refactor: 更新文档，优化批量上传和解析脚本说明；移除不再支持的转换功能

Author: xerrors

docs/advanced/document-processing.md

@@ -60,7 +60,7 @@ docker compose up paddlex --build
 
 ## 批量处理脚本
 
-系统提供便捷的批量处理脚本，支持文件上传和解析操作。
+系统提供便捷的批量处理脚本，用于高效批量上传文档。
 
 ### 文件上传脚本
 
@@ -90,26 +90,6 @@ uv run scripts/batch_upload.py upload \
 
 提示：系统按“内容哈希”进行去重；同一知识库已存在相同内容的文件会被拒绝（409）。
 
-### 文件解析脚本
-
-使用 `scripts/batch_upload.py trans` 将文件解析为 Markdown：
-
-```bash
-# 批量解析文档
-uv run scripts/batch_upload.py trans \
-    --db-id your_kb_id \
-    --directory path/to/your/data \
-    --output-dir path/to/output_markdown \
-    --pattern "*.docx" \
-    --base-url http://127.0.0.1:5050/api \
-    --username your_username \
-    --password your_password \
-    --concurrency 4 \
-    --recursive
-```
-
-**输出结果**: 解析后的 Markdown 文件将保存到指定输出目录。
-
 ### 脚本功能
 
 - **进度跟踪**: 实时显示处理进度

docs/changelog/faq.md

@@ -32,7 +32,6 @@
 
 - 批量上传与转换示例？
   - 上传入库：`uv run scripts/batch_upload.py upload --db-id <id> --directory <dir> --username <u> --password <p> --base-url http://127.0.0.1:5050/api`
-  - 转 Markdown：`uv run scripts/batch_upload.py trans --db-id <id> --directory <dir> --username <u> --password <p>`
   - 参考：高级配置 → 文档解析
 
 - 登录失败被锁定？

docs/intro/knowledge-base.md

@@ -58,7 +58,6 @@ LightRAG 知识库可在知识库详情中可视化，但不支持在侧边栏
 ### 批量脚本
 
 - 上传并入库：参见 `scripts/batch_upload.py upload`
-- 转换为 Markdown：参见 `scripts/batch_upload.py trans`
 
 ## 知识图谱
 

scripts/batch_upload.py

@@ -230,74 +230,6 @@ def save_processed_files(record_file: pathlib.Path, processed_files: set[str]):
         console.print(f"[bold red]Error: Could not save processed files record: {e}[/bold red]")
 
 
-async def convert_to_markdown(
-    client: httpx.AsyncClient,
-    base_url: str,
-    db_id: str,
-    server_file_path: str,
-) -> str | None:
-    """Calls the file-to-markdown conversion endpoint."""
-    try:
-        response = await client.post(
-            f"{base_url}/knowledge/files/markdown",
-            json={"db_id": db_id, "file_path": server_file_path},
-            timeout=600,  # 10 minutes timeout for conversion
-        )
-        response.raise_for_status()
-        result = response.json()
-        if result.get("status") == "success":
-            return result.get("markdown_content")
-        else:
-            console.print(f"[bold red]Failed to convert {server_file_path}: {result.get('message')}[/bold red]")
-            return None
-    except httpx.HTTPStatusError as e:
-        console.print(
-            f"[bold red]Failed to convert {server_file_path}: {e.response.status_code} - {e.response.text}[/bold red]"
-        )
-        return None
-    except httpx.RequestError as e:
-        console.print(f"[bold red]Request failed for {server_file_path}: {e}[/bold red]")
-        return None
-
-
-async def trans_worker(
-    semaphore: asyncio.Semaphore,
-    client: httpx.AsyncClient,
-    base_url: str,
-    db_id: str,
-    file_path: pathlib.Path,
-    output_dir: pathlib.Path,
-    progress: Progress,
-    task_id: int,
-):
-    """A worker task that uploads a file and converts it to markdown."""
-    async with semaphore:
-        # 1. Upload file
-        server_file_path = await upload_file(client, base_url, db_id, file_path)
-        if not server_file_path:
-            progress.update(task_id, advance=1, postfix=f"[red]Upload failed for {file_path.name}[/red]")
-            return file_path, "upload_failed"
-
-        # 2. Convert file to markdown
-        markdown_content = await convert_to_markdown(client, base_url, db_id, server_file_path)
-        if not markdown_content:
-            progress.update(task_id, advance=1, postfix=f"[yellow]Conversion failed for {file_path.name}[/yellow]")
-            return file_path, "conversion_failed"
-
-        # 3. Save markdown content to output directory
-        try:
-            output_path = output_dir / file_path.with_suffix(".md").name
-            output_path.parent.mkdir(parents=True, exist_ok=True)
-            with open(output_path, "w", encoding="utf-8") as f:
-                f.write(markdown_content)
-            progress.update(task_id, advance=1, postfix=f"[green]Converted {file_path.name}[/green]")
-            return file_path, "success"
-        except OSError as e:
-            console.print(f"[bold red]Error saving markdown for {file_path.name}: {e}[/bold red]")
-            progress.update(task_id, advance=1, postfix=f"[red]Save failed for {file_path.name}[/red]")
-            return file_path, "save_failed"
-
-
 @app.command()
 def upload(
     db_id: str = typer.Option(..., help="The ID of the knowledge base."),
@@ -447,91 +379,6 @@ async def run():
     asyncio.run(run())
 
