Merge branch 'main' into ragtool-migration

docs/source/conf.py

@@ -131,6 +131,7 @@ html_static_path = ["../_static"]
 def setup(app):
     app.add_css_file("css/my_theme.css")
     app.add_js_file("js/detect_theme.js")
+    app.add_js_file("js/horizontal_nav.js")
     app.add_js_file("js/keyboard_shortcuts.js")
 
     def dockerhub_role(name, rawtext, text, lineno, inliner, options={}, content=[]):

docs/source/distributions/k8s-benchmark/benchmark.py

@@ -58,14 +58,6 @@ class BenchmarkStats:
         
         print(f"\n{'='*60}")
         print(f"BENCHMARK RESULTS")
-        print(f"{'='*60}")
-        print(f"Total time: {total_time:.2f}s")
-        print(f"Concurrent users: {self.concurrent_users}")
-        print(f"Total requests: {self.total_requests}")
-        print(f"Successful requests: {self.success_count}")
-        print(f"Failed requests: {len(self.errors)}")
-        print(f"Success rate: {success_rate:.1f}%")
-        print(f"Requests per second: {self.success_count / total_time:.2f}")
         
         print(f"\nResponse Time Statistics:")
         print(f"  Mean: {statistics.mean(self.response_times):.3f}s")
@@ -106,6 +98,15 @@ class BenchmarkStats:
             print(f"  Mean chunks per response: {statistics.mean(self.chunks_received):.1f}")
             print(f"  Total chunks received: {sum(self.chunks_received)}")
         
+        print(f"{'='*60}")
+        print(f"Total time: {total_time:.2f}s")
+        print(f"Concurrent users: {self.concurrent_users}")
+        print(f"Total requests: {self.total_requests}")
+        print(f"Successful requests: {self.success_count}")
+        print(f"Failed requests: {len(self.errors)}")
+        print(f"Success rate: {success_rate:.1f}%")
+        print(f"Requests per second: {self.success_count / total_time:.2f}")
+        
         if self.errors:
             print(f"\nErrors (showing first 5):")
             for error in self.errors[:5]:
@@ -215,7 +216,7 @@ class LlamaStackBenchmark:
                         await asyncio.sleep(1)  # Report every second
                         if time.time() >= last_report_time + 10:  # Report every 10 seconds
                             elapsed = time.time() - stats.start_time
-                            print(f"Completed: {stats.total_requests} requests in {elapsed:.1f}s")
+                            print(f"Completed: {stats.total_requests} requests in {elapsed:.1f}s, RPS: {stats.total_requests / elapsed:.1f}")
                             last_report_time = time.time()
                     except asyncio.CancelledError:
                         break

docs/source/distributions/k8s-benchmark/stack_run_config.yaml

@@ -2,6 +2,7 @@ version: '2'
 image_name: kubernetes-benchmark-demo
 apis:
 - agents
+- files
 - inference
 - files
 - safety
@@ -20,6 +21,14 @@ providers:
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
+  files:
+  - provider_id: meta-reference-files
+    provider_type: inline::localfs
+    config:
+      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}
+      metadata_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db
   vector_io:
   - provider_id: ${env.ENABLE_CHROMADB:+chromadb}
     provider_type: remote::chromadb