LLM支持优化

src/llm/ollama.rs

@@ -9,6 +9,9 @@ pub struct OllamaClient {
     base_url: String,
     model: String,
     client: reqwest::Client,
+    max_tokens: u32,
+    temperature: f32,
+    top_p: Option<f32>,
 }
 
 #[derive(Debug, Serialize)]
@@ -49,11 +52,14 @@ impl OllamaClient {
     pub fn new(base_url: &str, model: &str) -> Self {
         let client = create_http_client(Duration::from_secs(120))
             .expect("Failed to create HTTP client");
-        
+
         Self {
             base_url: base_url.trim_end_matches('/').to_string(),
             model: model.to_string(),
             client,
+            max_tokens: 500,
+            temperature: 0.7,
+            top_p: None,
         }
     }
 
@@ -64,6 +70,21 @@ impl OllamaClient {
         self
     }
 
+    pub fn with_max_tokens(mut self, max_tokens: u32) -> Self {
+        self.max_tokens = max_tokens;
+        self
+    }
+
+    pub fn with_temperature(mut self, temperature: f32) -> Self {
+        self.temperature = temperature;
+        self
+    }
+
+    pub fn with_top_p(mut self, top_p: f32) -> Self {
+        self.top_p = Some(top_p);
+        self
+    }
+
     /// List available models
     pub async fn list_models(&self) -> Result<Vec<String>> {
         let url = format!("{}/api/tags", self.base_url);
@@ -143,8 +164,8 @@ impl LlmProvider for OllamaClient {
             system,
             stream: false,
             options: GenerationOptions {
-                temperature: Some(0.7),
-                num_predict: Some(500),
+                temperature: Some(self.temperature),
+                num_predict: Some(self.max_tokens),
             },
         };