feat: Add max tokens setting for model generations

Adds a new setting to control the maximum number of tokens generated by the model. This provides more control over the length of responses and can be useful for limiting the amount of text generated in certain situations.

src/models/index.ts

@@ -13,7 +13,8 @@ export const pageAssistModel = async ({
   topP,
   numCtx,
   seed,
-  numGpu
+  numGpu,
+  numPredict,
 }: {
   model: string
   baseUrl: string
@@ -24,12 +25,13 @@ export const pageAssistModel = async ({
   numCtx?: number
   seed?: number
   numGpu?: number
+  numPredict?: number
 }) => {
 
   if (model === "chrome::gemini-nano::page-assist") {
     return new ChatChromeAI({
       temperature,
-      topK
+      topK,
     })
   }
 
@@ -46,6 +48,7 @@ export const pageAssistModel = async ({
       openAIApiKey: providerInfo.apiKey || "temp",
       temperature,
       topP,
+      maxTokens: numPredict,
       configuration: {
         apiKey: providerInfo.apiKey || "temp",
         baseURL: providerInfo.baseUrl || "",
@@ -64,7 +67,8 @@ export const pageAssistModel = async ({
     numCtx,
     seed,
     model,
-    numGpu
+    numGpu,
+    numPredict
   })