- Add killport.js script for terminating processes on specific ports

- Introduce `supportedModels` in `ClientChatStore` and update model validation logic
- Enhance OpenAI inferencing with local setup adaptations and improved streaming options
- Modify ChatService to handle local and remote model fetching
- Update input menu to dynamically fetch and display supported models
- Add start_inference_server.sh for initiating local inference server
- Upgrade OpenAI SDK to v5.0.1 and adjust dependencies accordingly

workers/site/api-router.ts

@@ -28,6 +28,13 @@ export function createRouter() {
         },
       )
 
+    .get("/api/models",
+        async (req, env, ctx) => {
+            const { chatService } = createRequestContext(env, ctx);
+            return chatService.getSupportedModels();
+        },
+    )
+
       .post("/api/feedback", async (r, e, c) => {
         const { feedbackService } = createRequestContext(e, c);
         return feedbackService.handleFeedback(r);