Struct OllamaConfig 

pub struct OllamaConfig {

    pub enabled: bool,
    pub host: String,
    pub port: u16,
    pub embedding_model: String,
    pub chat_model: String,
    pub timeout_seconds: u64,
    pub max_retries: u32,
    pub fallback_to_hash: bool,
    pub max_tokens: Option<u32>,
    pub temperature: Option<f32>,
    pub enable_caching: bool,
    pub keep_alive: Option<String>,
    pub num_ctx: Option<u32>,
}

Ollama configuration

Fields

enabled: bool

Enable Ollama integration

host: String

Ollama host URL

port: u16

Ollama port

embedding_model: String

Model for embeddings

chat_model: String

Model for chat/generation

timeout_seconds: u64

Timeout in seconds

max_retries: u32

Maximum retry attempts

fallback_to_hash: bool

Fallback to hash-based IDs on error

max_tokens: Option<u32>

Maximum tokens to generate

temperature: Option<f32>

Temperature for generation (0.0 - 1.0)

enable_caching: bool

Enable model caching

keep_alive: Option<String>

How long to keep the model loaded in memory between requests (e.g. “1h”, “30m”, “0”).

Without this, Ollama may unload the model between requests, destroying the KV cache and forcing full re-evaluation of long document contexts on every request. Set to “1h” when processing multiple chunks from the same document.

num_ctx: Option<u32>

Default context window size for generation requests.

Ollama silently truncates prompts exceeding this value (default is often 2048-8192). For long-document processing, set this to at least: tokens(document) + tokens(max_chunk) + tokens(instructions) + 150 output tokens Use None to let Ollama use its model default.

Trait Implementations

impl Clone for OllamaConfig

fn clone(&self) -> OllamaConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for OllamaConfig

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

Formats the value using the given formatter.

impl Default for OllamaConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for OllamaConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for OllamaConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.