Enhance embedding model component and Docker builds

Switches Docker Compose services to local builds for backend, frontend, and langflow. Updates embedding model component to support IBM watsonx.ai features, including input token truncation and original text output, adds new dependencies, and improves configuration options in ingestion and agent flows.

docker-compose.yml

@@ -45,9 +45,9 @@ services:
 
   openrag-backend:
     image: phact/openrag-backend:${OPENRAG_VERSION:-latest}
-    # build:
-    #   context: .
-    #   dockerfile: Dockerfile.backend
+    build:
+      context: .
+      dockerfile: Dockerfile.backend
     container_name: openrag-backend
     depends_on:
       - langflow
@@ -89,9 +89,9 @@ services:
 
   openrag-frontend:
     image: phact/openrag-frontend:${OPENRAG_VERSION:-latest}
-    # build:
-    #   context: .
-    #   dockerfile: Dockerfile.frontend
+    build:
+      context: .
+      dockerfile: Dockerfile.frontend
     container_name: openrag-frontend
     depends_on:
       - openrag-backend
@@ -104,9 +104,9 @@ services:
     volumes:
       - ./flows:/app/flows:U,z
     image: phact/openrag-langflow:${LANGFLOW_VERSION:-latest}
-    # build:
-    #   context: .
-    #   dockerfile: Dockerfile.langflow
+    build:
+      context: .
+      dockerfile: Dockerfile.langflow
     container_name: langflow
     ports:
       - "7860:7860"