Go to file
Кирилл Блинов b5f7c6327e Add tiling OCR, preprocess and visualization tools
- tiling_ocr.py: split large drawings into overlapping tiles for better small-text recognition
- preprocess_for_ocr.py: CLAHE + unsharp mask for enhancing blueprint contrast
- visualize_dimensions.py: draw bounding boxes around detected dimension numbers
- compare_ocr.py: side-by-side visualization of normal vs tiling OCR results
- dimension_extractor.py: line-based dimension detection with pixel verification
- ocr_qwen.py: Alibaba Cloud qwen-vl-ocr client with resize and regex fallback parser
- test_qwen_ocr.py: standalone test for qwen OCR
- process_any_pdf.py: add --use-tiling flag to switch between normal and tiling OCR
2026-06-01 12:29:26 +03:00
output Add PDF OCR pipeline and project indexes for Кронштадтский and 123 2026-05-29 01:04:01 +03:00
output_123 Add PDF OCR pipeline and project indexes for Кронштадтский and 123 2026-05-29 01:04:01 +03:00
.env.example Add RAG pipeline: LightRAG indexer, OpenCode API, VLM describer, and test tools 2026-05-29 09:54:37 +03:00
.gitignore Add RAG pipeline: LightRAG indexer, OpenCode API, VLM describer, and test tools 2026-05-29 09:54:37 +03:00
123.pdf Add PDF source files and remove *.pdf from gitignore 2026-05-29 01:45:03 +03:00
AGENTS.md Add RAG pipeline: LightRAG indexer, OpenCode API, VLM describer, and test tools 2026-05-29 09:54:37 +03:00
build_index.py Add PDF OCR pipeline and project indexes for Кронштадтский and 123 2026-05-29 01:04:01 +03:00
compare_ocr.py Add tiling OCR, preprocess and visualization tools 2026-06-01 12:29:26 +03:00
dimension_extractor.py Add tiling OCR, preprocess and visualization tools 2026-06-01 12:29:26 +03:00
ocr_qwen.py Add tiling OCR, preprocess and visualization tools 2026-06-01 12:29:26 +03:00
preprocess_for_ocr.py Add tiling OCR, preprocess and visualization tools 2026-06-01 12:29:26 +03:00
process_any_pdf.py Add tiling OCR, preprocess and visualization tools 2026-06-01 12:29:26 +03:00
process_pdf_full.py Add RAG pipeline: LightRAG indexer, OpenCode API, VLM describer, and test tools 2026-05-29 09:54:37 +03:00
process_pdf.py Add RAG pipeline: LightRAG indexer, OpenCode API, VLM describer, and test tools 2026-05-29 09:54:37 +03:00
rag_indexer.py Add RAG pipeline: LightRAG indexer, OpenCode API, VLM describer, and test tools 2026-05-29 09:54:37 +03:00
rag_query.py Add RAG pipeline: LightRAG indexer, OpenCode API, VLM describer, and test tools 2026-05-29 09:54:37 +03:00
README_RAG.md Add RAG pipeline: LightRAG indexer, OpenCode API, VLM describer, and test tools 2026-05-29 09:54:37 +03:00
requirements.txt Add RAG pipeline: LightRAG indexer, OpenCode API, VLM describer, and test tools 2026-05-29 09:54:37 +03:00
run_pipeline.bat Add RAG pipeline: LightRAG indexer, OpenCode API, VLM describer, and test tools 2026-05-29 09:54:37 +03:00
run_pipeline.sh Add RAG pipeline: LightRAG indexer, OpenCode API, VLM describer, and test tools 2026-05-29 09:54:37 +03:00
test_model.py Add RAG pipeline: LightRAG indexer, OpenCode API, VLM describer, and test tools 2026-05-29 09:54:37 +03:00
test_qwen_ocr.py Add tiling OCR, preprocess and visualization tools 2026-06-01 12:29:26 +03:00
tiling_ocr.py Add tiling OCR, preprocess and visualization tools 2026-06-01 12:29:26 +03:00
visualize_dimensions.py Add tiling OCR, preprocess and visualization tools 2026-06-01 12:29:26 +03:00
vlm_describer.py Add RAG pipeline: LightRAG indexer, OpenCode API, VLM describer, and test tools 2026-05-29 09:54:37 +03:00
Кронштадтский 16-18 НК1_ОСК (v3).pdf Add PDF source files and remove *.pdf from gitignore 2026-05-29 01:45:03 +03:00