 
-@app.command()
-def trans(
-    db_id: str = typer.Option(..., help="The ID of the knowledge base (for temporary file upload)."),
-    directory: pathlib.Path = typer.Option(
-        ..., help="The directory containing files to convert.", exists=True, file_okay=False
-    ),
-    output_dir: pathlib.Path = typer.Option("output_markdown", help="The directory to save converted markdown files."),
-    pattern: str = typer.Option("*.docx", help="The glob pattern for files to convert (e.g., '*.pdf', '*.docx')."),
-    base_url: str = typer.Option("http://127.0.0.1:5050/api", help="The base URL of the API server."),
-    username: str = typer.Option(..., help="Admin username for login."),
-    password: str = typer.Option(..., help="Admin password for login."),
-    concurrency: int = typer.Option(4, help="The number of concurrent conversion tasks."),
-    recursive: bool = typer.Option(False, "--recursive", "-r", help="Search for files recursively in subdirectories."),
-):
-    """
-    Batch convert files to Markdown format.
-    """
-    console.print(f"[bold green]Starting batch conversion for files in: {directory}[/bold green]")
-    output_dir.mkdir(parents=True, exist_ok=True)
-
-    # Discover files
-    glob_method = directory.rglob if recursive else directory.glob
-    files_to_convert = list(glob_method(pattern))
-    if not files_to_convert:
-        console.print(f"[bold yellow]No files found in '{directory}' matching '{pattern}'. Aborting.[/bold yellow]")
-        raise typer.Exit()
-
-    # 过滤掉macos的隐藏文件
-    files_to_convert = [f for f in files_to_convert if not f.name.startswith("._")]
-
-    console.print(f"Found {len(files_to_convert)} files to convert.")
-
-    async def run():
-        async with httpx.AsyncClient() as client:
-            # Login
-            token = await login(client, base_url, username, password)
-            if not token:
-                raise typer.Exit(code=1)
-
-            client.headers = {"Authorization": f"Bearer {token}"}
-
-            # Setup concurrency and tasks
-            semaphore = asyncio.Semaphore(concurrency)
-            tasks = []
-
-            with Progress(
-                SpinnerColumn(),
-                TextColumn("[progress.description]{task.description}"),
-                BarColumn(),
-                TextColumn("[progress.percentage]{task.percentage:>3.0f}%"),
-                TimeElapsedColumn(),
-                TextColumn("{task.fields[postfix]}"),
-                console=console,
-                transient=True,
-            ) as progress:
-                task_id = progress.add_task("[bold blue]Converting...", total=len(files_to_convert), postfix="")
-
-                for file_path in files_to_convert:
-                    task = asyncio.create_task(
-                        trans_worker(semaphore, client, base_url, db_id, file_path, output_dir, progress, task_id)
-                    )
-                    tasks.append(task)
-
-                results = await asyncio.gather(*tasks)
-
-            # Summarize results
-            successful_files = []
-            failed_files = []
-
-            for file_path, status in results:
-                if status == "success":
-                    successful_files.append(file_path)
-                else:
-                    failed_files.append((file_path, status))
-
-            console.print("[bold green]Batch conversion complete.[/bold green]")
-            console.print(f"  - [green]Successful:[/green] {len(successful_files)}")
-            console.print(f"  - [red]Failed:[/red] {len(failed_files)}")
-            if failed_files:
-                for f, status in failed_files:
-                    console.print(f"    - {f} (Reason: {status})")
-
-    asyncio.run(run())
-
-
 """
 # Example for upload
 uv run scripts/batch_upload.py upload \
@@ -544,18 +391,6 @@ async def run():
     --concurrency 4 \
     --recursive \
     --record-file scripts/tmp/batch_processed_files.txt
-
-# Example for trans
-uv run scripts/batch_upload.py trans \
-    --db-id your_kb_id \
-    --directory path/to/your/data \
-    --output-dir path/to/output_markdown \
-    --pattern "*.docx" \
-    --base-url http://127.0.0.1:5050/api \
-    --username your_username \
-    --password your_password \
-    --concurrency 4 \
-    --recursive
 """
 if __name__ == "__main__":
     app()

src/storage/minio/client.py

@@ -51,8 +51,10 @@ def __init__(self):
                 host_ip = host_ip.split("://")[-1]
             host_ip = host_ip.rstrip("/")
             self.public_endpoint = f"{host_ip}:9000"
+            logger.debug(f"Docker MinIOClient public_endpoint: {self.public_endpoint}")
         else:
             self.public_endpoint = "localhost:9000"
+            logger.debug(f"Default_client: {self.public_endpoint}")
 
     @property
     def client(self) -> Minio: