<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/retrieval/semantic_retriever.py#L311-L336) |

Options for the semantic retriever task.

```python
mp.tasks.retrieval.SemanticRetrieverOptions(
    embedder: `mp.tasks.retrieval.UniversalEmbedder`,
    embedding_dimension: int = _DEFAULT_EMBEDDING_DIMENSION,
    database_path: Optional[str] = None,
    chunk_size: int = 512,
    chunk_overlap: int = 100,
    chunking_mode: int = ChunkingMode.CHARACTER
)
```

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `embedder` | Dataclass field |
| `embedding_dimension` | Dataclass field |
| `database_path` | Dataclass field |
| `chunk_size` | Dataclass field |
| `chunk_overlap` | Dataclass field |
| `chunking_mode` | Dataclass field |

<br />

## Methods

### `to_ctypes`

[View source](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/retrieval/semantic_retriever.py#L322-L336)

```python
to_ctypes() -> _MpSemanticRetrieverOptionsC
```

Generates a ctypes MpSemanticRetrieverOptionsC object.

### `__eq__`

```python
__eq__(
    other
)
```

Return self==value.

<br />

<br />

<br />

| ## Class Variables ||
|---|---|
| chunk_overlap | `100` |
| chunk_size | `512` |
| chunking_mode | `0` |
| database_path | `None` |
| embedding_dimension | `768` |

<br />