> ## 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.embeddings.vlm embedding

<a id="camel.embeddings.vlm_embedding" />

<a id="camel.embeddings.vlm_embedding.VisionLanguageEmbedding" />

## VisionLanguageEmbedding

```python theme={"system"}
class VisionLanguageEmbedding:
```

Provides image embedding functionalities using multimodal model.

**Parameters:**

* **model\_name**: The model type to be used for generating embeddings. And the default value is: obj:`openai/clip-vit-base-patch32`.

<a id="camel.embeddings.vlm_embedding.VisionLanguageEmbedding.__init__" />

### **init**

```python theme={"system"}
def __init__(self, model_name: str = 'openai/clip-vit-base-patch32'):
```

Initializes the: obj: `VisionLanguageEmbedding` class with a
specified model and return the dimension of embeddings.

**Parameters:**

* **model\_name** (str, optional): The version name of the model to use. (default: :obj:`openai/clip-vit-base-patch32`)

<a id="camel.embeddings.vlm_embedding.VisionLanguageEmbedding.embed_list" />

### embed\_list

```python theme={"system"}
def embed_list(self, objs: List[Union[Image.Image, str]], **kwargs: Any):
```

Generates embeddings for the given images or texts.

**Parameters:**

* **objs** (List\[Image.Image|str]): The list of images or texts for which to generate the embeddings.
* **image\_processor\_kwargs**: Extra kwargs passed to the image processor.
* **tokenizer\_kwargs**: Extra kwargs passed to the text tokenizer (processor).
* **model\_kwargs**: Extra kwargs passed to the main model.

**Returns:**

List\[List\[float]]: A list that represents the generated embedding
as a list of floating-point numbers.

<a id="camel.embeddings.vlm_embedding.VisionLanguageEmbedding.get_output_dim" />

### get\_output\_dim

```python theme={"system"}
def get_output_dim(self):
```

**Returns:**

int: The dimensionality of the embedding for the current model.