> ## Documentation Index > Fetch the complete documentation index at: https://docs.ag2.ai/llms.txt > Use this file to discover all available pages before exploring further. # autogen.agentchat.contrib.vectordb.pgvectordb.PGVectorDB
`PGVectorDB`



```python theme={null}
PGVectorDB(
    *,
    conn: ForwardRef('Connection') | None = None,
    connection_string: str | None = None,
    host: str | None = None,
    port: int | str | None = None,
    dbname: str | None = None,
    username: str | None = None,
    password: str | None = None,
    connect_timeout: int | None = 10,
    embedding_function: Callable = None,
    metadata: dict[str, Any] | None = None
)
```

A vector database that uses PGVector as the backend.
Initialize the vector database.
Note: connection\_string or host + port + dbname must be specified

Parameters:

| Name                 | Description                                                                     |
| -------------------- | ------------------------------------------------------------------------------- |
| `conn`               | **Type:** ForwardRef('psycopg.Connection') \| None

**Default:** None |
| `connection_string`  | **Type:** str \| None

**Default:** None                              |
| `host`               | **Type:** str \| None

**Default:** None                              |
| `port`               | **Type:** int \| str \| None

**Default:** None                       |
| `dbname`             | **Type:** str \| None

**Default:** None                              |
| `username`           | **Type:** str \| None

**Default:** None                              |
| `password`           | **Type:** str \| None

**Default:** None                              |
| `connect_timeout`    | **Type:** int \| None

**Default:** 10                                |
| `embedding_function` | **Type:** Callable

**Default:** None                                 |
| `metadata`           | **Type:** dict\[str, typing.Any] \| None

**Default:** None           |

### Class Attributes



#### active\_collection









#### embedding\_function









#### type







### Instance Methods



#### create\_collection

```python theme={null}
create_collection(
    self,
    collection_name: str,
    overwrite: bool = False,
    get_or_create: bool = True
) -> Collection
```

Create a collection in the vector database.
Case 1. if the collection does not exist, create the collection.
Case 2. the collection exists, if overwrite is True, it will overwrite the collection.
Case 3. the collection exists and overwrite is False, if get\_or\_create is True, it will get the collection,
otherwise it raise a ValueError.


Parameters:

| Name              | Description |                                                                                                                                        |
| ----------------- | ----------- | -------------------------------------------------------------------------------------------------------------------------------------- |
| `collection_name` | str         | The name of the collection.

**Type:** str                                                                                   |
| `overwrite`       | bool        | Whether to overwrite the collection if it exists.

Default is False.

**Type:** bool

**Default:** False |
| `get_or_create`   | bool        | Whether to get the collection if it exists.

Default is True.

**Type:** bool

**Default:** True         |

Returns:

| Type                                                                                       | Description                          |
| ------------------------------------------------------------------------------------------ | ------------------------------------ |
| [Collection](/docs/api-reference/autogen/agentchat/contrib/vectordb/pgvectordb/Collection) | Collection \| The collection object. |






#### delete\_collection

```python theme={null}
delete_collection(self, collection_name: str) -> None
```

Delete the collection from the vector database.


Parameters:

| Name              | Description |                                                      |
| ----------------- | ----------- | ---------------------------------------------------- |
| `collection_name` | str         | The name of the collection.

**Type:** str |

Returns:

| Type | Description |
| ---- | ----------- |
| None | None        |






#### delete\_docs

```python theme={null}
delete_docs(
    self,
    ids: list[str | int],
    collection_name: str = None
) -> None
```

Delete documents from the collection of the vector database.


Parameters:

| Name              | Description   |                                                                                                               |
| ----------------- | ------------- | ------------------------------------------------------------------------------------------------------------- |
| `ids`             | List\[ItemID] | A list of document ids.

Each id is a typed `ItemID`.

**Type:** list\[str \| int]        |
| `collection_name` | str           | The name of the collection.

Default is None.

**Type:** str

**Default:** None |

Returns:

| Type | Description |
| ---- | ----------- |
| None | None        |






#### establish\_connection

```python theme={null}
establish_connection(
    self,
    conn: ForwardRef('Connection') | None = None,
    connection_string: str | None = None,
    host: str | None = None,
    port: int | str | None = None,
    dbname: str | None = None,
    username: str | None = None,
    password: str | None = None,
    connect_timeout: int | None = 10
) -> Connection
```

Establishes a connection to a PostgreSQL database using psycopg.


Parameters:

| Name                | Description                                                                                                                                                                                   |
| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `conn`              | An existing psycopg connection object.

If provided, this connection will be used.

**Type:** ForwardRef('psycopg.Connection') \| None

**Default:** None       |
| `connection_string` | A string containing the connection information.

If provided, a new connection will be established using this string.

**Type:** str \| None

**Default:** None |
| `host`              | The hostname of the PostgreSQL server.

Used if connection\_string is not provided.

**Type:** str \| None

**Default:** None                                   |
| `port`              | The port number to connect to at the server host.

Used if connection\_string is not provided.

**Type:** int \| str \| None

**Default:** None                 |
| `dbname`            | The database name.

Used if connection\_string is not provided.

