Struct IngestBatchConfig 

pub struct IngestBatchConfig {
    pub extraction: GraphExtractionConfig,
    pub dry_run: bool,
    pub dry_run_hub_top_n: Option<usize>,
    pub max_content_bytes: usize,
}

Configuration for SemanticMemory::ingest_documents.

Wraps the per-extraction GraphExtractionConfig and adds batch-level options.

Fields

extraction: GraphExtractionConfig

Per-document extraction config. Quality gates, timeouts, and model settings.

The provenance and system_prompt fields are overwritten per document inside ingest_documents — callers do not need to set them.

dry_run: bool

When true, run LLM extraction but write nothing to the graph or the ledger.

The report will contain projected entity/edge counts and hub-degree distribution. This is the spec-067 FR-026 dry-run mode.

dry_run_hub_top_n: Option<usize>

Number of top entities to include in the dry-run hub-degree report.

None defaults to 10.

max_content_bytes: usize

Maximum allowed content size in bytes for a single document.

Documents whose content exceeds this limit are rejected with DocOutcome::Failed before any LLM call is made. This is a security measure to prevent arbitrarily large payloads from reaching the provider.

Defaults to 512 KiB (512 * 1024).

Trait Implementations

impl Clone for IngestBatchConfig

fn clone(&self) -> IngestBatchConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for IngestBatchConfig

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

Formats the value using the given formatter.

impl Default for IngestBatchConfig

fn default() -> Self

Returns the “default value” for a type.