Enum EmbedError 

#[non_exhaustive]
pub enum EmbedError {
    ModelNotLoaded(String),
    WrongModelLoaded {
        expected: String,
        actual: String,
    },
    ModelInitialization(String),
    InferenceFailed(String),
    TaskFailed(String),
    InvalidInput(String),
    TextTooLong {
        length: usize,
        max: usize,
    },
    DimensionMismatch {
        expected: usize,
        actual: usize,
    },
    UnsupportedModel(String),
    Internal(String),
    TierMismatch {
        op: &'static str,
        expected: QuantizationTier,
        actual: QuantizationTier,
    },
}

Stable: external consumers may depend on this; breaking changes require a SemVer bump.

Errors that can occur during embedding operations.

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

ModelNotLoaded(String)

Model not loaded (needs initialization).

WrongModelLoaded

Wrong model loaded (concurrent model switch in progress).

This can happen when multiple tasks request different models concurrently. The caller should retry with backoff.

Fields

expected: String

Model that was expected.

actual: String

Model that was actually loaded.

ModelInitialization(String)

Model initialization failed.

InferenceFailed(String)

Embedding inference failed.

TaskFailed(String)

Blocking task failed (panic or cancellation).

The model cache may be lost; next call will reinitialize.

InvalidInput(String)

Invalid input provided.

TextTooLong

Input text exceeds maximum allowed length.

Fields

length: usize

Actual length in characters.

max: usize

Maximum allowed length.

DimensionMismatch

Dimension mismatch between expected and actual.

Fields

expected: usize

Expected dimension.

actual: usize

Actual dimension.

UnsupportedModel(String)

Model not supported by this service.

Internal(String)

Internal logic error (count mismatch, unexpected state).

TierMismatch

A quantization tier did not match the tier required by the operation.

Raised by the simd::tier prepared-dispatch functions (e.g. approximate_cosine_distance_prepared) when a PreparedQuery’s tier does not match the stored data’s tier, or a batch dispatch function’s presumed tier.

Fields

op: &'static str

Name of the operation where the mismatch was detected.

expected: QuantizationTier

Tier the operation required.

actual: QuantizationTier

Tier actually supplied.

Trait Implementations

impl Debug for EmbedError

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

Formats the value using the given formatter.

impl Display for EmbedError

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

Formats the value using the given formatter.

impl Error for EmbedError

fn source(&self) -> Option<&(dyn Error + 'static)>

Returns the lower-level source of this error, if any.

fn description(&self) -> &str

👎Deprecated since 1.42.0:

use the Display impl or to_string()

fn cause(&self) -> Option<&dyn Error>

👎Deprecated since 1.33.0:

replaced by Error::source, which can support downcasting

fn provide<'a>(&'a self, request: &mut Request<'a>)

🔬This is a nightly-only experimental API. (error_generic_member_access)

Provides type-based access to context intended for error reports.