volcengine · qin-ctx · Aug 12, 2026 · Aug 12, 2026 · Aug 12, 2026
diff --git a/docs/en/api/02-resources.md b/docs/en/api/02-resources.md
@@ -12,19 +12,19 @@ OpenViking supports various resource types, categorized by functionality:
 
 | Type | Extensions | Description |
 |------|------------|-------------|
-| PDF | `.pdf` | Supports local parsing and MinerU API conversion |
+| PDF | `.pdf` | Uses pdf-inspector for page text, headings, tables, and reading order; pdfplumber extracts images after each page's text. Pages that require OCR are kept with explicit warnings |
 | Markdown | `.md`, `.markdown`, `.mdown`, `.mkd` | Native support, extracts structure and stores in segments |
 | HTML | `.html`, `.htm` | Cleans navigation/ads and extracts content, converts to Markdown |
-| Word | `.docx` | Extracts text, headings, tables and converts to Markdown |
+| Word | `.doc`, `.docx` | Uses AnyDoc to preserve text, headings, tables, and embedded image positions in Markdown |
 | Plain Text | `.txt`, `.text` | Direct import and processing |
-| EPUB | `.epub` | E-book format, supports ebooklib or manual extraction |
+| EPUB | `.epub` | Uses AnyDoc to convert the e-book structure and embedded images to Markdown |
 
 **Spreadsheets & Presentations**
 
 | Type | Extensions | Description |
 |------|------------|-------------|
-| Excel | `.xlsx`, `.xls`, `.xlsm` | Supports new and legacy Excel formats, converts to Markdown tables by worksheet |
-| PowerPoint | `.pptx` | Extracts content by slide, supports extracting notes |
+| Excel | `.xlsx`, `.xls`, `.xlsm` | Uses AnyDoc to convert worksheets to Markdown |
+| PowerPoint | `.pptx` | Uses AnyDoc to preserve slide content and embedded image positions; speaker notes stay in the same resource under `Speaker Notes` sections |
 
 **Code**
 

diff --git a/docs/en/configuration/01-server.md b/docs/en/configuration/01-server.md
@@ -336,7 +336,6 @@ Parsers live under `parsers`:
     "audio": {},
     "video": {},
     "markdown": {},
-    "excel": {},
     "html": {},
     "text": {},
     "directory": {},
@@ -357,8 +356,7 @@ Parsers live under `parsers`:
 | `code` | Repository file types, ignore rules, and network safety |
 | `image` | Image understanding and OCR |
 | `audio`, `video` | Audio/video parsing |
-| `markdown`, `html`, `text` | Text document chunking |
-| `excel` | Workbook parsing and chunking |
+| `markdown`, `html`, `text` | Text document chunking; AnyDoc-backed Office and EPUB files reuse the `markdown` sectioning settings |
 | `directory` | Directory scanning and ignore rules |
 | `feishu` | Feishu/Lark access and parsing |
 | `webfeed` | Sitemap, RSS, and Atom ingestion |

diff --git a/docs/zh/api/02-resources.md b/docs/zh/api/02-resources.md
@@ -11,18 +11,18 @@ OpenViking 支持多种资源类型，按照功能分类如下：
 文档类
 | 类型 | 扩展名 | 说明 |
 |------|--------|------|
-| PDF | `.pdf` | 支持本地解析和 MinerU API 转换 |
+| PDF | `.pdf` | 由 pdf-inspector 提取分页文本、标题、表格和阅读顺序，pdfplumber 在每页正文后提取图片；需要 OCR 的页面会保留并给出明确警告 |
 | Markdown | `.md`, `.markdown`, `.mdown`, `.mkd` | 原生支持，会提取结构并分段存储 |
 | HTML | `.html`, `.htm` | 清理导航/广告后提取内容，转换为 Markdown |
-| Word | `.docx` | 提取文本、标题、表格并转换为 Markdown |
+| Word | `.doc`, `.docx` | 通过 AnyDoc 将文本、标题、表格和嵌入图片的原始位置转换为 Markdown |
 | 纯文本 | `.txt`, `.text` | 直接导入处理 |
-| EPUB | `.epub` | 电子书格式，支持 ebooklib 或手动提取 |
+| EPUB | `.epub` | 通过 AnyDoc 将电子书结构和嵌入图片转换为 Markdown |
 
 表格类
 | 类型 | 扩展名 | 说明 |
 |------|--------|------|
-| Excel | `.xlsx`, `.xls`, `.xlsm` | 支持新版和老版 Excel，按工作表转换为 Markdown 表格 |
-| PowerPoint | `.pptx` | 按幻灯片提取内容，支持提取备注 |
+| Excel | `.xlsx`, `.xls`, `.xlsm` | 通过 AnyDoc 将工作表转换为 Markdown |
+| PowerPoint | `.pptx` | 通过 AnyDoc 保留幻灯片内容和嵌入图片位置；演讲者备注保留在同一资源的 `Speaker Notes` 分节中 |
 
