Struct EmbeddingUnit 

pub struct EmbeddingUnit {

    pub id: String,
    pub file: String,
    pub name: String,
    pub kind: UnitKind,
    pub code: String,
    pub signature: String,
    pub docstring: Option<String>,
    pub start_line: usize,
    pub end_line: usize,
    pub token_count: usize,
    pub semantic_tags: Vec<String>,
    pub parent: Option<String>,
    pub language: String,
    pub calls: Vec<String>,
    pub called_by: Vec<String>,
    pub cfg_summary: String,
    pub dfg_summary: String,
    pub dependencies: String,
    pub complexity: CodeComplexity,
    pub chunk_index: usize,
    pub chunk_total: usize,
}

A code unit for semantic embedding.

Contains information from all 5 brrr analysis layers plus semantic enrichment. This is the primary unit of indexing and retrieval in semantic search.

Fields

id: String

Unique identifier (typically file::qualified_name or file::name#chunkN)

file: String

Source file path (relative to project root)

name: String

Simple name (function/class/method name)

kind: UnitKind

Kind of code unit

code: String

Full code content (may be truncated for large units)

signature: String

Function/method signature or class declaration

docstring: Option<String>

Docstring or documentation comment

start_line: usize

Starting line number (1-indexed)

end_line: usize

Ending line number (1-indexed)

token_count: usize

Token count for this unit’s code

semantic_tags: Vec<String>

Semantic tags detected from code patterns

parent: Option<String>

Parent unit name (for chunks and methods)

language: String

L1: Programming language

calls: Vec<String>

L2: Functions this unit calls

called_by: Vec<String>

L2: Functions that call this unit

cfg_summary: String

L3: CFG summary (complexity, block count)

dfg_summary: String

L4: DFG summary (variable count, def-use chains)

dependencies: String

L5: Dependencies (imported modules)

complexity: CodeComplexity

Code complexity metrics

chunk_index: usize

Chunk index (0-indexed, for chunked units)

chunk_total: usize

Total number of chunks (1 for non-chunked units)

Implementations

impl EmbeddingUnit

pub fn new( file: impl Into<String>, name: impl Into<String>, kind: UnitKind, code: impl Into<String>, start_line: usize, language: impl Into<String>, ) -> Self

Create a new embedding unit with minimal required fields.

pub fn is_chunk(&self) -> bool

Check if this unit is a chunk of a larger unit.

pub fn needs_chunking(&self) -> bool

Check if this unit needs to be split into chunks based on token count.

pub fn qualified_name(&self) -> String

Get the qualified name (file::name or file::parent.name for methods).

pub fn to_map(&self) -> HashMap<String, Value>

Convert to a HashMap for JSON serialization.

Trait Implementations

impl Clone for EmbeddingUnit

fn clone(&self) -> EmbeddingUnit

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for EmbeddingUnit

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for EmbeddingUnit

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for EmbeddingUnit

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

where __S: Serializer,

Serialize this value into the given Serde serializer.