Struct ExtractedMemory 

pub struct ExtractedMemory {
    pub content: String,
    pub memory_type: String,
    pub confidence: f32,
    pub entities: Vec<String>,
    pub tags: Vec<String>,
    pub context: Vec<String>,
    pub reasoning: String,
}

A single memory extracted from a conversation by the LLM.

Fields

content: String

The factual content of the memory.

memory_type: String

Classification: decision, preference, correction, fact, entity, anti_pattern.

confidence: f32

How confident the LLM is that this is worth remembering (0.0 to 1.0).

entities: Vec<String>

Entities mentioned in this memory.

tags: Vec<String>

Categorization tags.

context: Vec<String>

Life-context categories this memory belongs to (e.g., [“health_device”, “shopping”]). Used for categorical retrieval — stored as context: tags on the memory node.

reasoning: String

Why this memory was extracted (for debugging and auditing).

Implementations

impl ExtractedMemory

pub fn embedding_key(&self) -> String

Build an augmented text string for embedding generation.

Concatenates the content with entities and tags to create a richer vector representation that matches on more search queries.

Trait Implementations

impl Clone for ExtractedMemory

fn clone(&self) -> ExtractedMemory

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ExtractedMemory

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ExtractedMemory

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ExtractedMemory

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

where __S: Serializer,

Serialize this value into the given Serde serializer.