diff --git a/CodeGen/docker_compose/intel/cpu/xeon/README.md b/CodeGen/docker_compose/intel/cpu/xeon/README.md
index f8cb1e03ff..b32b230175 100644
--- a/CodeGen/docker_compose/intel/cpu/xeon/README.md
+++ b/CodeGen/docker_compose/intel/cpu/xeon/README.md
@@ -83,13 +83,13 @@ Different Docker Compose files are available to select the LLM serving backend.
 
 - **Compose File:** `compose.yaml`
 - **Description:** Uses vLLM optimized for Intel CPUs as the LLM serving engine. This is the default deployment option used in the Quick Start.
-- **Services Deployed:** `codegen-vllm-server`, `codegen-llm-server`, `codegen-tei-embedding-server`, `codegen-retriever-server`, `redis-vector-db`, `codegen-dataprep-server`, `codegen-backend-server`, `codegen-gradio-ui-server`.
+- **Services Deployed:** `codegen-vllm-server`, `codegen-llm-server`, `codegen-tei-embedding-server`, `codegen-retriever-server`, `redis-vector-db`, `codegen-dataprep-server`, `codegen-backend-server`, `codegen-ui-server`.
 
 #### TGI-based Deployment (`compose_tgi.yaml`)
 
 - **Compose File:** `compose_tgi.yaml`
 - **Description:** Uses Hugging Face Text Generation Inference (TGI) optimized for Intel CPUs as the LLM serving engine.
-- **Services Deployed:** `codegen-tgi-server`, `codegen-llm-server`, `codegen-tei-embedding-server`, `codegen-retriever-server`, `redis-vector-db`, `codegen-dataprep-server`, `codegen-backend-server`, `codegen-gradio-ui-server`.
+- **Services Deployed:** `codegen-tgi-server`, `codegen-llm-server`, `codegen-tei-embedding-server`, `codegen-retriever-server`, `redis-vector-db`, `codegen-dataprep-server`, `codegen-backend-server`, `codegen-ui-server`.
 - **To Run:**
 
   ```bash
@@ -101,7 +101,7 @@ Different Docker Compose files are available to select the LLM serving backend.
 
 - **Compose File:** `compose_remote.yaml`
 - **Description:** Uses remote endpoints to access the served LLM's. This is the default configurations except for the LLM serving engine.
-- **Services Deployed:** `codegen-tei-embedding-server`, `codegen-retriever-server`, `redis-vector-db`, `codegen-dataprep-server`, `codegen-backend-server`, `codegen-gradio-ui-server`.
+- **Services Deployed:** `codegen-tei-embedding-server`, `codegen-retriever-server`, `redis-vector-db`, `codegen-dataprep-server`, `codegen-backend-server`, `codegen-ui-server`.
 - **To Run:**
 
 When models are deployed on a remote server, a base URL and an API key are required to access them. To set up a remote server and acquire the base URL and API key, refer to [Intel® AI for Enterprise Inference](https://www.intel.com/content/www/us/en/developer/topic-technology/artificial-intelligence/enterprise-inference.html) offerings.
@@ -158,7 +158,7 @@ Different Docker Compose files (`compose.yaml`, `compose_tgi.yaml`) control whic
 If you need to modify the microservices:
 
 1.  Clone the [OPEA GenAIComps](https://github.com/opea-project/GenAIComps) repository.
-2.  Follow build instructions in the respective component directories (e.g., `comps/llms/text-generation`, `comps/codegen`, `comps/ui/gradio`, etc.). Use the provided Dockerfiles (e.g., `CodeGen/Dockerfile`, `CodeGen/ui/docker/Dockerfile.gradio`).
+2.  Follow build instructions in the respective component directories (e.g., `comps/llms/text-generation`, `comps/codegen`, etc.). Use the provided Dockerfiles (e.g., `CodeGen/Dockerfile`, `CodeGen/ui/docker/Dockerfile`).
 3.  Tag your custom images appropriately (e.g., `my-custom-codegen:latest`).
 4.  Update the `image:` fields in the compose files (`compose.yaml` or `compose_tgi.yaml`) to use your custom image tags.
 
@@ -206,18 +206,17 @@ Use `curl` commands to test the main service endpoints. Ensure `HOST_IP` is corr
 
 Multiple UI options can be configured via the compose files.
