Update README.md

README.md

@@ -90,11 +90,23 @@ Install `gradio` first.
 pip install gradio
 ```
 
-Adapt the code in `pipeline_gradio.py` according to your device.
+Clone demo source code.
 
-- For M1/M2/M3 users, please make sure `model = model.to(device='mps', dtype=torch.float16)` then run `PYTORCH_ENABLE_MPS_FALLBACK=1 python pipeline_gradio.py`.
-- For x86 CPU users, please remove `model = model.to(device)` then run `python pipeline_gradio.py`.
-- For x86 CPU + Nvidia GPU users, please make sure `model = model.to('cuda')` then run `python pipeline_gradio.py`.
+- For retrieval-only demo (without generation), you should clone https://huggingface.co/spaces/bokesyo/MiniCPM_Visual_Document_Retriever_Demo.
+- For retrieval and generation (full RAG pipeline), you should clone https://huggingface.co/spaces/bokesyo/MiniCPMV-RAG-PDFQA.
+
+```bash
+git clone https://huggingface.co/spaces/bokesyo/MiniCPM_Visual_Document_Retriever_Demo
+git clone https://huggingface.co/spaces/bokesyo/MiniCPMV-RAG-PDFQA
+```
+
+For `retrieval and generation` demo, you need to also install `flash_attn`.
+
+Adapt the code in `app.py` according to your device.
+
+- For M1/M2/M3 users, please make sure `model = model.to(device='mps', dtype=torch.float16)` then run `PYTORCH_ENABLE_MPS_FALLBACK=1 python app.py`.
+- For x86 CPU users, please remove `model = model.to(device)` then run `python app.py`.
+- For x86 CPU + Nvidia GPU users, please make sure `model = model.to('cuda')` then run `python app.py`.
 - If you encountered an error, please open an issue [here](https://huggingface.co/RhapsodyAI/minicpm-visual-embedding-v0/discussions), we will respond soon.