> ## 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.capabilities.teachability.MemoStore

<h2 id="autogen.agentchat.contrib.capabilities.teachability.MemoStore" class="doc doc-heading">
  <code class="doc-symbol doc-symbol-heading doc-symbol-class" />

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

```python theme={null}
MemoStore(
    verbosity: int | None = 0,
    reset: bool | None = False,
    path_to_db_dir: str | None = './tmp/teachable_agent_db'
)
```

Provides memory storage and retrieval for a teachable agent, using a vector database.<br />Each DB entry (called a memo) is a pair of strings: an input text and an output text.<br />The input text might be a question, or a task to perform.<br />The output text might be an answer to the question, or advice on how to perform the task.<br />Vector embeddings are currently supplied by Chroma's default Sentence Transformers.<br />

<b>Parameters:</b>

| Name             | Description                                                                |
| ---------------- | -------------------------------------------------------------------------- |
| `verbosity`      | **Type:** int \| None<br /><br />**Default:** 0                            |
| `reset`          | **Type:** bool \| None<br /><br />**Default:** False                       |
| `path_to_db_dir` | **Type:** str \| None<br /><br />**Default:** './tmp/teachable\_agent\_db' |

### Instance Methods

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

#### add\_input\_output\_pair

```python theme={null}
add_input_output_pair(
    self,
    input_text: str,
    output_text: str
) -> 
```

Adds an input-output pair to the vector DB.

<b>Parameters:</b>

| Name          | Description   |
| ------------- | ------------- |
| `input_text`  | **Type:** str |
| `output_text` | **Type:** str |

<br />

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

#### get\_nearest\_memo

```python theme={null}
get_nearest_memo(self, query_text: str) -> 
```

Retrieves the nearest memo to the given query text.

<b>Parameters:</b>

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

<br />

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

#### get\_related\_memos

```python theme={null}
get_related_memos(
    self,
    query_text: str,
    n_results: int,
    threshold: int | float
) -> 
```

Retrieves memos that are related to the given query text within the specified distance threshold.

<b>Parameters:</b>

| Name         | Description            |
| ------------ | ---------------------- |
| `query_text` | **Type:** str          |
| `n_results`  | **Type:** int          |
| `threshold`  | **Type:** int \| float |

<br />

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

#### list\_memos

```python theme={null}
list_memos(self) -> 
```

Prints the contents of MemoStore.

<br />

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

#### prepopulate

```python theme={null}
prepopulate(self) -> 
```

Adds a few arbitrary examples to the vector DB, just to make retrieval less trivial.

<br />

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

#### reset\_db

```python theme={null}
reset_db(self) -> 
```

Forces immediate deletion of the DB's contents, in memory and on disk.

<br />