 
-### Gradio UI (Default)
+### Svelte UI (Default)
 
-Access the default Gradio UI by navigating to:
+Access the default Svelte UI by navigating to:
 `http://{HOST_IP}:5173`
-_(Port `5173` is the default host mapping for `codegen-gradio-ui-server`)_
+_(Port `5173` is the default host mapping for `codegen-ui-server`)_
 
-![Gradio UI - Code Generation](../../../../assets/img/codegen_gradio_ui_main.png)
-![Gradio UI - Resource Management](../../../../assets/img/codegen_gradio_ui_dataprep.png)
+![Svelte UI - Code Generation](../../../../assets/img/codeGen_ui_init.jpg)
 
-### Svelte UI (Optional)
+### Gradio UI (Optional)
 
-1.  Modify the compose file (either `compose.yaml` or `compose_tgi.yaml`): Comment out the `codegen-gradio-ui-server` service and uncomment/add the `codegen-xeon-ui-server` (Svelte) service definition, ensuring the port mapping is correct (e.g., `"- 5173:5173"`).
+1.  Modify the compose file (either `compose.yaml` or `compose_tgi.yaml`): Comment out the `codegen-xeon-ui-server` (Svelte) service and uncomment/add the `codegen-gradio-ui-server` service definition, ensuring the port mapping is correct (e.g., `"- 5173:5173"`).
 2.  Restart Docker Compose: `docker compose up -d` or `docker compose -f compose_tgi.yaml up -d`
 3.  Access: `http://{HOST_IP}:5173` (or the host port you mapped).
 
diff --git a/CodeGen/docker_compose/intel/cpu/xeon/compose_remote.yaml b/CodeGen/docker_compose/intel/cpu/xeon/compose_remote.yaml
index e4ad0fd364..62b79796ee 100644
--- a/CodeGen/docker_compose/intel/cpu/xeon/compose_remote.yaml
+++ b/CodeGen/docker_compose/intel/cpu/xeon/compose_remote.yaml
@@ -26,7 +26,7 @@ services:
     ipc: host
     restart: always
   codegen-xeon-ui-server:
-    image: ${REGISTRY:-opea}/codegen-gradio-ui:${TAG:-latest}
+    image: ${REGISTRY:-opea}/codegen-ui:${TAG:-latest}
     container_name: codegen-xeon-ui-server
     depends_on:
       - codegen-xeon-backend-server
diff --git a/CodeGen/docker_compose/intel/hpu/gaudi/README.md b/CodeGen/docker_compose/intel/hpu/gaudi/README.md
index 0f1e438cf8..e96fab350d 100644
--- a/CodeGen/docker_compose/intel/hpu/gaudi/README.md
+++ b/CodeGen/docker_compose/intel/hpu/gaudi/README.md
@@ -83,7 +83,7 @@ There are two separate Docker Compose files to select the LLM serving backend ac
 - **Compose File:** `compose.yaml`
 - **Description:** Uses vLLM optimized for Intel Gaudi HPUs as the LLM serving engine. This is the default deployment used in the Quick Start.
 - **Gaudi Service:** `codegen-vllm-gaudi-server`
-- **Other Services:** `codegen-llm-server`, `codegen-tei-embedding-server` (CPU), `codegen-retriever-server` (CPU), `redis-vector-db` (CPU), `codegen-dataprep-server` (CPU), `codegen-backend-server` (CPU), `codegen-gradio-ui-server` (CPU).
+- **Other Services:** `codegen-llm-server`, `codegen-tei-embedding-server` (CPU), `codegen-retriever-server` (CPU), `redis-vector-db` (CPU), `codegen-dataprep-server` (CPU), `codegen-backend-server` (CPU), `codegen-ui-server` (CPU).
 
 ### TGI-based Deployment (`compose_tgi.yaml`)
 
@@ -194,23 +194,23 @@ Use `curl` commands targeting the main service endpoints. Ensure `HOST_IP` is co
 
 UI options are similar to the Xeon deployment.
 
-### Gradio UI (Default)
+### Svelte UI (Default)
 
-Access the default Gradio UI:
+Access the default Svelte UI:
 `http://{HOST_IP}:5173`
 _(Port `5173` is the default host mapping)_
 
-![Gradio UI](../../../../assets/img/codegen_gradio_ui_main.png)
+![Svelte UI](../../../../assets/img/codeGen_ui_init.jpg)
 
-### Svelte UI (Optional)
+### Gradio UI (Optional)
 
-1.  Modify the compose file (either `compose.yaml` or `compose_tgi.yaml`): Swap Gradio service for Svelte (`codegen-gaudi-ui-server`), check port map (e.g., `5173:5173`).
