gmakstutis/ragflow
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
ragflow/rag
History
Debug Doctor 3e19044dee
Feat: add OCR's muti-gpus and parallel processing support (#5972) 
### What problem does this PR solve?

Add OCR's muti-gpus and parallel processing support

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

@yuzhichang I've tried to resolve the comments in #5697. OCR jobs can
now be done on both CPU and GPU. ( By the way, I've encountered a
“Generate embedding error” issue #5954 that might be due to my outdated
GPUs? idk. ) Please review it and give me suggestions.

GPU:

![gpu_ocr](https://github.com/user-attachments/assets/0ee2ecfb-a665-4e50-8bc7-15941b9cd80e)

![smi](https://github.com/user-attachments/assets/a2312f8c-cf24-443d-bf89-bec50503546d)

CPU:

![cpu_ocr](https://github.com/user-attachments/assets/1ba6bb0b-94df-41ea-be79-790096da4bf1)
2025-03-17 11:58:40 +08:00
..
app Feat: add OCR's muti-gpus and parallel processing support (#5972) 2025-03-17 11:58:40 +08:00
llm Refa: remove max toekns for image2txt models. (#6078) 2025-03-14 13:51:45 +08:00
nlp Fix: empty tag field issue. (#6103) 2025-03-14 17:35:57 +08:00
res Format file format from Windows/dos to Unix (#1949) 2024-08-15 09:17:36 +08:00
svr Feat: add OCR's muti-gpus and parallel processing support (#5972) 2025-03-17 11:58:40 +08:00
utils Introduced task priority (#6118) 2025-03-14 23:43:46 +08:00
__init__.py Update comments (#4569) 2025-01-21 20:52:28 +08:00
benchmark.py Refactor embedding batch_size (#3825) 2024-12-03 16:22:39 +08:00
prompts.py Fix: Reduce excessive IO operations by loading LLM factory configurations (#6047) 2025-03-14 09:54:38 +08:00
raptor.py Refactor graphrag to remove redis lock (#5828) 2025-03-10 15:15:06 +08:00
settings.py Introduced task priority (#6118) 2025-03-14 23:43:46 +08:00