from pathlib import Path
from paddleocr import PPStructureV3

pipeline = PPStructureV3()

# For Image
output = pipeline.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/pp_structure_v3_demo.png")

# 可视化结果并保存 json 结果
for res in output:
    res.print() 
    res.save_to_json(save_path="output") 
    res.save_to_markdown(save_path="output") 

# For PDF File
input_file = "./your_pdf_file.pdf"
output_path = Path("./output")

output = pipeline.predict(input_file)

markdown_list = []
markdown_images = []

for res in output:
    md_info = res.markdown
    markdown_list.append(md_info)
    markdown_images.append(md_info.get("markdown_images", {}))

markdown_texts = pipeline.concatenate_markdown_pages(markdown_list)

mkd_file_path = output_path / f"{Path(input_file).stem}.md"
mkd_file_path.parent.mkdir(parents=True, exist_ok=True)

with open(mkd_file_path, "w", encoding="utf-8") as f:
    f.write(markdown_texts)

for item in markdown_images:
    if item:
        for path, image in item.items():
            file_path = output_path / path
            file_path.parent.mkdir(parents=True, exist_ok=True)
            image.save(file_path)

from paddleocr import PPChatOCRv4Doc

chat_bot_config = {
    "module_name": "chat_bot",
    "model_name": "ernie-3.5-8k",
    "base_url": "https://qianfan.baidubce.com/v2",
    "api_type": "openai",
    "api_key": "api_key",  # your api_key
}

retriever_config = {
    "module_name": "retriever",
    "model_name": "embedding-v1",
    "base_url": "https://qianfan.baidubce.com/v2",
    "api_type": "qianfan",
    "api_key": "api_key",  # your api_key
}

mllm_chat_bot_config = {
    "module_name": "chat_bot",
    "model_name": "PP-DocBee",
    "base_url": "http://127.0.0.1:8080/",  # your local mllm service url
    "api_type": "openai",
    "api_key": "api_key",  # your api_key
}

pipeline = PPChatOCRv4Doc()

visual_predict_res = pipeline.visual_predict(
    input="https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/vehicle_certificate-1.png",
    use_doc_orientation_classify=False,
    use_doc_unwarping=False,
    use_common_ocr=True,
    use_seal_recognition=True,
    use_table_recognition=True,
)

visual_info_list = []
for res in visual_predict_res:
    visual_info_list.append(res["visual_info"])
    layout_parsing_result = res["layout_parsing_result"]

vector_info = pipeline.build_vector(
    visual_info_list, flag_save_bytes_vector=True, retriever_config=retriever_config
)
mllm_predict_res = pipeline.mllm_pred(
    input="vehicle_certificate-1.png",
    key_list=["驾驶室准乘人数"],
    mllm_chat_bot_config=mllm_chat_bot_config,
)
mllm_predict_info = mllm_predict_res["mllm_res"]
chat_result = pipeline.chat(
    key_list=["驾驶室准乘人数"],
    visual_info=visual_info_list,
    vector_info=vector_info,
    mllm_predict_info=mllm_predict_info,
    chat_bot_config=chat_bot_config,
    retriever_config=retriever_config,
)
print(chat_result)