x

docker/Dockerfile

@@ -303,8 +303,8 @@ RUN set -ex && \
 # ===========================================================================
 RUN set -ex && \
     export http_proxy=${GIT_PROXY} https_proxy=${GIT_PROXY} && \
-    ${VENV}/bin/pip install 'mineru[core]' click gradio && \
+    ${VENV}/bin/pip install 'mineru[core]' click gradio httpx && \
-    ${VENV}/bin/python -c "import torch; import vllm; import mineru; import click; import gradio; import mineru.cli.gradio_app; print('MinerU + Gradio CLI imports OK')" && \
+    ${VENV}/bin/python -c "import torch; import vllm; import mineru; import click; import gradio; import httpx; print('MinerU + Gradio + httpx imports OK')" && \
     ${VENV}/bin/mineru-gradio --help >/dev/null
 
 # ===========================================================================

docker/docker-compose.yml

@@ -4,7 +4,7 @@
 # =============================================================================
 
 services:
-  # --- WebUI 前端 ---
+  # --- WebUI 前端（纯前端，不本地处理，通过 Router → Worker 处理）---
   gradio:
     image: mineru-rocm:7.2.1
     profiles: ["gradio"]
@@ -16,6 +16,7 @@ services:
       - "10002:7860"
     environment:
       - GRADIO_SERVER_NAME=0.0.0.0
+      - MINERU_API_BASE=http://mineru-router:8000
       - MINERU_MODEL_SOURCE=${MINERU_MODEL_SOURCE:-huggingface}
       - HF_HUB_CACHE=${HF_HUB_CACHE:-/opt/models/huggingface}
       - MODELSCOPE_CACHE=${MODELSCOPE_CACHE:-/opt/models/modelscope}
@@ -26,10 +27,7 @@ services:
       - ./scripts:/opt/scripts:ro
     command:
       [
-        "mineru-gradio",
+        "/opt/mineru_venv/bin/python", "/opt/scripts/gradio_client.py",
-        "--server-name", "0.0.0.0",
-        "--server-port", "7860",
-        "--api-url", "http://mineru-router:8000",
       ]
     depends_on:
       - router

