diff --git a/README_zh.md b/README_zh.md
index 63d605a3..8b2aefad 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -140,10 +140,9 @@
    $ docker compose -f docker-compose.yml up -d
    ```
 
-   > 请注意，运行上述命令会自动下载 RAGFlow 的开发版本 docker 镜像。如果你想下载并运行特定版本的 docker 镜像，请在 docker/.env 文件中找到 RAGFLOW_IMAGE 变量，将其改为对应版本。例如 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.12.0-slim`，然后运行上述命令。
-
-   > 核心镜像下载大小为 1 GB，可能需要一定时间拉取。请耐心等待。
-
+   > 运行上述命令会自动下载 RAGFlow 的 dev-slim 版本的 Docker 镜像，该镜像并不包含 embedding 模型以及一些 Python 库，因此镜像大小约 1GB。如果你想下载并运行特定版本的 Docker 镜像，请在 docker/slim.env 文件中找到 RAGFLOW_IMAGE 变量，将其改为对应版本。例如 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.12.0-slim`，然后再运行上述命令。
+   > 如果您想安装内置 embedding 模型的 dev 版本的 docker 镜像，需要把docker/.env文件中 RAGFLOW_IMAGE 变量，这样的修改： `RAGFLOW_IMAGE=infiniflow/ragflow:dev`。如果您想指定指定特定版本，则可以修改为：`RAGFLOW_IMAGE=infiniflow/ragflow:v0.12.0`。修改后，再运行上面的命令。注意 dev 版本的 RAGFlow Docker image 大小约 9 GB，可能需要一定时间下载，请耐心等待。
+   
 4. 服务器启动成功后再次确认服务器状态：
 
    ```bash
diff --git a/docker/.env b/docker/.env
index aaf86ab1..8cb40201 100644
--- a/docker/.env
+++ b/docker/.env
@@ -1,7 +1,6 @@
 # Version of Elastic products
 STACK_VERSION=8.11.3
 
-
 # Port to expose Elasticsearch HTTP API to the host
 ES_PORT=1200
 
@@ -13,11 +12,10 @@ KIBANA_PORT=6601
 KIBANA_USER=rag_flow
 KIBANA_PASSWORD=infini_rag_flow
 
-# Increase or decrease based on the available host memory (in bytes)
+# Update according to the available host memory (in bytes)
 
 MEM_LIMIT=8073741824
 
-
 MYSQL_PASSWORD=infini_rag_flow
 MYSQL_PORT=5455
 
@@ -33,21 +31,45 @@ REDIS_PASSWORD=infini_rag_flow
 
 SVR_HTTP_PORT=9380
 
+# the Docker image for the slim version
 RAGFLOW_IMAGE=infiniflow/ragflow:dev-slim
 
-# If can't download RAGFlow docker image, try to uncomment either of the following hub.docker.com mirrors:
+# If you cannot download the RAGFlow Docker image, try uncommenting either of the following hub.docker.com mirrors:
 # RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:dev-slim
 # RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:dev-slim
 
+# To download the RAGFlow Docker image with embedding models, modify the line above as follows:
+# RAGFLOW_IMAGE=infiniflow/ragflow:dev
+
+# This Docker image includes the following four models:
+# - BAAI/bge-large-zh-v1.5
+# - BAAI/bge-reranker-v2-m3
+# - maidalun1020/bce-embedding-base_v1
+# - maidalun1020/bce-reranker-base_v1
+
+# And the following models will be downloaded if you select them in the RAGFlow UI.
+# - BAAI/bge-base-en-v1.5
+# - BAAI/bge-large-en-v1.5
+# - BAAI/bge-small-en-v1.5
+# - BAAI/bge-small-zh-v1.5
+# - jinaai/jina-embeddings-v2-base-en
+# - jinaai/jina-embeddings-v2-small-en
+# - nomic-ai/nomic-embed-text-v1.5
+# - sentence-transformers/all-MiniLM-L6-v2
+
+# If you cannot download the RAGFlow Docker image, try uncommenting either of the following hub.docker.com mirrors:
+# RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:dev
+# RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:dev
+
 TIMEZONE='Asia/Shanghai'
 
-# If can't download models, try to uncomment the following huggingface.co mirror:
+# If you cannot download the RAGFlow Docker image, try uncommenting the following huggingface.co mirror:
 # HF_ENDPOINT=https://hf-mirror.com
 
 ######## OS setup for ES ###########
 # sysctl vm.max_map_count
 # sudo sysctl -w vm.max_map_count=262144
-# However, this change is not persistent and will be reset after a system reboot.
-# To make the change permanent, you need to update the /etc/sysctl.conf file.
-# Add or update the following line in the file:
+# Note that this change is not permanent and will be reset after a system reboot.
+# To make your change permanent, update /etc/sysctl.conf by:
+# Adding or modifying the following line:
 # vm.max_map_count=262144