update getting started guide and add llm gateway and prompt gateway samples (#330)

arch/arch_config_schema.yaml

@@ -28,6 +28,11 @@ properties:
             type: string
           connect_timeout:
             type: string
+          protocol:
+            type: string
+            enum:
+              - http
+              - https
         additionalProperties: false
         required:
           - endpoint
@@ -92,6 +97,8 @@ properties:
                 type: array
                 items:
                   type: string
+              in_path:
+                type: boolean
             additionalProperties: false
             required:
               - name
@@ -104,6 +111,11 @@ properties:
               type: string
             path:
               type: string
+            http_method:
+              type: string
+              enum:
+                - GET
+                - POST
           additionalProperties: false
           required:
             - name

arch/envoy.template.yaml

@@ -500,7 +500,18 @@ static_resources:
                     socket_address:
                       address: {{ cluster.endpoint }}
                       port_value: {{ cluster.port }}
-                  hostname: {{ cluster.name }}
+                  hostname: {{ cluster.endpoint }}
+      {% if cluster.protocol == "https" %}
+      transport_socket:
+        name: envoy.transport_sockets.tls
+        typed_config:
+          "@type": type.googleapis.com/envoy.extensions.transport_sockets.tls.v3.UpstreamTlsContext
+          sni: {{ cluster.endpoint }}
+          common_tls_context:
+            tls_params:
+              tls_minimum_protocol_version: TLSv1_2
+              tls_maximum_protocol_version: TLSv1_3
+      {% endif %}
 {% endfor %}
     - name: arch_internal
       connect_timeout: 5s

arch/tools/cli/config_generator.py

@@ -49,7 +49,9 @@ def validate_and_render_schema():
 
     if "prompt_targets" in config_yaml:
         for prompt_target in config_yaml["prompt_targets"]:
-            name = prompt_target.get("endpoint", {}).get("name", "")
+            name = prompt_target.get("endpoint", {}).get("name", None)
+            if not name:
+                continue
             if name not in inferred_clusters:
                 inferred_clusters[name] = {
                     "name": name,

arch/tools/cli/core.py

@@ -196,7 +196,7 @@ def start_arch_modelserver():
         subprocess.run(
             ["archgw_modelserver", "restart"], check=True, start_new_session=True
         )
-        log.info("Successfull ran model_server")
+        log.info("Successfully ran model_server")
     except subprocess.CalledProcessError as e:
         log.info(f"Failed to start model_server. Please check archgw_modelserver logs")
         sys.exit(1)
@@ -212,7 +212,7 @@ def stop_arch_modelserver():
             ["archgw_modelserver", "stop"],
             check=True,
         )
-        log.info("Successfull stopped the archgw model_server")
+        log.info("Successfully stopped the archgw model_server")
     except subprocess.CalledProcessError as e:
         log.info(f"Failed to start model_server. Please check archgw_modelserver logs")
         sys.exit(1)

arch/tools/cli/main.py

@@ -171,7 +171,7 @@ def up(file, path, service):
         log.info(f"Error: {str(e)}")
         sys.exit(1)
 
-    log.info("Starging arch model server and arch gateway")
+    log.info("Starting arch model server and arch gateway")
 
     # Set the ARCH_CONFIG_FILE environment variable
     env_stage = {}