docker/scripts/gradio_client.py

@@ -0,0 +1,275 @@
+#!/usr/bin/env python3
+"""MinerU Gradio 客户端 — 纯前端，所有解析任务通过 HTTP 转发到 Router/Worker。
+
+与 mineru-gradio 的区别：
+- 不启动内嵌 FastAPI server
+- 不需要 GPU / vLLM
+- 通过 HTTP 调用 mineru-router → mineru-worker 处理任务
+"""
+import os
+import time
+import asyncio
+import tempfile
+import zipfile
+import json
+from pathlib import Path
+
+import gradio as gr
+import httpx
+
+API_BASE = os.environ.get("MINERU_API_BASE", "http://mineru-router:8000")
+DEFAULT_BACKEND = os.environ.get("MINERU_BACKEND", "hybrid-auto-engine")
+DEFAULT_LANG = os.environ.get("MINERU_LANG", "ch")
+POLL_INTERVAL = float(os.environ.get("MINERU_POLL_INTERVAL", "1.0"))
+MAX_WAIT = float(os.environ.get("MINERU_MAX_WAIT", "600"))
+
+
+async def discover_api(client: httpx.AsyncClient) -> str:
+    """探测实际可用的 API 前缀: /api/v1/tasks 或 /tasks"""
+    candidates = [
+        f"{API_BASE}/api/v1/health",
+        f"{API_BASE}/health",
+        f"{API_BASE}/docs",
+    ]
+    for url in candidates:
+        try:
+            r = await client.get(url, timeout=5)
+            if r.status_code < 500:
+                # FastAPI docs → /api/v1 ; plain health → /
+                if "/api/v1" in str(r.url):
+                    return "/api/v1/tasks"
+                return "/tasks"
+        except Exception:
+            continue
+    # 默认新版 API
+    return "/api/v1/tasks"
+
+
+async def submit_task(client: httpx.AsyncClient, api_prefix: str,
+                      file_path: str, file_name: str,
+                      backend: str, lang: str) -> dict:
+    """提交解析任务"""
+    submit_url = f"{API_BASE}{api_prefix}/submit"
+    with open(file_path, "rb") as f:
+        files = {"file": (file_name, f, "application/pdf")}
+        data = {
+            "backend": backend,
+            "lang": lang,
+        }
+        r = await client.post(submit_url, files=files, data=data, timeout=30)
+        r.raise_for_status()
+        return r.json()
+
+
+async def get_task_status(client: httpx.AsyncClient, api_prefix: str,
+                          task_id: str) -> dict:
+    """查询任务状态"""
+    url = f"{API_BASE}{api_prefix}/{task_id}"
+    r = await client.get(url, timeout=10)
+    r.raise_for_status()
+    return r.json()
+
+
+async def download_result(client: httpx.AsyncClient, api_prefix: str,
+                          task_id: str, output_dir: str) -> str:
+    """下载任务结果。尝试多种 endpoint 格式"""
+    candidates = [
+        f"{api_prefix}/{task_id}/data",
+        f"{api_prefix}/{task_id}/result",
+    ]
+    for suffix in candidates:
+        url = f"{API_BASE}{suffix}"
+        try:
+            r = await client.get(url, timeout=60, follow_redirects=True)
+            if r.status_code == 200:
+                # 下载 zip 文件
+                zip_path = os.path.join(output_dir, f"{task_id}.zip")
+                with open(zip_path, "wb") as f:
+                    f.write(r.content)
+                return zip_path
+        except Exception:
+            continue
+    raise RuntimeError(f"Failed to download result for task {task_id}")
+
+
+def extract_readme(zip_path: str, output_dir: str) -> str:
+    """解压结果并返回 markdown 内容"""
+    extract_dir = os.path.join(output_dir, "extracted")
+    os.makedirs(extract_dir, exist_ok=True)
+    with zipfile.ZipFile(zip_path, "r") as zf:
+        zf.extractall(extract_dir)
+    # 查找 markdown 文件
+    md_files = list(Path(extract_dir).rglob("*.md"))
+    if md_files:
+        return md_files[0].read_text(encoding="utf-8")
+    return "No markdown output found in result."
+
+
+# ---------------------------------------------------------------------------
+# Gradio 处理函数
+# ---------------------------------------------------------------------------
+async def process_pdf(file_obj, backend, lang, progress=gr.Progress()):
+    """Gradio 事件处理：上传 → 提交 → 轮询 → 返回结果"""
+    if file_obj is None:
+        return "Please upload a PDF file.", "", ""
+
+    tmp_dir = tempfile.mkdtemp(prefix="mineru-client-")
+    file_path = file_obj.name if hasattr(file_obj, "name") else os.path.join(tmp_dir, "input.pdf")
+    file_name = os.path.basename(file_path)
+
+    async with httpx.AsyncClient(timeout=httpx.Timeout(120)) as client:
+        # 1. 探测 API
+        progress(0.05, desc="Connecting to API...")
+        api_prefix = await discover_api(client)
+        progress(0.1, desc=f"API prefix: {api_prefix}")
+
+        # 2. 提交任务
+        progress(0.15, desc="Submitting task...")
+        try:
+            submit_resp = await submit_task(client, api_prefix, file_path, file_name, backend, lang)
+        except httpx.HTTPStatusError as e:
+            # 尝试旧版 endpoint（不带 /submit 后缀）
+            alt_data = {"backend": backend, "lang": lang}
+            try:
+                alt_url = f"{API_BASE}{api_prefix}"
+                with open(file_path, "rb") as f:
+                    files = {"file": (file_name, f, "application/pdf")}
+                    r = await client.post(alt_url, files=files, data=alt_data, timeout=30)
+                    r.raise_for_status()
+                    submit_resp = r.json()
+            except Exception as e2:
