Struct EmbeddingConfig 

pub struct EmbeddingConfig {
    pub provider: String,
    pub model: String,
    pub api_key_env: String,
    pub base_url: Option<String>,
    pub dimension: Option<usize>,
    pub cache_dir: Option<String>,
}

Configuration for embedding generation (optional).

When configured under [memory.embedding], enables hybrid retrieval (BM25 + vector cosine) for improved recall quality.

Fields

provider: String

Provider name: “openai”, “local”, or “none” (default).

model: String

Model name for the embedding API.

api_key_env: String

Environment variable name containing the API key.

base_url: Option<String>

Base URL for the embedding API (optional, defaults to OpenAI).

dimension: Option<usize>

Embedding vector dimension (auto-detected from model if omitted).

cache_dir: Option<String>

Model cache directory for local embedding provider (optional).

Trait Implementations

impl Clone for EmbeddingConfig

fn clone(&self) -> EmbeddingConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for EmbeddingConfig

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for EmbeddingConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.