83 lines
2.6 KiB
Python
83 lines
2.6 KiB
Python
# from paddleocr import PaddleOCR
|
|
# # 初始化 PaddleOCR 实例
|
|
# ocr = PaddleOCR(
|
|
# use_doc_orientation_classify=False,
|
|
# use_doc_unwarping=False,
|
|
# use_textline_orientation=False)
|
|
# # 对示例图像执行 OCR 推理
|
|
# result = ocr.predict(
|
|
# input="test1.png")
|
|
# # 可视化结果并保存 json 结果
|
|
# for res in result:
|
|
# res.print()
|
|
# res.save_to_img("output")
|
|
# res.save_to_json("output")
|
|
|
|
|
|
|
|
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": "bce-v3/ALTAK-5bKjjmEZxz7bnIjpWxxZT/723849a3548dc0d9f639b0ffaed5255a1ccf3f30", # your api_key
|
|
}
|
|
|
|
retriever_config = {
|
|
"module_name": "retriever",
|
|
"model_name": "embedding-v1",
|
|
"base_url": "https://qianfan.baidubce.com/v2",
|
|
"api_type": "qianfan",
|
|
"api_key": "bce-v3/ALTAK-5bKjjmEZxz7bnIjpWxxZT/723849a3548dc0d9f639b0ffaed5255a1ccf3f30", # your api_key
|
|
}
|
|
|
|
pipeline = PPChatOCRv4Doc(
|
|
use_doc_orientation_classify=False,
|
|
use_doc_unwarping=False
|
|
)
|
|
|
|
visual_predict_res = pipeline.visual_predict(
|
|
input="https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/vehicle_certificate-1.png",
|
|
use_common_ocr=True,
|
|
use_seal_recognition=True,
|
|
use_table_recognition=True,
|
|
)
|
|
|
|
mllm_predict_info = None
|
|
use_mllm = False
|
|
# 如果使用多模态大模型，需要启动本地 mllm 服务，可以参考文档：https://github.com/PaddlePaddle/PaddleX/blob/release/3.0/docs/pipeline_usage/tutorials/vlm_pipelines/doc_understanding.md 进行部署，并更新 mllm_chat_bot_config 配置。
|
|
if use_mllm:
|
|
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
|
|
}
|
|
|
|
mllm_predict_res = pipeline.mllm_pred(
|
|
input="test1.png",
|
|
key_list=["Gross Weight"],
|
|
mllm_chat_bot_config=mllm_chat_bot_config,
|
|
)
|
|
mllm_predict_info = mllm_predict_res["mllm_res"]
|
|
|
|
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
|
|
)
|
|
chat_result = pipeline.chat(
|
|
key_list=["Gross Weight"],
|
|
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) |