**Type:** str \| None

**Default:** None                                                       |
| `username`          | The username to connect as.

Used if connection\_string is not provided.

**Type:** str \| None

**Default:** None                                              |
| `password`          | The user's password.

Used if connection\_string is not provided.

**Type:** str \| None

**Default:** None                                                     |
| `connect_timeout`   | Maximum wait for connection, in seconds.

The default is 10 seconds.

**Type:** int \| None

**Default:** 10                                                    |

Returns:

| Type               | Description                                                          |
| ------------------ | -------------------------------------------------------------------- |
| psycopg.Connection | A psycopg.Connection object representing the established connection. |






#### get\_collection

```python theme={null}
get_collection(self, collection_name: str = None) -> Collection
```

Get the collection from the vector database.


Parameters:

| Name              | Description |                                                                                                                                                                         |
| ----------------- | ----------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `collection_name` | str         | The name of the collection.

Default is None.

If None, return the current active collection.

**Type:** str

**Default:** None |

Returns:

| Type                                                                                       | Description                          |
| ------------------------------------------------------------------------------------------ | ------------------------------------ |
| [Collection](/docs/api-reference/autogen/agentchat/contrib/vectordb/pgvectordb/Collection) | Collection \| The collection object. |






#### get\_docs\_by\_ids

```python theme={null}
get_docs_by_ids(
    self,
    ids: list[str | int] = None,
    collection_name: str = None,
    include=None,
    **kwargs
) -> list[Document]
```

Retrieve documents from the collection of the vector database based on the ids.


Parameters:

| Name              | Description   |                                                                                                                                                                            |
| ----------------- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `ids`             | List\[ItemID] | A list of document ids.

If None, will return all the documents.

Default is None.

**Type:** list\[str \| int]

**Default:** None |
| `collection_name` | str           | The name of the collection.

Default is None.

**Type:** str

**Default:** None                                                              |
| `include=None`    |               |                                                                                                                                                                            |
| `**kwargs`        |               |                                                                                                                                                                            |

Returns:

| Type                                                                                    | Description                     |
| --------------------------------------------------------------------------------------- | ------------------------------- |
| list\[[Document](/docs/api-reference/autogen/agentchat/contrib/vectordb/base/Document)] | List\[Document] \| The results. |






#### insert\_docs

```python theme={null}
insert_docs(
    self,
    docs: list[Document],
    collection_name: str = None,
    upsert: bool = False
) -> None
```

Insert documents into the collection of the vector database.


Parameters:

| Name              | Description     |                                                                                                                                                                                       |
| ----------------- | --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `docs`            | List\[Document] | A list of documents.

Each document is a TypedDict `Document`.

**Type:** list\[[Document](/docs/api-reference/autogen/agentchat/contrib/vectordb/base/Document)] |
| `collection_name` | str             | The name of the collection.

Default is None.

**Type:** str

**Default:** None                                                                         |
| `upsert`          | bool            | Whether to update the document if it exists.

Default is False.

**Type:** bool

**Default:** False                                                     |

Returns:

| Type | Description |
| ---- | ----------- |
| None | None        |






#### retrieve\_docs

```python theme={null}
retrieve_docs(
    self,
    queries: list[str],
    collection_name: str = None,
    n_results: int = 10,
    distance_threshold: float = -1
) -> list[list[tuple[Document, float]]]
```

Retrieve documents from the collection of the vector database based on the queries.


Parameters:

| Name                 | Description |                                                                                                                                                                                                                |
| -------------------- | ----------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `queries`            | List\[str]  | A list of queries.

Each query is a string.

**Type:** list\[str]                                                                                                                          |
| `collection_name`    | str         | The name of the collection.

Default is None.

**Type:** str

**Default:** None                                                                                                  |
| `n_results`          | int         | The number of relevant documents to return.

Default is 10.

**Type:** int

**Default:** 10                                                                                      |
| `distance_threshold` | float       | The threshold for the distance score, only distance smaller than it will be returned.

Don't filter with it if ` 0`.

Default is -1.

**Type:** float

**Default:** -1 |

Returns:

| Type                                                                                                          | Description                                                                                                                |
| ------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |
| list\[list\[tuple\[[Document](/docs/api-reference/autogen/agentchat/contrib/vectordb/base/Document), float]]] | QueryResults \| The query results. Each query result is a list of list of tuples containing the document and the distance. |






#### update\_docs

```python theme={null}
update_docs(
    self,
    docs: list[Document],
    collection_name: str = None
) -> None
```

Update documents in the collection of the vector database.


Parameters:

| Name              | Description     |                                                                                                                                   |
| ----------------- | --------------- | --------------------------------------------------------------------------------------------------------------------------------- |
| `docs`            | List\[Document] | A list of documents.

**Type:** list\[[Document](/docs/api-reference/autogen/agentchat/contrib/vectordb/base/Document)] |
| `collection_name` | str             | The name of the collection.

Default is None.

**Type:** str

**Default:** None                     |

Returns:

| Type | Description |
| ---- | ----------- |
| None | None        |