Struct NerCfg 

pub struct NerCfg {
    pub enabled: bool,
    pub model_path: String,
    pub tokenizer_path: String,
    pub labels: Vec<String>,
    pub threshold: f32,
    pub max_seq_len: usize,
}

ML NER settings ([llm.dlp.ner]). Off by default. When enabled, the proxy must be built with --features ner; otherwise startup fails with a clear error rather than running regex-only while the operator believes ML coverage is active. The model is an ONNX token-classification (BIO) NER network run through the pure-Rust [edgeguard_ner] crate.

Fields

enabled: bool

Turn the NER family on. Requires the ner feature.

model_path: String

Path to the ONNX model file.

tokenizer_path: String

Path to the HuggingFace tokenizer.json.

labels: Vec<String>

Per-class label list in model id order (e.g. ["O","B-PER","I-PER","B-LOC", …]). Used to map argmax class ids back to entity labels.

threshold: f32

Confidence floor in [0.0, 1.0]; spans below it are dropped. Default 0.5.

max_seq_len: usize

Max tokens fed to the model per scan (longer inputs are truncated). Default 256.

Trait Implementations

impl Clone for NerCfg

fn clone(&self) -> NerCfg

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for NerCfg

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

Formats the value using the given formatter.

impl Default for NerCfg

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for NerCfg

where NerCfg: Default,

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.