Skip to content

armgit / camel

Public Imported from GitHub
0

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

1.7 KB
Raw Blame
<a id="camel.loaders.mistral_reader"></a>

<a id="camel.loaders.mistral_reader.MistralReader"></a>

## MistralReader

```python
class MistralReader:
```

Mistral Document Loader.

<a id="camel.loaders.mistral_reader.MistralReader.__init__"></a>

### __init__

```python
def __init__(
    self,
    api_key: Optional[str] = None,
    model: Optional[str] = 'mistral-ocr-latest'
):
```

Initialize the MistralReader.

**Parameters:**

- **api_key** (Optional[str]): The API key for the Mistral API. (default: :obj:`None`)
- **model** (Optional[str]): The model to use for OCR. (default: :obj:`"mistral-ocr-latest"`)

<a id="camel.loaders.mistral_reader.MistralReader._encode_file"></a>

### _encode_file

```python
def _encode_file(self, file_path: str):
```

Encode the pdf to base64.

**Parameters:**

- **file_path** (str): Path to the input file.

**Returns:**

  str: base64 version of the file.

<a id="camel.loaders.mistral_reader.MistralReader.extract_text"></a>

### extract_text

```python
def extract_text(
    self,
    file_path: str,
    is_image: bool = False,
    pages: Optional[List[int]] = None,
    include_image_base64: Optional[bool] = None
):
```

Converts the given file to Markdown format.

**Parameters:**

- **file_path** (str): Path to the input file or a remote URL.
- **is_image** (bool): Whether the file or URL is an image. If True, uses image_url type instead of document_url. (default: :obj:`False`)
- **pages** (Optional[List[int]]): Specific pages user wants to process in various formats: single number, range, or list of both. Starts from 0. (default: :obj:`None`)
- **include_image_base64** (Optional[bool]): Whether to include image URLs in response. (default: :obj:`None`)

**Returns:**

  OCRResponse: page wise extractions.