> ## Documentation Index
> Fetch the complete documentation index at: https://docs.camel-ai.org/llms.txt
> Use this file to discover all available pages before exploring further.
# Camel.storages.vectordb storages.pgvector
## PgVectorStorage
```python theme={"system"}
class PgVectorStorage(BaseVectorStorage):
```
PgVectorStorage is an implementation of BaseVectorStorage for
PostgreSQL with pgvector extension.
This class provides methods to add, delete, query, and manage vector
records in a PostgreSQL database using the pgvector extension.
It supports different distance metrics for similarity search.
**Parameters:**
* **vector\_dim** (int): The dimension of the vectors to be stored.
* **conn\_info** (Dict\[str, Any]): Connection information for psycopg2.connect.
* **table\_name** (str, optional): Name of the table to store vectors. (default: :obj:`None`)
* **distance** (VectorDistance, optional): Distance metric for vector comparison. (default: :obj:`VectorDistance.COSINE`)
### **init**
```python theme={"system"}
def __init__(
self,
vector_dim: int,
conn_info: Dict[str, Any],
table_name: Optional[str] = None,
distance: VectorDistance = VectorDistance.COSINE,
**kwargs: Any
):
```
Initialize PgVectorStorage.
**Parameters:**
* **vector\_dim** (int): The dimension of the vectors.
* **conn\_info** (Dict\[str, Any]): Connection info for psycopg2.connect.
* **table\_name** (str, optional): Table name. (default: :obj:`None`)
* **distance** (VectorDistance, optional): Distance metric. (default: :obj:`VectorDistance.COSINE`)
### \_ensure\_table
```python theme={"system"}
def _ensure_table(self):
```
Ensure the vector table exists in the database.
Creates the table if it does not exist.
### \_ensure\_index
```python theme={"system"}
def _ensure_index(self):
```
Ensure vector similarity search index exists for better
performance.
### add
```python theme={"system"}
def add(self, records: List[VectorRecord], **kwargs: Any):
```
Add or update vector records in the database.
**Parameters:**
* **records** (List\[VectorRecord]): List of vector records to add or update.
### delete
```python theme={"system"}
def delete(self, ids: List[str], **kwargs: Any):
```
Delete vector records from the database by their IDs.
**Parameters:**
* **ids** (List\[str]): List of record IDs to delete.
### query
```python theme={"system"}
def query(self, query: VectorDBQuery, **kwargs: Any):
```
Query the database for the most similar vectors to the given
query vector.
**Parameters:**
* **query** (VectorDBQuery): Query object containing the query vector and top\_k. \*\*kwargs (Any): Additional keyword arguments for the query.
**Returns:**
List\[VectorDBQueryResult]: List of query results sorted by
similarity.
### status
```python theme={"system"}
def status(self, **kwargs: Any):
```
Get the status of the vector database, including vector
dimension and count.
**Returns:**
VectorDBStatus: Status object with vector dimension and count.
### clear
```python theme={"system"}
def clear(self):
```
Remove all vectors from the storage by truncating the table.
### load
```python theme={"system"}
def load(self):
```
Load the collection hosted on cloud service (no-op for pgvector).
This method is provided for interface compatibility.
### close
```python theme={"system"}
def close(self):
```
Close the database connection.
### **del**
```python theme={"system"}
def __del__(self):
```
Ensure connection is closed when object is destroyed.
### client
```python theme={"system"}
def client(self):
```
**Returns:**
Any: The underlying psycopg connection object.