Update .gitignore and enhance README with new project plans
- Added `RAG_data/` to .gitignore to prevent tracking of specific data files. - Expanded the README to include detailed plans for document type-specific chunk templates, improvements in document understanding, OCR accuracy, and layout detection design. - Removed several outdated user manuals and documents to streamline the repository.
This commit is contained in:
@@ -13,6 +13,7 @@ storage/uploads/
|
||||
storage/results/
|
||||
storage/assets/
|
||||
output/
|
||||
RAG_data/
|
||||
|
||||
# IDE / local agent / task notes (keep local only)
|
||||
.idea/
|
||||
|
||||
@@ -428,7 +428,10 @@ hits, n = recall_chunks("login password", result.chunks, top_k=5)
|
||||
|
||||
## 后续计划
|
||||
|
||||
- [ ] PDF OCR / 视觉描述增强
|
||||
- [ ] **按文档类型提供专用 Chunk 模板**:在现有通用、按行和标识符切分的基础上,为论文、书籍、法律法规、演示文稿、问答和表格等文档提供结构感知的模板,并保留章节路径、页码、内容类型等元数据。
|
||||
- [ ] **参考 RAGFlow DeepDoc 完善文档理解层**:在切分前统一完成 OCR、版面分析、表格结构识别、图片/图注关联和文档结构恢复,输出标准化 Block / Document Tree,供不同 Chunk 模板复用。
|
||||
- [ ] **完善 OCR 精准识别**:增强扫描 PDF、文档内嵌图片和复杂背景图片的文字识别,补充方向校正、语言检测、置信度过滤与识别结果回填,并建立可量化的准确率评测集。
|
||||
- [ ] **引入 Layout Detection 设计**:识别标题、正文、列表、表格、图片、图注、页眉和页脚等版面区域,结合坐标恢复多栏阅读顺序,并保证图片、表格与上下文在切片中的相对位置。
|
||||
- [ ] 向量召回(Embedding)
|
||||
- [ ] wps 格式支持
|
||||
|
||||
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Reference in New Issue
Block a user