 代码类
 | 类型 | 资源名 | 说明 |

diff --git a/docs/zh/configuration/01-server.md b/docs/zh/configuration/01-server.md
@@ -336,7 +336,6 @@ Provider 和密钥管理配置见[加密指南](../guides/08-encryption.md)。
     "audio": {},
     "video": {},
     "markdown": {},
-    "excel": {},
     "html": {},
     "text": {},
     "directory": {},
@@ -357,8 +356,7 @@ Provider 和密钥管理配置见[加密指南](../guides/08-encryption.md)。
 | `code` | 代码仓库文件类型、忽略规则和安全限制 |
 | `image` | 图片理解和 OCR |
 | `audio`、`video` | 音视频内容解析 |
-| `markdown`、`html`、`text` | 文本文档分段 |
-| `excel` | Excel 工作表解析与分段 |
+| `markdown`、`html`、`text` | 文本文档分段；由 AnyDoc 解析的 Office 和 EPUB 文件复用 `markdown` 分段配置 |
 | `directory` | 目录扫描和忽略规则 |
 | `feishu` | 飞书文档访问与解析 |
 | `webfeed` | Sitemap、RSS 和 Atom 导入 |

diff --git a/examples/ov.conf.example b/examples/ov.conf.example
@@ -223,14 +223,10 @@
     },
     "parsers": {
         "pdf": {
-            "strategy": "auto",
             "max_content_length": 100000,
             "max_section_size": 4000,
             "section_size_flexibility": 0.3,
             "max_section_chars": 6000,
-            "mineru_endpoint": "https://mineru.example.com/api/v1",
-            "mineru_api_key": "{your-mineru-api-key}",
-            "mineru_timeout": 300.0,
         },
         "code": {
             "github_raw_domain": "raw.githubusercontent.com",

diff --git a/openviking/parse/image_validation.py b/openviking/parse/image_validation.py
@@ -0,0 +1,58 @@
+# Copyright (c) 2026 Beijing Volcano Engine Technology Co., Ltd.
+# SPDX-License-Identifier: AGPL-3.0
+"""Shared acceptance policy for images embedded in parsed documents."""
+
+import io
+from pathlib import Path
+
+from openviking_cli.utils.logger import get_logger
+
+logger = get_logger(__name__)
+
+IMAGE_MIN_SIDE = 14
+IMAGE_MIN_PIXELS = 196
+IMAGE_MAX_PIXELS = 36_000_000
+IMAGE_MIN_ASPECT_RATIO = 1 / 150
+IMAGE_MAX_ASPECT_RATIO = 150
+IMAGE_MAX_FILE_BYTES = 10 * 1024 * 1024
+
+
+def is_valid_image(image_bytes: bytes, source_path: Path) -> bool:
+    """Return whether an extracted image is safe and useful to ingest."""
+    if len(image_bytes) > IMAGE_MAX_FILE_BYTES:
+        logger.warning(f"[ImageValidation] Image exceeds 10MB, skipping: {source_path}")
+        return False
+
+    try:
+        from PIL import Image
+
+        with Image.open(io.BytesIO(image_bytes)) as image:
+            width, height = image.size
+    except Exception as exc:
+        logger.warning(
+            f"[ImageValidation] Cannot read image dimensions, skipping {source_path}: {exc}"
+        )
+        return False
+
+    if width <= IMAGE_MIN_SIDE or height <= IMAGE_MIN_SIDE:
+        logger.warning(
+            f"[ImageValidation] Image side too small ({width}x{height}), skipping: {source_path}"
+        )
+        return False
+
+    pixels = width * height
+    if pixels < IMAGE_MIN_PIXELS or pixels > IMAGE_MAX_PIXELS:
+        logger.warning(
+            f"[ImageValidation] Image pixel count out of range ({pixels}), skipping: {source_path}"
+        )
+        return False
+
+    aspect_ratio = width / height
+    if aspect_ratio < IMAGE_MIN_ASPECT_RATIO or aspect_ratio > IMAGE_MAX_ASPECT_RATIO:
+        logger.warning(
+            f"[ImageValidation] Image aspect ratio out of range ({aspect_ratio:.4f}), "
+            f"skipping: {source_path}"
+        )
+        return False
+
+    return True
diff --git a/openviking/parse/parsers/__init__.py b/openviking/parse/parsers/__init__.py
@@ -1,26 +1,20 @@
 # Copyright (c) 2026 Beijing Volcano Engine Technology Co., Ltd.
 # SPDX-License-Identifier: AGPL-3.0
 
+from .anydoc import AnyDocParser
 from .base_parser import BaseParser
-from .epub import EPubParser
-from .excel import ExcelParser
 from .html import HTMLParser
 from .markdown import MarkdownParser
 from .pdf import PDFParser
-from .powerpoint import PowerPointParser
 from .text import TextParser
-from .word import WordParser
 from .zip_parser import ZipParser
 
 __all__ = [
+    "AnyDocParser",
     "BaseParser",
-    "EPubParser",
-    "ExcelParser",
     "HTMLParser",
     "MarkdownParser",
     "PDFParser",
-    "PowerPointParser",
     "TextParser",
-    "WordParser",
     "ZipParser",
 ]