Struct RagConfig 

pub struct RagConfig {

    pub provider: LlmProvider,
    pub api_endpoint: String,
    pub api_key: Option<String>,
    pub model: String,
    pub max_tokens: usize,
    pub temperature: f32,
    pub top_p: f32,
    pub timeout_secs: u64,
    pub max_retries: u32,
    pub embedding_provider: EmbeddingProvider,
    pub embedding_model: String,
    pub embedding_dimensions: usize,
    pub chunk_size: usize,
    pub chunk_overlap: usize,
    pub top_k: usize,
    pub similarity_threshold: f32,
    pub hybrid_search: bool,
    pub semantic_weight: f32,
    pub keyword_weight: f32,
    pub query_expansion: bool,
    pub response_filtering: bool,
    pub caching: bool,
    pub cache_ttl_secs: u64,
    pub rate_limiting: RateLimitConfig,
    pub retry_config: RetryConfig,
    pub custom_headers: HashMap<String, String>,
    pub debug_mode: bool,
    pub max_context_length: usize,
    pub response_format: ResponseFormat,
    pub logging: LoggingConfig,
    pub monitoring: MonitoringConfig,
}

RAG configuration

Fields

provider: LlmProvider

LLM provider

api_endpoint: String

LLM API endpoint

api_key: Option<String>

API key for authentication

model: String

Model name to use

max_tokens: usize

Maximum tokens for generation

temperature: f32

Temperature for generation (0.0 to 2.0)

top_p: f32

Top-p sampling (0.0 to 1.0)

timeout_secs: u64

Request timeout in seconds

max_retries: u32

Maximum retry attempts

embedding_provider: EmbeddingProvider

Embedding provider

embedding_model: String

Embedding model name

embedding_dimensions: usize

Embedding dimensions

chunk_size: usize

Chunk size for document splitting

chunk_overlap: usize

Chunk overlap for document splitting

top_k: usize

Top-k similar chunks to retrieve

similarity_threshold: f32

Similarity threshold (0.0 to 1.0)

hybrid_search: bool

Enable hybrid search (combines semantic and keyword search)

semantic_weight: f32

Weight for semantic search in hybrid mode (0.0 to 1.0)

keyword_weight: f32

Weight for keyword search in hybrid mode (0.0 to 1.0)

query_expansion: bool

Enable query expansion

response_filtering: bool

Enable response filtering

caching: bool

Enable caching

cache_ttl_secs: u64

Cache TTL in seconds

rate_limiting: RateLimitConfig

Rate limiting configuration

retry_config: RetryConfig

Retry configuration

custom_headers: HashMap<String, String>

Custom headers for API requests

debug_mode: bool

Enable debug mode

max_context_length: usize

Maximum context length

response_format: ResponseFormat

Response format preferences

logging: LoggingConfig

Logging configuration

monitoring: MonitoringConfig

Performance monitoring

Implementations

impl RagConfig

pub fn new(provider: LlmProvider, model: String) -> Self

Create a new RAG configuration

pub fn with_api_key(self, api_key: String) -> Self

Set API key

pub fn with_endpoint(self, endpoint: String) -> Self

Set API endpoint

pub fn with_model_params( self, max_tokens: usize, temperature: f32, top_p: f32, ) -> Self

Set model parameters

pub fn with_embedding( self, provider: EmbeddingProvider, model: String, dimensions: usize, ) -> Self

Set embedding configuration

pub fn with_chunking(self, chunk_size: usize, chunk_overlap: usize) -> Self

Set chunking parameters

pub fn with_retrieval(self, top_k: usize, similarity_threshold: f32) -> Self

Set retrieval parameters

pub fn with_hybrid_search( self, semantic_weight: f32, keyword_weight: f32, ) -> Self

Enable hybrid search

pub fn with_caching(self, enabled: bool, ttl_secs: u64) -> Self

Set caching configuration

pub fn with_rate_limit(self, requests_per_minute: u32, burst_size: u32) -> Self

Set rate limiting

pub fn with_retry(self, max_attempts: u32, backoff_secs: u64) -> Self

Set retry configuration

pub fn with_header(self, key: String, value: String) -> Self

Add custom header

pub fn with_debug_mode(self, debug: bool) -> Self

Enable debug mode

pub fn validate(&self) -> Result<()>

Validate configuration

pub fn timeout_duration(&self) -> Duration

Get timeout duration

pub fn cache_ttl_duration(&self) -> Duration

Get cache TTL duration

pub fn is_caching_enabled(&self) -> bool

Check if caching is enabled

pub fn is_rate_limited(&self) -> bool

Check if rate limiting is enabled

pub fn requests_per_minute(&self) -> u32

Get requests per minute limit

pub fn burst_size(&self) -> u32

Get burst size for rate limiting

pub fn max_retry_attempts(&self) -> u32

Get maximum retry attempts

pub fn backoff_duration(&self) -> Duration

Get backoff duration for retries

pub fn is_exponential_backoff(&self) -> bool

Check if exponential backoff is enabled

pub fn response_format(&self) -> &ResponseFormat

Get response format

pub fn logging_config(&self) -> &LoggingConfig

Get logging configuration

pub fn monitoring_config(&self) -> &MonitoringConfig

Get monitoring configuration

Trait Implementations

impl Clone for RagConfig

fn clone(&self) -> RagConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RagConfig

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

Formats the value using the given formatter.

impl Default for RagConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for RagConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for RagConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.