Update demo vllm script and docs

README.md

@@ -560,18 +560,18 @@ CUDA_VISIBLE_DEVICES=0 vllm serve rednote-hilab/dots.ocr-1.5 --tensor-parallel-s
 CUDA_VISIBLE_DEVICES=0 vllm serve rednote-hilab/dots.ocr-1.5-svg --tensor-parallel-size 1 --gpu-memory-utilization 0.9 --chat-template-content-format string --served-model-name model --trust-remote-code
 
 # vLLM API Demo
-# See dots_ocr/model/inference.py for details on parameter and prompt settings 
+# See dots_ocr/model/inference.py and dots_ocr/utils/prompts.py for details on parameter and prompt settings 
 # that help achieve the best output quality.
 ## document parsing
-python3 ./demo/demo_vllm.py --prompt_mode prompt_layout_all_en
+python3 ./demo/demo_vllm.py --prompt_mode prompt_layout_all_en 
 ## web parsing 
-
+python3 ./demo/demo_vllm.py --prompt_mode prompt_web_parsing --image_path ./assets/showcase_dots_ocr_1_5/origin/webpage_1.png
 ## scene spoting
-
+python3 ./demo/demo_vllm.py --prompt_mode prompt_scene_spotting --image_path ./assets/showcase_dots_ocr_1_5/origin/scene_1.jpg
 ## image parsing with svg code
-
+python3 ./demo/demo_vllm_svg.py --prompt_mode prompt_image_to_svg 
 ## general qa
-
+python3 ./demo/demo_vllm_general.py
 ```
 
 ### Hugginface inference

demo/demo_vllm.py

@@ -11,6 +11,7 @@ parser = argparse.ArgumentParser()
 parser.add_argument("--ip", type=str, default="localhost")
 parser.add_argument("--port", type=str, default="8000")
 parser.add_argument("--model_name", type=str, default="rednote-hilab/dots.ocr")
+parser.add_argument("--image_path", type=str, default="demo/demo_image1.jpg")
 parser.add_argument("--prompt_mode", type=str, default="prompt_layout_all_en",help=(
         "Choose a task prompt: "
         "prompt_layout_all_en=full document layout+OCR to JSON/MD; "
@@ -28,7 +29,7 @@ require_version("openai>=1.5.0", "To fix: pip install openai>=1.5.0")
 
 def main():
     addr = f"http://{args.ip}:{args.port}/v1"
-    image_path = "demo/demo_image1.jpg"
+    image_path = args.image_path
     prompt = dict_promptmode_to_prompt[args.prompt_mode]
     image = Image.open(image_path)
     response = inference_with_vllm(

requirements.txt

@@ -4,7 +4,7 @@ gradio_image_annotation
 PyMuPDF
 openai
 qwen_vl_utils
-transformers==4.51.3
+transformers==4.56.1
 huggingface_hub
 modelscope
 # flash-attn==2.8.0.post2  # to speed up inference need flash-attn