docs: rewrite install and usage docs

next_docs/en/user_guide/usage/docker.rst

+
+
+Docker 
+=======
+
+.. admonition:: Important
+   :class: tip
+
+   Docker requires a GPU with at least 16GB of VRAM, and all acceleration features are enabled by default.
+
+   Before running this Docker, you can use the following command to check if your device supports CUDA acceleration on Docker. 
+
+   .. code-block:: bash
+
+      bash  docker run --rm --gpus=all nvidia/cuda:12.1.0-base-ubuntu22.04 nvidia-smi
+
+
+.. code:: sh
+
+   wget https://github.com/opendatalab/MinerU/raw/master/Dockerfile
+   docker build -t mineru:latest .
+   docker run --rm -it --gpus=all mineru:latest /bin/bash
+   magic-pdf --help
+

next_docs/zh_cn/user_guide/data/data_reader_writer.rst

@@ -111,11 +111,11 @@ S3DataReader 基于 MultiBucketS3DataReader 构建，但仅支持单个桶。S3D
 
     # S3 相关的
     s3_reader1 = S3DataReader(
-        default_prefix_without_bucket = "test_prefix",
-        bucket: "test_bucket",
-        ak: "ak",
-        sk: "sk",
-        endpoint_url: "localhost"
+        "test_prefix",
+        "test_bucket",
+        "ak",
+        "sk",
+        "localhost"
     )
 
     ## 将读取 s3://test_bucket/test_prefix/abc 
@@ -172,11 +172,11 @@ S3DataReader 基于 MultiBucketS3DataReader 构建，但仅支持单个桶。S3D
 
     # S3 相关的
     s3_writer1 = S3DataWriter(
-        default_prefix_without_bucket = "test_prefix",
-        bucket: "test_bucket",
-        ak: "ak",
-        sk: "sk",
-        endpoint_url: "localhost"
+        "test_prefix",
+        "test_bucket",
+        "ak",
+        "sk",
+        "localhost"
     )
 
     ## 将写入 123 到 s3://test_bucket/test_prefix/abc 

next_docs/zh_cn/user_guide/data/read_api.rst

@@ -15,13 +15,41 @@ read_jsonl
 
 .. code:: python
 
-    from magic_pdf.data.io.read_api import *
+    from magic_pdf.data.read_api import *
+    from magic_pdf.data.data_reader_writer import MultiBucketS3DataReader
+    from magic_pdf.data.schemas import S3Config
 
-    # 从本地机器读取 JSONL
-    datasets = read_jsonl("tt.jsonl", None)
+    # 读取本地 jsonl 文件
+    datasets = read_jsonl("tt.jsonl", None)   # 替换为有效的文件
+
+    # 读取 s3 jsonl 文件
+
+    bucket = "bucket_1"                     # 替换为有效的 s3 bucket
+    ak = "access_key_1"                     # 替换为有效的 s3 access key
+    sk = "secret_key_1"                     # 替换为有效的 s3 secret key
+    endpoint_url = "endpoint_url_1"         # 替换为有效的 s3 endpoint url
+
+    bucket_2 = "bucket_2"                   # 替换为有效的 s3 bucket
+    ak_2 = "access_key_2"                   # 替换为有效的 s3 access key
+    sk_2 = "secret_key_2"                   # 替换为有效的 s3 secret key
+    endpoint_url_2 = "endpoint_url_2"       # 替换为有效的 s3 endpoint url
+
+    s3configs = [
+        S3Config(
+            bucket_name=bucket, access_key=ak, secret_key=sk, endpoint_url=endpoint_url
+        ),
+        S3Config(
+            bucket_name=bucket_2,
+            access_key=ak_2,
+            secret_key=sk_2,
+            endpoint_url=endpoint_url_2,
+        ),
+    ]
+
+    s3_reader = MultiBucketS3DataReader(bucket, s3configs)
+
+    datasets = read_jsonl(f"s3://bucket_1/tt.jsonl", s3_reader)  # 替换为有效的 s3 jsonl file
 
-    # 从远程 S3 读取 JSONL
-    datasets = read_jsonl("s3://bucket_1/tt.jsonl", s3_reader)
 
 read_local_pdfs
 ^^^^^^^^^^^^^^^^
@@ -30,7 +58,7 @@ read_local_pdfs
 
 .. code:: python
 
-    from magic_pdf.data.io.read_api import *
+    from magic_pdf.data.read_api import *
 
     # 读取 PDF 路径
     datasets = read_local_pdfs("tt.pdf")
@@ -45,7 +73,7 @@ read_local_images
 
 .. code:: python
 
-    from magic_pdf.data.io.read_api import *
+    from magic_pdf.data.read_api import *
 
     # 从图像路径读取
     datasets = read_local_images("tt.png")