(df)
```
### Combining with MATCH
This is where it gets interesting. Chain `VECTOR SEARCH` with a `MATCH` clause to join the nearest-neighbor IDs back to your graph:
```jsx theme={null}
VECTOR SEARCH IN doc_embeddings FOR 10 (0.12, 0.45, 0.78, 0.33) YIELD ids
MATCH (d:Document) WHERE d.id = ids
RETURN d.title, d.summary
```
```python theme={null}
df = client.query("""
VECTOR SEARCH IN doc_embeddings FOR 10 (0.12, 0.45, 0.78, 0.33) YIELD ids
MATCH (d:Document) WHERE d.id = ids
RETURN d.title, d.summary
""")
print(df)
```
The `ids` variable works exactly like a variable introduced by `CALL ... YIELD`, so any subsequent `MATCH` clause can reference it.
## Manage indexes
### List all vector indexes
```jsx theme={null}
SHOW VECTOR INDEXES
```
### Delete a vector index
```jsx theme={null}
DELETE VECTOR INDEX doc_embeddings
```
This removes the index and frees the associated resources.
## Complete workflow
```jsx theme={null}
// 1. Create a vector index for product embeddings
CREATE VECTOR INDEX product_vectors WITH DIMENSION 384 METRIC COSINE
// 2. Load embeddings generated by your model
LOAD VECTOR FROM "product_embeddings.csv" IN product_vectors
// 3. Find the 10 most similar products to a query embedding
VECTOR SEARCH IN product_vectors FOR 10 (0.15, 0.82, 0.44, 0.91) YIELD ids
MATCH (p:Product) WHERE p.id = ids
RETURN p.name, p.price, p.category
// 4. Inspect existing indexes
SHOW VECTOR INDEXES
// 5. Clean up
DELETE VECTOR INDEX product_vectors
```
```python theme={null}
from turingdb import TuringDB
client = TuringDB(host="http://localhost:6666")
# 1. Create a vector index for product embeddings
client.query("CREATE VECTOR INDEX product_vectors WITH DIMENSION 384 METRIC COSINE")
# 2. Load embeddings generated by your model
client.query('LOAD VECTOR FROM "product_embeddings.csv" IN product_vectors')
# 3. Find the 10 most similar products to a query embedding
df = client.query("""
VECTOR SEARCH IN product_vectors FOR 10 (0.15, 0.82, 0.44, 0.91) YIELD ids
MATCH (p:Product) WHERE p.id = ids
RETURN p.name, p.price, p.category
""")
print(df)
# 4. Inspect existing indexes
client.query("SHOW VECTOR INDEXES")
# 5. Clean up
client.query("DELETE VECTOR INDEX product_vectors")
```