+1.  Modify the compose file (either `compose.yaml` or `compose_tgi.yaml`): Swap Svelte service for Gradio (`codegen-gradio-ui-server`), check port map (e.g., `5173:5173`).
 2.  Restart: `docker compose up -d` or `docker compose -f compose_tgi.yaml up -d`
 3.  Access: `http://{HOST_IP}:5173`
 
 ### React UI (Optional)
 
-1.  Modify the compose file (either `compose.yaml` or `compose_tgi.yaml`): Swap Gradio service for React (`codegen-gaudi-react-ui-server`), check port map (e.g., `5174:80`).
+1.  Modify the compose file (either `compose.yaml` or `compose_tgi.yaml`): Swap Svelte service for React (`codegen-gaudi-react-ui-server`), check port map (e.g., `5174:80`).
 2.  Restart: `docker compose up -d` or `docker compose -f compose_tgi.yaml up -d`
 3.  Access: `http://{HOST_IP}:5174`
 
diff --git a/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml b/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
index 92e2cb02da..6b33db7e82 100644
--- a/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
+++ b/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -74,7 +74,7 @@ services:
     ipc: host
     restart: always
   codegen-gaudi-ui-server:
-    image: ${REGISTRY:-opea}/codegen-gradio-ui:${TAG:-latest}
+    image: ${REGISTRY:-opea}/codegen-ui:${TAG:-latest}
     container_name: codegen-gaudi-ui-server
     depends_on:
       - codegen-gaudi-backend-server
diff --git a/CodeGen/docker_compose/intel/hpu/gaudi/compose_tgi.yaml b/CodeGen/docker_compose/intel/hpu/gaudi/compose_tgi.yaml
index 8339451000..aa8f4a51ea 100644
--- a/CodeGen/docker_compose/intel/hpu/gaudi/compose_tgi.yaml
+++ b/CodeGen/docker_compose/intel/hpu/gaudi/compose_tgi.yaml
@@ -74,7 +74,7 @@ services:
     ipc: host
     restart: always
   codegen-gaudi-ui-server:
-    image: ${REGISTRY:-opea}/codegen-gradio-ui:${TAG:-latest}
+    image: ${REGISTRY:-opea}/codegen-ui:${TAG:-latest}
     container_name: codegen-gaudi-ui-server
     depends_on:
       - codegen-gaudi-backend-server
diff --git a/CodeGen/tests/test_compose_on_epyc.sh b/CodeGen/tests/test_compose_on_epyc.sh
index 7e5b7bfcbd..56dfb45b37 100644
--- a/CodeGen/tests/test_compose_on_epyc.sh
+++ b/CodeGen/tests/test_compose_on_epyc.sh
@@ -29,7 +29,7 @@ function build_docker_images() {
 	popd && sleep 1s
 
 	echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-	service_list="codegen codegen-gradio-ui llm-textgen dataprep retriever embedding"
+	service_list="codegen codegen-ui llm-textgen dataprep retriever embedding"
 
 	docker compose -f build.yaml build ${service_list} --no-cache >${LOG_PATH}/docker_image_build.log
 
diff --git a/CodeGen/tests/test_compose_on_gaudi.sh b/CodeGen/tests/test_compose_on_gaudi.sh
index 25cf3a945d..f2f6bdd706 100644
--- a/CodeGen/tests/test_compose_on_gaudi.sh
+++ b/CodeGen/tests/test_compose_on_gaudi.sh
@@ -26,7 +26,7 @@ function build_docker_images() {
     popd && sleep 1s
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="codegen codegen-gradio-ui llm-textgen dataprep retriever embedding"
+    service_list="codegen codegen-ui llm-textgen dataprep retriever embedding"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker images && sleep 1s
diff --git a/CodeGen/tests/test_compose_tgi_on_epyc.sh b/CodeGen/tests/test_compose_tgi_on_epyc.sh
index 72fc88b4ae..347b322ccc 100644
--- a/CodeGen/tests/test_compose_tgi_on_epyc.sh
+++ b/CodeGen/tests/test_compose_tgi_on_epyc.sh
@@ -29,7 +29,7 @@ function build_docker_images() {
 	popd && sleep 1s
 
 	echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-	service_list="codegen codegen-gradio-ui llm-textgen dataprep retriever embedding"
+	service_list="codegen codegen-ui llm-textgen dataprep retriever embedding"
 
 	docker compose -f build.yaml build ${service_list} --no-cache >${LOG_PATH}/docker_image_build.log