rename archgw_model_sever => model_server (#106)

arch/docker-compose.yaml

@@ -11,10 +11,10 @@ services:
       - /etc/ssl/cert.pem:/etc/ssl/cert.pem
       - ./arch_log:/var/log/
     depends_on:
-      archgw_model_server:
+      model_server:
         condition: service_healthy
 
-  archgw_model_server:
+  model_server:
     build:
       context: ../model_server
       dockerfile: Dockerfile

arch/envoy.template.yaml

@@ -132,20 +132,20 @@ static_resources:
         typed_config:
           "@type": type.googleapis.com/envoy.extensions.transport_sockets.tls.v3.UpstreamTlsContext
           sni: api.mistral.ai
-    - name: archgw_model_server
+    - name: model_server
       connect_timeout: 5s
       type: STRICT_DNS
       lb_policy: ROUND_ROBIN
       load_assignment:
-        cluster_name: archgw_model_server
+        cluster_name: model_server
         endpoints:
           - lb_endpoints:
               - endpoint:
                   address:
                     socket_address:
-                      address: archgw_model_server
+                      address: model_server
                       port_value: 80
-                  hostname: "archgw_model_server"
+                  hostname: "model_server"
     - name: mistral_7b_instruct
       connect_timeout: 5s
       type: STRICT_DNS
@@ -171,7 +171,7 @@ static_resources:
               - endpoint:
                   address:
                     socket_address:
-                      address: archgw_model_server
+                      address: model_server
                       port_value: 80
                   hostname: "arch_fc"
 {% for _, cluster in arch_clusters.items() %}

arch/src/consts.rs

@@ -7,6 +7,6 @@ pub const USER_ROLE: &str = "user";
 pub const GPT_35_TURBO: &str = "gpt-3.5-turbo";
 pub const ARC_FC_CLUSTER: &str = "arch_fc";
 pub const ARCH_FC_REQUEST_TIMEOUT_MS: u64 = 120000; // 2 minutes
-pub const MODEL_SERVER_NAME: &str = "archgw_model_server";
+pub const MODEL_SERVER_NAME: &str = "model_server";
 pub const ARCH_ROUTING_HEADER: &str = "x-arch-llm-provider";
 pub const ARCH_MESSAGES_KEY: &str = "arch_messages";

arch/tests/integration.rs

@@ -104,7 +104,7 @@ fn normal_flow(module: &mut Tester, filter_context: i32, http_context: i32) {
         .expect_get_buffer_bytes(Some(BufferType::HttpRequestBody))
         .returning(Some(chat_completions_request_body))
         // The actual call is not important in this test, we just need to grab the token_id
-        .expect_http_call(Some("archgw_model_server"), None, None, None, None)
+        .expect_http_call(Some("model_server"), None, None, None, None)
         .returning(Some(1))
         .expect_log(Some(LogLevel::Debug), None)
         .expect_metric_increment("active_http_calls", 1)
@@ -136,7 +136,7 @@ fn normal_flow(module: &mut Tester, filter_context: i32, http_context: i32) {
         .returning(Some(&embeddings_response_buffer))
         .expect_log(Some(LogLevel::Debug), None)
         .expect_log(Some(LogLevel::Debug), None)
-        .expect_http_call(Some("archgw_model_server"), None, None, None, None)
+        .expect_http_call(Some("model_server"), None, None, None, None)
         .returning(Some(2))
         .expect_metric_increment("active_http_calls", 1)
         .expect_log(Some(LogLevel::Debug), None)
@@ -313,7 +313,7 @@ fn successful_request_to_open_ai_chat_completions() {
         .returning(Some(chat_completions_request_body))
         .expect_log(Some(LogLevel::Debug), None)
         .expect_log(Some(LogLevel::Info), None)
-        .expect_http_call(Some("archgw_model_server"), None, None, None, None)
+        .expect_http_call(Some("model_server"), None, None, None, None)
         .returning(Some(4))
         .expect_metric_increment("active_http_calls", 1)
         .execute_and_expect(ReturnType::Action(Action::Pause))

demos/employee_details_copilot/docker-compose.yaml

@@ -28,7 +28,7 @@ services:
     environment:
       - LOG_LEVEL=debug
 
-  archgw_model_server:
+  model_server:
     build:
       context: ../../model_server
       dockerfile: Dockerfile

demos/employee_details_copilot_arch/docker-compose.yaml

@@ -28,7 +28,7 @@ services:
     environment:
       - LOG_LEVEL=debug
 
-  archgw_model_server:
+  model_server:
     build:
       context: ../../model_server
       dockerfile: Dockerfile

demos/function_calling/docker-compose.yaml

@@ -1,14 +1,5 @@
 services:
 
-  config_generator:
-    build:
-      context: ../../
-      dockerfile: config_generator/Dockerfile
-    volumes:
-      - ../../arch/envoy.template.yaml:/usr/src/app/envoy.template.yaml
-      - ./arch_config.yaml:/usr/src/app/arch_config.yaml
-      - ./generated:/usr/src/app/out
-
   arch:
     build:
       context: ../../
@@ -21,14 +12,12 @@ services:
       - /etc/ssl/cert.pem:/etc/ssl/cert.pem
       - ./arch_log:/var/log/
     depends_on:
-      config_generator:
-        condition: service_completed_successfully
       model_server:
         condition: service_healthy
     environment:
       - LOG_LEVEL=debug
 
-  archgw_model_server:
+  model_server:
     build:
       context: ../../model_server
       dockerfile: Dockerfile

demos/network_copilot/docker-compose.yaml

@@ -28,7 +28,7 @@ services:
     environment:
       - LOG_LEVEL=debug
 
-  archgw_model_server:
+  model_server:
     build:
       context: ../../model_server
       dockerfile: Dockerfile

demos/prompt_guards/docker-compose.yaml

@@ -29,7 +29,7 @@ services:
     environment:
       - LOG_LEVEL=debug
 
-  archgw_model_server:
+  model_server:
     build:
       context: ../../model_server
       dockerfile: Dockerfile

gateway.code-workspace

@@ -16,14 +16,6 @@
       "name": "chatbot_ui",
       "path": "chatbot_ui"
     },
-    {
-      "name": "open-message-format",
-      "path": "open-message-format"
-    },
-    {
-      "name": "config_generator",
-      "path": "config_generator"
-    },
     {
       "name": "demos/function_calling",
       "path": "./demos/function_calling",