From 682cad6910cf61595a5bb7b538073beb4519985b Mon Sep 17 00:00:00 2001 From: HuangHai <10402852@qq.com> Date: Fri, 4 Jul 2025 20:39:41 +0800 Subject: [PATCH] 'commit' --- .../Tools/T1_Office_document_test.py | 47 ++++++++++- dsRagAnything/Tools/T2_End_to_End.py | 80 +++++++++++++++++++ 2 files changed, 124 insertions(+), 3 deletions(-) create mode 100644 dsRagAnything/Tools/T2_End_to_End.py diff --git a/dsRagAnything/Tools/T1_Office_document_test.py b/dsRagAnything/Tools/T1_Office_document_test.py index 51b4871a..50476ba5 100644 --- a/dsRagAnything/Tools/T1_Office_document_test.py +++ b/dsRagAnything/Tools/T1_Office_document_test.py @@ -18,7 +18,7 @@ Office文档解析测试脚本 - RAG-Anything项目 import argparse import sys from pathlib import Path -from raganything import RAGAnything +from raganything import RAGAnything, RAGAnythingConfig def check_libreoffice_installation(): @@ -28,6 +28,8 @@ def check_libreoffice_installation(): 返回: bool: 如果LibreOffice可用返回True，否则返回False """ + + """ import subprocess # 尝试不同的LibreOffice命令名称 @@ -55,6 +57,8 @@ def check_libreoffice_installation(): print(" - Ubuntu/Debian: sudo apt-get install libreoffice") print(" - CentOS/RHEL: sudo yum install libreoffice") return False + """ + return True def test_office_document_parsing(file_path: str): @@ -67,6 +71,9 @@ def test_office_document_parsing(file_path: str): 返回: bool: 解析成功返回True，否则返回False """ + # 在test_office_document_parsing函数中添加 + import os + os.environ["LIBREOFFICE_PATH"] = "C:\\Program Files\\LibreOffice\\program" print(f"🧪 测试Office文档解析: {file_path}") # 检查文件是否存在且是支持的Office格式 @@ -92,15 +99,43 @@ def test_office_document_parsing(file_path: str): rag = RAGAnything(config=config) try: + # 添加MinerU安装检查 + from raganything.mineru_parser import MineruParser + if not MineruParser.check_installation(): + print("❌ MinerU未正确安装") + return False + + # 确保output_dir已定义 + output_dir = "./test_output" + Path(output_dir).mkdir(exist_ok=True) + + # 添加PDF转换检查 + pdf_path = Path(output_dir) / f"{file_path.stem}.pdf" + print(f"PDF转换路径: {pdf_path}") + if pdf_path.exists(): + print(f"✅ PDF已生成，大小: {pdf_path.stat().st_size}字节") + else: + print("❌ PDF转换失败") + # 使用MinerU测试文档解析 print("\n🔄 使用MinerU测试文档解析...") + + # 使用绝对路径确保输出目录位置明确 + output_dir = Path("d:/dsWork/dsProject/dsRagAnything/Tools/test_output").absolute() + output_dir.mkdir(exist_ok=True) + content_list, md_content = rag.parse_document( file_path=str(file_path), - output_dir="./test_output", + output_dir=str(output_dir), parse_method="auto", display_stats=True, ) - + + # 检查输出目录内容 + print(f"\n📂 输出目录内容({output_dir}):") + for f in output_dir.glob("*"): + print(f" - {f.name}") + print("✅ 解析成功!") print(f" 📊 内容块数量: {len(content_list)}") print(f" 📝 Markdown长度: {len(md_content)} 字符") @@ -167,6 +202,10 @@ def test_office_document_parsing(file_path: str): print("📁 输出文件保存到: ./test_output") return True + # 在test_office_document_parsing函数中添加 + pdf_path = Path(output_dir) / f"{file_path.stem}.pdf" + print(f"PDF文件内容预览(前100字符): {pdf_path.read_text()[:100]}") + except Exception as e: print(f"\n❌ Office文档解析失败: {str(e)}") import traceback @@ -203,3 +242,5 @@ def main(): if __name__ == "__main__": sys.exit(main()) + + diff --git a/dsRagAnything/Tools/T2_End_to_End.py b/dsRagAnything/Tools/T2_End_to_End.py new file mode 100644 index 00000000..769e526b --- /dev/null +++ b/dsRagAnything/Tools/T2_End_to_End.py @@ -0,0 +1,80 @@ +import asyncio +from raganything import RAGAnything +from lightrag.llm.openai import openai_complete_if_cache, openai_embed +from lightrag.utils import EmbeddingFunc + +async def main(): + # Initialize RAGAnything + rag = RAGAnything( + working_dir="./rag_storage", + llm_model_func=lambda prompt, system_prompt=None, history_messages=[], **kwargs: openai_complete_if_cache( + "gpt-4o-mini", + prompt, + system_prompt=system_prompt, + history_messages=history_messages, + api_key="your-api-key", + **kwargs, + ), + vision_model_func=lambda prompt, system_prompt=None, history_messages=[], image_data=None, **kwargs: openai_complete_if_cache( + "gpt-4o", + "", + system_prompt=None, + history_messages=[], + messages=[ + {"role": "system", "content": system_prompt} if system_prompt else None, + {"role": "user", "content": [ + {"type": "text", "text": prompt}, + {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_data}"}} + ]} if image_data else {"role": "user", "content": prompt} + ], + api_key="your-api-key", + **kwargs, + ) if image_data else openai_complete_if_cache( + "gpt-4o-mini", + prompt, + system_prompt=system_prompt, + history_messages=history_messages, + api_key="your-api-key", + **kwargs, + ), + embedding_func=EmbeddingFunc( + embedding_dim=3072, + max_token_size=8192, + func=lambda texts: openai_embed( + texts, + model="text-embedding-3-large", + api_key=api_key, + base_url=base_url, + ), + ), + ) + + # Process a document + await rag.process_document_complete( + file_path="path/to/your/document.pdf", + output_dir="./output", + parse_method="auto" + ) + + # Query the processed content + # Pure text query - for basic knowledge base search + text_result = await rag.aquery( + "What are the main findings shown in the figures and tables?", + mode="hybrid" + ) + print("Text query result:", text_result) + + # Multimodal query with specific multimodal content + multimodal_result = await rag.aquery_with_multimodal( + "Explain this formula and its relevance to the document content", + multimodal_content=[{ + "type": "equation", + "latex": "P(d|q) = \\frac{P(q|d) \\cdot P(d)}{P(q)}", + "equation_caption": "Document relevance probability" + }], + mode="hybrid" +) + print("Multimodal query result:", multimodal_result) + +if __name__ == "__main__": + asyncio.run(main()) \ No newline at end of file