Struct PartitionParameters

pub struct PartitionParameters {

    pub coordinates: bool,
    pub encoding: Option<String>,
    pub extract_image_block_types: Vec<String>,
    pub gz_uncompressed_content_type: Option<String>,
    pub hi_res_model_name: Option<String>,
    pub include_page_breaks: bool,
    pub languages: Option<Vec<String>>,
    pub output_format: String,
    pub skip_infer_table_types: Vec<String>,
    pub starting_page_number: Option<i32>,
    pub strategy: Strategy,
    pub unique_element_ids: bool,
    pub xml_keep_tags: bool,
    pub chunking_strategy: Option<ChunkingStrategy>,
    pub combine_under_n_chars: Option<i32>,
    pub include_orig_elements: bool,
    pub max_characters: Option<i32>,
    pub multipage_sections: bool,
    pub new_after_n_chars: Option<i32>,
    pub overlap: i32,
    pub overlap_all: bool,
    pub similarity_threshold: Option<f64>,
}

Fields

coordinates: bool

If True, return coordinates for each element extracted via OCR. Default: False.

encoding: Option<String>

The encoding method used to decode the text input. Default: utf-8

extract_image_block_types: Vec<String>

The types of elements to extract, for use in extracting image blocks as base64 encoded data stored in metadata fields. Default: [].

gz_uncompressed_content_type: Option<String>

If file is gzipped, use this content type after unzipping.

hi_res_model_name: Option<String>

The name of the inference model used when strategy is hi_res

include_page_breaks: bool

If true, the output will include page breaks if the filetype supports it. Default: false

languages: Option<Vec<String>>

The languages present in the document, for use in partitioning and/or OCR. See the Tesseract documentation for a full list of languages. Default: [].

output_format: String

The format of the response. Supported formats are application/json and text/csv. Default: application/json.

skip_infer_table_types: Vec<String>

The document types that you want to skip table extraction with. Default: [].

starting_page_number: Option<i32>

When PDF is split into pages before sending it into the API, providing this information will allow the page number to be assigned correctly. Introduced in 1.0.27.

strategy: Strategy

The strategy to use for partitioning PDF/image. Options are fast, hi_res, auto. Default: auto

unique_element_ids: bool

When True, assign UUIDs to element IDs, which guarantees their uniqueness (useful when using them as primary keys in database). Otherwise a SHA-256 of element text is used. Default: False

xml_keep_tags: bool

If True, will retain the XML tags in the output. Otherwise it will simply extract the text from within the tags. Only applies to XML documents. Default: false

chunking_strategy: Option<ChunkingStrategy>

Use one of the supported strategies to chunk the returned elements after partitioning. When ‘chunking_strategy’ is not specified, no chunking is performed and any other chunking parameters provided are ignored. Supported strategies: ‘basic’, ‘by_page’, ‘by_similarity’, or ‘by_title’

combine_under_n_chars: Option<i32>

If chunking strategy is set, combine elements until a section reaches a length of n chars. Default: 500

include_orig_elements: bool

When a chunking strategy is specified, each returned chunk will include the elements consolidated to form that chunk as .metadata.orig_elements. Default: true.

max_characters: Option<i32>

If chunking strategy is set, cut off new sections after reaching a length of n chars (hard max). Default: 500

multipage_sections: bool

If chunking strategy is set, determines if sections can span multiple sections. Default: true

new_after_n_chars: Option<i32>

If chunking strategy is set, cut off new sections after reaching a length of n chars (soft max). Default: 1500

overlap: i32

Specifies the length of a string (‘tail’) to be drawn from each chunk and prefixed to the next chunk as a context-preserving mechanism. By default, this only applies to split-chunks where an oversized element is divided into multiple chunks by text-splitting. Default 0.

overlap_all: bool

When True, apply overlap between ‘normal’ chunks formed from whole elements and not subject to text-splitting. Use this with caution as it entails a certain level of ‘pollution’ of otherwise clean semantic chunk boundaries. Default false.

similarity_threshold: Option<f64>

A value between 0.0 and 1.0 describing the minimum similarity two elements must have to be included in the same chunk. Note that similar elements may be separated to meet chunk-size criteria; this value can only guarantees that two elements with similarity below the threshold will appear in separate chunks.

Trait Implementations

impl Debug for PartitionParameters

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for PartitionParameters

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for PartitionParameters

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl From<PartitionParameters> for Form

fn from(value: PartitionParameters) -> Self

Converts to this type from the input type.

impl Serialize for PartitionParameters

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.