+                return f"Task submission failed: {e}\nAlt attempt: {e2}", "", ""
+
+        task_id = submit_resp.get("task_id") or submit_resp.get("data", {}).get("task_id")
+        if not task_id:
+            return f"Unexpected submit response:\n{json.dumps(submit_resp, indent=2)}", "", ""
+
+        progress(0.2, desc=f"Task ID: {task_id}")
+
+        # 3. 轮询状态
+        status_text = ""
+        start_time = time.time()
+        last_idx = -1
+        tickers = ["⣾", "⣽", "⣻", "⢿", "⡿", "⣟", "⣯", "⣷"]
+
+        while True:
+            elapsed = time.time() - start_time
+            if elapsed > MAX_WAIT:
+                return f"Task timed out after {MAX_WAIT}s\nLast status:\n{status_text}", "", ""
+
+            t = (int(elapsed * 2)) % len(tickers)
+            progress(min(0.2 + 0.6 * (elapsed / 60), 0.8),
+                     desc=f"{tickers[t]} Processing... ({int(elapsed)}s)")
+
+            try:
+                status_resp = await get_task_status(client, api_prefix, task_id)
+            except Exception as e:
+                status_text = f"Polling error: {e}"
+                await asyncio.sleep(POLL_INTERVAL)
+                continue
+
+            status = status_resp.get("status", "unknown")
+            progress_pct = status_resp.get("progress", 0)
+            err_msg = status_resp.get("error", "")
+            status_text = json.dumps(status_resp, indent=2, ensure_ascii=False)
+
+            if status == "completed" or status == "success":
+                progress(0.85, desc="Downloading result...")
+                break
+            elif status == "failed":
+                return f"## Task Failed\n\nError: {err_msg}\n\n```json\n{status_text}\n```", "", ""
+            elif status == "processing":
+                pass
+            else:
+                pass
+
+            await asyncio.sleep(POLL_INTERVAL)
+
+        # 4. 下载结果
+        progress(0.9, desc="Downloading result...")
+        try:
+            zip_path = await download_result(client, api_prefix, task_id, tmp_dir)
+        except Exception as e:
+            return f"Result download failed: {e}\n\nStatus:\n{status_text}", "", ""
+
+        # 5. 提取 markdown
+        progress(0.95, desc="Extracting results...")
+        try:
+            md_content = extract_readme(zip_path, tmp_dir)
+        except Exception as e:
+            md_content = f"Extraction error: {e}"
+
+        progress(1.0, desc="Done!")
+        return md_content, status_text, zip_path
+
+
+# ---------------------------------------------------------------------------
+# Gradio UI
+# ---------------------------------------------------------------------------
+def create_ui():
+    custom_css = """
+    .result-panel { min-height: 400px; }
+    .status-panel { min-height: 200px; font-size: 13px; }
+    """
+    with gr.Blocks(css=custom_css, title="MinerU ROCm — Document Parser") as demo:
+        gr.Markdown("""
+        # MinerU ROCm — Document Parser
+
+        Upload a PDF file. Processing is handled by the **mineru-router → mineru-worker** backend.
+        """)
+
+        with gr.Row():
+            with gr.Column(scale=1):
+                file_input = gr.File(
+                    label="Upload PDF",
+                    file_types=[".pdf"],
+                    type="filepath",
+                )
+                backend_dd = gr.Dropdown(
+                    label="Backend",
+                    choices=["hybrid-auto-engine", "hybrid-http-client",
+                             "vlm-http-client", "pipeline", "auto"],
+                    value=DEFAULT_BACKEND,
+                )
+                lang_dd = gr.Dropdown(
+                    label="Language",
+                    choices=["ch", "en", "japan", "korean"],
+                    value=DEFAULT_LANG,
+                )
+                submit_btn = gr.Button("Parse Document", variant="primary", size="lg")
+                status_display = gr.Textbox(
+                    label="Status",
+                    lines=6,
+                    max_lines=12,
+                    elem_classes=["status-panel"],
+                )
+                zip_display = gr.File(
+                    label="Download Result ZIP",
+                    type="filepath",
+                    visible=True,
+                )
+
+            with gr.Column(scale=2):
+                result_display = gr.Markdown(
+                    value="*Upload a PDF to start parsing...*",
+                    elem_classes=["result-panel"],
+                )
+
+        submit_btn.click(
+            fn=process_pdf,
+            inputs=[file_input, backend_dd, lang_dd],
+            outputs=[result_display, status_display, zip_display],
+        )
+
+    return demo
+
+
+if __name__ == "__main__":
+    server_name = os.environ.get("GRADIO_SERVER_NAME", "0.0.0.0")
+    server_port = int(os.environ.get("GRADIO_SERVER_PORT", "7860"))
+    demo = create_ui()
+    demo.queue(default_concurrency_limit=3, max_size=10).launch(
+        server_name=server_name,
+        server_port=server_port,
+        share=False,
+    )