> ## 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.couchbase.CouchbaseVectorDB

<h2 id="autogen.agentchat.contrib.vectordb.couchbase.CouchbaseVectorDB" class="doc doc-heading">
  <code class="doc-symbol doc-symbol-heading doc-symbol-class" />

  <span class="doc doc-object-name doc-class-name">CouchbaseVectorDB</span>
</h2>

```python theme={null}
CouchbaseVectorDB(
    connection_string: str = 'couchbase://localhost',
    username: str = 'Administrator',
    password: str = 'password',
    bucket_name: str = 'vector_db',
    embedding_function: Callable = None,
    scope_name: str = '_default',
    collection_name: str = '_default',
    index_name: str = None
)
```

A vector database implementation that uses Couchbase as the backend.<br />Initialize the vector database.<br />

<b>Parameters:</b>

| Name                 | Description                                           |
| -------------------- | ----------------------------------------------------- |
| `connection_string`  | **Type:** str<br /><br />**Default:** 'couchbase      |
| `username`           | **Type:** str<br /><br />**Default:** 'Administrator' |
| `password`           | **Type:** str<br /><br />**Default:** 'password'      |
| `bucket_name`        | **Type:** str<br /><br />**Default:** 'vector\_db'    |
| `embedding_function` | **Type:** Callable<br /><br />**Default:** None       |
| `scope_name`         | **Type:** str<br /><br />**Default:** '\_default'     |
| `collection_name`    | **Type:** str<br /><br />**Default:** '\_default'     |
| `index_name`         | **Type:** str<br /><br />**Default:** None            |

### Class Attributes

<code class="doc-symbol doc-symbol-heading doc-symbol-attribute" />

#### active\_collection

<br />

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-attribute" />

#### embedding\_function

<br />

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-attribute" />

#### type

<br />

<br />

### Instance Methods

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### 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 and create a vector search index in the collection.<br />

<b>Parameters:</b>

| Name              | Description                                                                                                                            |
| ----------------- | -------------------------------------------------------------------------------------------------------------------------------------- |
| `collection_name` | The name of the collection.<br /><br />**Type:** str                                                                                   |
| `overwrite`       | Whether to overwrite the collection if it exists.<br /><br />Default is False.<br /><br />**Type:** bool<br /><br />**Default:** False |
| `get_or_create`   | Whether to get or create the collection.<br /><br />Default is True<br /><br />**Type:** bool<br /><br />**Default:** True             |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### create\_index\_if\_not\_exists

```python theme={null}
create_index_if_not_exists(
    self,
    index_name: str = 'vector_index',
    collection: ForwardRef('Collection') | None = None
) -> 
```

Creates a vector search index on the specified collection in Couchbase.<br />

<b>Parameters:</b>

| Name         | Description                                                                                                                                                      |
| ------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `index_name` | The name of the vector search index to create.<br /><br />Defaults to "vector\_search\_index".<br /><br />**Type:** str<br /><br />**Default:** 'vector\_index'  |
| `collection` | The Couchbase collection to create the index on.<br /><br />Defaults to None.<br /><br />**Type:** ForwardRef('Collection') \| None<br /><br />**Default:** None |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### create\_vector\_search\_index

```python theme={null}
create_vector_search_index(
    self,
    collection,
    index_name: str | None = 'vector_index',
    similarity: Literal['l2_norm', 'dot_product'] = 'dot_product'
) -> None
```

Create a vector search index in the collection.

<b>Parameters:</b>

| Name         | Description                                                                           |
| ------------ | ------------------------------------------------------------------------------------- |
| `collection` |                                                                                       |
| `index_name` | **Type:** str \| None<br /><br />**Default:** 'vector\_index'                         |
| `similarity` | **Type:** Literal\['l2\_norm', 'dot\_product']<br /><br />**Default:** 'dot\_product' |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### delete\_collection

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

Delete the collection from the vector database.<br />

<b>Parameters:</b>

| Name              | Description                                          |
| ----------------- | ---------------------------------------------------- |
| `collection_name` | The name of the collection.<br /><br />**Type:** str |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### delete\_docs

```python theme={null}
delete_docs(
    self,
    ids: list[str | int],
    collection_name: str = None,
    batch_size: int = 1000,
    **kwargs
) -> 
```

Delete documents from the collection of the vector database.

<b>Parameters:</b>

| Name              | Description                                |
| ----------------- | ------------------------------------------ |
| `ids`             | **Type:** list\[str \| int]                |
| `collection_name` | **Type:** str<br /><br />**Default:** None |
| `batch_size`      | **Type:** int<br /><br />**Default:** 1000 |
| `**kwargs`        |                                            |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### get\_collection

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

Get the collection from the vector database.<br />

<b>Parameters:</b>

| Name              | Description                                                                                                                                                                     |
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `collection_name` | The name of the collection.<br /><br />Default is None.<br /><br />If None, return the current active collection.<br /><br />**Type:** str \| None<br /><br />**Default:** None |

<b>Returns:</b>

| Type       | Description                        |
| ---------- | ---------------------------------- |
| Collection | The collection object (Collection) |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### get\_docs\_by\_ids

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

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

<b>Parameters:</b>

| Name              | Description                                                      |
| ----------------- | ---------------------------------------------------------------- |
| `ids`             | **Type:** list\[str \| int] \| None<br /><br />**Default:** None |
| `collection_name` | **Type:** str<br /><br />**Default:** None                       |
| `include`         | **Type:** list\[str] \| None<br /><br />**Default:** None        |
| `**kwargs`        | **Type:** Any                                                    |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### insert\_docs

```python theme={null}
insert_docs(
    self,
    docs: list[Document],
    collection_name: str = None,
    upsert: bool = False,
    batch_size: int = 1000,
    **kwargs: Any
) -> None
```

Insert Documents and Vector Embeddings into the collection of the vector database. Documents are upserted in all cases.

<b>Parameters:</b>

| Name              | Description                                                                                       |
| ----------------- | ------------------------------------------------------------------------------------------------- |
| `docs`            | **Type:** list\[[Document](/docs/api-reference/autogen/agentchat/contrib/vectordb/base/Document)] |
| `collection_name` | **Type:** str<br /><br />**Default:** None                                                        |
| `upsert`          | **Type:** bool<br /><br />**Default:** False                                                      |
| `batch_size`      | **Type:** int<br /><br />**Default:** 1000                                                        |
| `**kwargs`        | **Type:** Any                                                                                     |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### retrieve\_docs

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

Retrieve documents from the collection of the vector database based on the queries.<br />Note: Distance threshold is not supported in Couchbase FTS.

<b>Parameters:</b>

| Name                 | Description                                |
| -------------------- | ------------------------------------------ |
| `queries`            | **Type:** list\[str]                       |
| `collection_name`    | **Type:** str<br /><br />**Default:** None |
| `n_results`          | **Type:** int<br /><br />**Default:** 10   |
| `distance_threshold` | **Type:** float<br /><br />**Default:** -1 |
| `**kwargs`           | **Type:** Any                              |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### search\_index\_exists

```python theme={null}
search_index_exists(self, index_name: str) -> 
```

Check if the specified index is ready

<b>Parameters:</b>

| Name         | Description   |
| ------------ | ------------- |
| `index_name` | **Type:** str |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### update\_docs

```python theme={null}
update_docs(
    self,
    docs: list[Document],
    collection_name: str = None,
    batch_size: int = 1000,
    **kwargs: Any
) -> None
```

Update documents, including their embeddings, in the Collection.

<b>Parameters:</b>

| Name              | Description                                                                                       |
| ----------------- | ------------------------------------------------------------------------------------------------- |
| `docs`            | **Type:** list\[[Document](/docs/api-reference/autogen/agentchat/contrib/vectordb/base/Document)] |
| `collection_name` | **Type:** str<br /><br />**Default:** None                                                        |
| `batch_size`      | **Type:** int<br /><br />**Default:** 1000                                                        |
| `**kwargs`        | **Type:** Any                                                                                     |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### upsert\_docs

```python theme={null}
upsert_docs(
    self,
    docs: list[Document],
    collection: Collection,
    batch_size: int = 1000,
    **kwargs: Any
) -> 
```

<b>Parameters:</b>

| Name         | Description                                                                                       |
| ------------ | ------------------------------------------------------------------------------------------------- |
| `docs`       | **Type:** list\[[Document](/docs/api-reference/autogen/agentchat/contrib/vectordb/base/Document)] |
| `collection` | **Type:** Collection                                                                              |
| `batch_size` | **Type:** int<br /><br />**Default:** 1000                                                        |
| `**kwargs`   | **Type:** Any                                                                                     |

<br />